CN113361413B - Mileage display area detection method, device, equipment and storage medium - Google Patents
Mileage display area detection method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113361413B CN113361413B CN202110635677.2A CN202110635677A CN113361413B CN 113361413 B CN113361413 B CN 113361413B CN 202110635677 A CN202110635677 A CN 202110635677A CN 113361413 B CN113361413 B CN 113361413B
- Authority
- CN
- China
- Prior art keywords
- initial
- image
- detected
- region
- standard
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 97
- 238000010586 diagram Methods 0.000 claims abstract description 65
- 238000000034 method Methods 0.000 claims abstract description 63
- 238000012216 screening Methods 0.000 claims abstract description 47
- 238000012545 processing Methods 0.000 claims abstract description 27
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 24
- 239000013598 vector Substances 0.000 description 20
- 238000013528 artificial neural network Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 239000013589 supplement Substances 0.000 description 3
- 238000002372 labelling Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the application discloses a method, a device, equipment and a storage medium for detecting a mileage display area, wherein the method comprises the following steps: processing an image to be detected to obtain at least one initial region associated with a mileage display region in the image to be detected and initial characteristic data corresponding to the at least one initial region respectively; performing feature matching on at least one piece of initial feature data and standard feature data of a standard template diagram associated with the image to be detected, and obtaining a feature matching result; performing primary screening on each initial region according to the feature matching result to obtain at least one target region; performing secondary screening on each target area to obtain a prediction area of the mileage display area; through the technical scheme, the target detection process is optimized, and the recall rate of target detection is improved.
Description
Technical Field
The embodiment of the application relates to the technical field of target detection, in particular to a method, a device, equipment and a storage medium for detecting a mileage display area.
Background
Object detection is an important application of computer vision, for example, detecting a target object such as a face, a vehicle, or a building from an image. In the solution provided in the related art, a target detection model is usually trained, and target detection is achieved through the trained target detection model.
However, due to the influence of factors such as illumination conditions and photographing angles, when inputting an image to be recognized into a target detection model, when detecting a target in the image to be recognized, even if the image to be recognized has a target to be detected, there is a possibility that there is a recognition failure or a recognition error.
Therefore, in view of the problems existing in the prior art, improvements are needed.
Disclosure of Invention
The application provides a mileage display area detection method, a mileage display area detection device, mileage display area detection equipment and a storage medium, so as to optimize a target detection process and improve a recall rate of target detection.
In a first aspect, an embodiment of the present application provides a mileage display area detection method, including:
Processing an image to be detected to obtain at least one initial region associated with a mileage display region in the image to be detected and initial characteristic data corresponding to the at least one initial region respectively;
Performing feature matching on at least one piece of initial feature data and standard feature data of a standard template diagram associated with the image to be detected, and obtaining a feature matching result;
performing primary screening on each initial region according to the feature matching result to obtain at least one target region;
And carrying out secondary screening on each target area to obtain a predicted area of the mileage display area.
In a second aspect, an embodiment of the present application further provides a mileage display area detecting apparatus, including:
The image processing module is used for processing the image to be detected to obtain at least one initial area associated with a mileage display area in the image to be detected and initial characteristic data corresponding to the at least one initial area respectively;
the matching module is used for carrying out feature matching on at least one piece of initial feature data and the standard feature data of the standard template diagram associated with the image to be detected, and obtaining a feature matching result;
The target area screening module is used for carrying out primary screening on each initial area according to the characteristic matching result to obtain at least one target area;
And the prediction area determining module is used for carrying out secondary screening on each target area to obtain a prediction area of the mileage display area.
In a third aspect, an embodiment of the present application further provides an electronic device, including:
One or more processors;
Storage means for storing one or more programs,
The one or more programs, when executed by the one or more processors, cause the one or more processors to implement any of the mileage display area detecting methods as provided by the embodiments of the first aspect.
In a sixth aspect, an embodiment of the present application further provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements any one of the mileage display area detecting methods provided in the embodiment of the first aspect.
According to the embodiment of the application, the image to be detected is processed to obtain at least one initial area associated with a mileage display area in the image to be detected and initial characteristic data corresponding to the at least one initial area respectively; performing feature matching on at least one piece of initial feature data and standard feature data of a standard template diagram associated with the image to be detected, and obtaining a feature matching result; performing primary screening on each initial region according to the feature matching result to obtain at least one target region; and carrying out secondary screening on each target area to obtain a predicted area of the mileage display area. According to the technical scheme, based on the feature matching result of the initial feature data and the standard feature data, the position areas with the possible driving mileage areas are initially screened, the position areas with the greater probability of the driving mileage areas are screened from the initial areas, the number of the initial areas is reduced, meanwhile, the initial areas can be screened in a purposeful manner, the target detection process is optimized, the recall rate of target detection is improved, and meanwhile, the target detection speed is also improved.
Drawings
FIG. 1 is a flowchart of a method for detecting a mileage display area according to an embodiment of the present application;
FIG. 2 is a flowchart of a method for detecting a mileage display area according to a second embodiment of the present application;
FIG. 3 is a schematic diagram illustrating a mileage display area detecting process according to a second embodiment of the present application;
FIG. 4 is a flowchart of a method for detecting a mileage display area according to a third embodiment of the present application;
Fig. 5 is a schematic diagram of a mileage display area detecting device according to a fourth embodiment of the present application;
fig. 6 is a schematic diagram of an electronic device according to a fifth embodiment of the present application.
Detailed Description
The application is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present application are shown in the drawings.
Before discussing exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart depicts steps as a sequential process, many of the steps may be implemented in parallel, concurrently, or with other steps. Furthermore, the order of the steps may be rearranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figures. The processes may correspond to methods, functions, procedures, subroutines, and the like.
Example 1
Fig. 1 is a flowchart of a method for detecting a mileage display area according to an embodiment of the present application. The embodiment of the application can be applied to the situation that the mileage display area is detected from the console image in the vehicle. The method may be performed by a mileage display area detecting apparatus, which may be implemented in software and/or hardware, and specifically configured in an electronic device, which may be a mobile terminal or a fixed terminal.
Referring to fig. 1, the mileage display area detection method provided by the embodiment of the application includes:
S110, processing the image to be detected to obtain at least one initial area and at least one initial area which are associated with the mileage display area in the image to be detected, wherein the initial characteristic data correspond to the at least one initial area respectively.
The image to be detected is an input vehicle center console image, a mileage display area, also called a mileage area, exists in the vehicle center console image, and the number in the mileage area is read to obtain how many kilometers the vehicle has travelled since leaving the factory. In general, the running mileage is one of important indexes for measuring the breakage rate of a vehicle, and therefore, it is important to identify the running mileage area in a console image in a vehicle.
The initial region refers to a location region identified as a possible mileage display region, and initial feature data is used to characterize the feature conditions of the initial regions, and each initial region can determine corresponding initial feature data.
In this embodiment, the image to be detected may be input to a pre-trained target detection model, so as to obtain initial feature data corresponding to at least one initial region and at least one initial region associated with a mileage display region in the image to be detected.
The target detection model may be a deep neural network mileage detection model, typically may be a neural network (BackPropagation Network, counter-propagation neural network) model, and is trained by a supervised learning method based on pre-labeled vehicle sample data.
Specifically, the vehicle sample data can be obtained by manually marking center console pictures of various vehicle types, vehicle systems and years and positioning driving mileage areas in the center console pictures. For simplicity, four vertices of the mileage area may be located in the center console picture, and a location area where the four vertices are located is determined as the mileage area.
In some embodiments, the target detection model may also be a deep neural network mileage detection model based on reinforcement learning, and according to a set target function and a reward value function, the intelligent agent interacts with the environment in a set environment, and as the interaction times increase, the model is continuously updated and evolved.
Alternatively, the initial feature data may be obtained from an initial region based on SIFT features (Scale-INVARIANT FEATURE TRANSFORM ). However, when the image quality of the image to be detected is not high, there may be an inaccurate or erroneous case of the acquired feature data.
Or alternatively, in order to obtain initial feature data with higher accuracy from the initial region, the image to be processed may be input to a deep neural network mileage detection model, and a detection result output by a detection head in the target detection model and a feature vector in a final layer of feature map output by a multi-scale feature fusion structure in the target detection model may be obtained.
The detection result includes a regression frame, confidence coefficient and coordinate point, and the regression frame is the initial region in the embodiment, and the feature vector in the final layer of feature map is the initial feature data in the embodiment. Each output of the depth neural network mileage detection model is in one-to-one correspondence, that is, one point in the confidence coefficient corresponds to one frame in the regression frame, one set of coordinates in the coordinate point, and the feature vector in the feature map.
It will be appreciated that the initial feature data determined by the deep neural network mileage detection model may better describe the feature conditions (e.g., size, rotational invariance) of the initial region, and the accuracy of the initial feature data obtained from the initial region is higher than the SIFT feature.
And S120, performing feature matching on at least one initial feature data and the standard feature data of the standard template diagram associated with the image to be detected, and obtaining a feature matching result.
The standard template image refers to a vehicle center console image similar to the image to be detected, namely the type of the vehicle center console image. It will be appreciated that the obtained images of the center console of the vehicle may be different for different types of vehicles, for example, the size and shape of the mileage area may be different for different types of vehicle center console images.
The standard feature data is obtained from a standard region in the standard template chart, and the standard region refers to a position region which is considered to possibly exist in a mileage display region, and the standard feature data is used for characterizing the feature condition of the standard region.
Optionally, the feature matching between the at least one initial feature data and the standard feature data of the standard template map associated with the image to be detected includes: and calculating the Hamming distance between at least one piece of initial characteristic data and the standard characteristic data of the standard template diagram associated with the image to be detected.
It can be understood that by calculating the hamming distance between the standard feature data and the initial feature data, the hamming distance is used as an evaluation standard of the feature matching similarity, and the difference between the features can be accurately measured without complex calculation, so that the method has high efficiency, and the feature matching speed is accelerated, thereby improving the target detection speed.
Optionally, feature matching can be performed on initial feature data corresponding to a part of initial regions in the initial regions and standard feature data of a standard template diagram associated with the image to be detected, so as to obtain feature matching results; of course, feature matching can be performed on the initial feature data corresponding to all the initial regions and the standard feature data of the standard template image associated with the image to be detected, so as to obtain feature matching results.
For example, feature matching may be performed on initial feature data corresponding to an initial region with higher confidence and standard feature data of a standard template image associated with an image to be detected according to the confidence of the initial region, so as to obtain a feature matching result.
Optionally, the standard feature data and the initial feature data may be feature vectors obtained based on a deep neural network mileage detection model; and performing feature matching on at least one initial feature data and the standard feature data of the standard template diagram associated with the image to be detected, and obtaining a feature matching result.
It can be understood that the traditional graphical SIFT feature matching method is easy to fail in matching when the difference of the conditions such as the size, the visual angle, the rotation angle, the illumination and the like of the image to be detected and the standard template image is large, and the algorithm calculated amount is large, so that the target detection speed is influenced. Compared with the traditional graphical SIFT feature matching mode, the feature vector obtained based on the depth neural network mileage detection model can fully utilize feature similarity, size and rotation invariance of the depth learning model, can accurately identify the image to be detected and the standard template image when the size, visual angle and rotation angle of the image to be detected are large in difference, and is high in robustness.
S130, performing primary screening on each initial area according to the feature matching result to obtain at least one target area.
The target area is a position area obtained after the initial areas are subjected to preliminary screening. Among these target areas, there is a greater probability that there is a location area of the mileage area.
In this embodiment, according to the obtained feature matching result, the initial feature data may be screened, and the initial region where the initial feature data (by comparing with a preset threshold) of the standard template image feature matching associated with the image to be detected is located is reserved, so that the initial region may be screened.
Specifically, if the feature matching is performed by calculating the hamming distance, the hamming distance in the feature matching result is not smaller than the preset distance threshold value, and is determined to be an incorrect matching, so that the incorrect matching is filtered; and judging that the Hamming distance in the feature matching result is a correct match when the Hamming distance is smaller than a preset distance threshold value, so as to keep. The preset distance threshold value can be set according to actual conditions and experience values.
And S140, performing secondary screening on each target area to obtain a predicted area of the mileage display area.
The prediction area is a position area of the area with the mileage, which is finally determined from the image to be detected.
In this embodiment, an NMS (Non-Maximum Suppression ) algorithm may be used to perform the secondary screening on each target area. The NMS algorithm is an algorithm for extracting a window with the highest score in the target detection result, and the window is the target area in this embodiment.
Specifically, in the process of detecting targets, since a plurality of detection windows are generated for the same target, but in fact, most of the windows are repeated, only one window is really needed, each target area is processed through an NMS algorithm, each target can be guaranteed to be detected only once, and therefore the frame with the best detection effect is found from each target area, namely, the position area of the area with the mileage is finally determined from the image to be detected.
According to the embodiment of the application, the image to be detected is processed to obtain at least one initial area associated with a mileage display area in the image to be detected and initial characteristic data corresponding to the at least one initial area respectively; performing feature matching on at least one piece of initial feature data and standard feature data of a standard template diagram associated with the image to be detected, and obtaining a feature matching result; performing primary screening on each initial region according to the feature matching result to obtain at least one target region; and carrying out secondary screening on each target area to obtain a predicted area of the mileage display area. According to the technical scheme, based on the feature matching result of the initial feature data and the standard feature data, the position areas with the possible driving mileage areas are initially screened, the position areas with the greater probability of the driving mileage areas are screened from the initial areas, the number of the initial areas is reduced, meanwhile, the initial areas can be screened in a purposeful manner, the target detection process is optimized, the recall rate of target detection is improved, and meanwhile, the target detection speed is also improved.
Example two
Fig. 2 is a flowchart of a mileage display area detecting method according to a second embodiment of the present application, where the scheme is optimized based on the foregoing embodiment.
Further, the operation of processing the image to be detected to obtain at least one initial region associated with a mileage display region in the image to be detected and initial feature data corresponding to at least one initial region respectively are thinned into the operation of inputting the image to be detected into a target detection model based on a first confidence threshold to obtain at least one first initial region associated with the mileage display region in the image to be detected; inputting the image to be detected into the target detection model based on a second confidence threshold value to obtain at least one second initial region associated with a mileage display region in the image to be detected and initial feature data corresponding to each second initial region; wherein the second confidence threshold is less than the first confidence threshold "; correspondingly, the operation of performing feature matching on at least one initial feature data and the standard feature data of the standard template diagram associated with the image to be detected to obtain a feature matching result is refined into the operation of performing feature matching on the initial feature data corresponding to at least one second initial region and the standard feature data of the standard template diagram associated with the image to be detected to obtain a feature matching result so as to define the image processing and feature matching process.
Wherein the same or corresponding terms as those of the above-described embodiments are not explained in detail herein.
Referring to fig. 2, the mileage display area detecting method provided in the present embodiment includes:
S210, inputting an image to be detected into a target detection model based on a first confidence threshold value, and obtaining at least one first initial area associated with a mileage display area in the image to be detected.
The target detection model is a pre-trained deep neural network mileage detection model.
In this embodiment, the first confidence threshold may be set according to the actual situation and specific requirements. For example, the first confidence threshold may be set to 0.95, and a regression box with a confidence level greater than 0.95 may be reserved as the first initial region according to the preset first confidence threshold.
S220, inputting the image to be detected into a target detection model based on a second confidence threshold value, and obtaining at least one second initial region associated with a mileage display region in the image to be detected and initial feature data corresponding to each second initial region; wherein the second confidence threshold is less than the first confidence threshold.
In this embodiment, the second confidence threshold may be set according to the actual situation and specific requirements as well. For example, the second confidence threshold may be set to 0.94, and a regression box with a confidence level greater than 0.94 may be reserved as the second initial region according to the preset second confidence threshold.
Alternatively, the second confidence threshold may be set based on empirical values, such as may be determined through extensive experimentation.
In an alternative embodiment, the second confidence threshold is 0.009 less than the first confidence threshold.
It should be noted that, since the second confidence threshold is smaller than the first confidence threshold, the number of second initial regions derived from the target detection model output is greater than the number of first initial regions, i.e., the number of initial regions derived based on the smaller confidence threshold is greater.
And S230, performing feature matching on the initial feature data corresponding to the at least one second initial region and the standard feature data of the standard template diagram associated with the image to be detected, and obtaining a feature matching result.
In this embodiment, in view of the more severe screening conditions of the higher confidence threshold, the number of the first initial areas obtained is smaller, and some location areas where the mileage areas may exist may be omitted. Based on the method, the initial feature data corresponding to a larger number of second initial areas are subjected to feature matching with the standard feature data of the standard template image associated with the image to be detected, so that the position areas where the mileage areas possibly exist are subjected to supplementary searching, and omission is avoided.
It can be understood that, due to the influence of factors such as illumination conditions and shooting angles, when an image to be identified is input into a target detection model and a target in the image to be identified is detected, even if the image to be identified has the target to be detected, there may be a situation that the identification fails or is wrong, that is, the detection of the target object is realized only through the target detection model, and there may be a situation that the recall rate is not high. The application fully utilizes the characteristic relation between the image to be detected and the standard template image to discover and supplement the position area possibly with the driving mileage area, thereby improving the recall rate of target detection.
Optionally, the standard feature data of the standard template map is determined in the following manner: inputting the standard template diagram into a target detection model based on a preset confidence threshold to obtain at least one standard region; and obtaining standard characteristic data corresponding to each standard region.
The target detection model can be a pre-trained deep neural network mileage detection model.
The preset confidence threshold may be the same as the first confidence threshold or the second confidence threshold; or the preset confidence threshold may be different from the first confidence threshold or the second confidence threshold, and the setting of the preset confidence threshold may be determined according to the actual situation, which is not particularly limited in the embodiment of the present application.
In an alternative embodiment, the preset confidence threshold may be the same as the second confidence threshold.
Optionally, the inputting the standard template map to the target detection model based on the preset confidence threshold value to obtain a standard area includes: inputting the standard template diagram into a target detection model based on a preset confidence threshold value to obtain at least one candidate standard region and candidate standard feature data corresponding to each candidate standard region; taking the candidate standard region meeting the cross ratio condition as the standard region; correspondingly, acquiring the standard characteristic data corresponding to the standard region comprises the following steps: and taking the candidate standard characteristic data corresponding to the standard region as the standard characteristic data.
Wherein, the cross ratio condition is a preset IoU (Intersection-over-Union) threshold condition, and the IoU threshold can be set according to the actual situation.
In this embodiment, the finally obtained standard feature data may be controlled by setting a preset confidence threshold and a cross-correlation condition.
In an alternative embodiment, by reasonably setting the preset confidence threshold and the cross ratio condition, the number of standard feature data can be controlled within a preset number range without reducing the accuracy of target detection, so that the occupation of storage space is reduced, and the target detection speed is improved.
Specifically, regression frames with confidence degrees higher than a preset confidence degree threshold value can be found first, ioU of the regression frames and a pre-labeled real frame are calculated, confidence degree point sets larger than the IoU threshold value are reserved, feature vectors corresponding to the points in the feature images are stored, the number of the feature vectors of each template image is smaller than 20, and the length of each feature vector is 256.
S240, performing preliminary screening on each initial area according to the feature matching result to obtain at least one target area.
Wherein each initial region includes a first initial region and a second initial region.
In this embodiment, the second initial regions may be initially screened according to the feature matching result, without initially screening the first initial regions, because the first initial region is a location region determined with a higher confidence, and is generally considered to be a location region where a mileage region exists with a higher probability.
Specifically, the process of performing the preliminary screening on each initial region according to the feature matching result may include: for each feature vector in the standard template diagram, carrying out feature matching on the feature vector and each feature vector of the first initial area in sequence; and reserving a first initial area corresponding to the feature vector with the highest matching degree in the feature matching result, and finally, screening a second initial area to obtain position areas with the same number as the feature vectors of the standard template diagram, namely obtaining a target area.
In this embodiment, the second initial regions with successful feature matching in the feature matching result can be reserved, so that effective identification of the position regions where the mileage number regions may exist is realized, the condition that the target regions are omitted under higher confidence level is avoided, and the purpose of screening each second initial region is achieved.
Optionally, the performing a preliminary screening on each initial area according to the feature matching result to obtain at least one target area includes: and combining the second initial region successfully matched with the first initial region to obtain at least one target region.
The first initial region may be understood as a normal recognition result obtained based on the target detection model.
In this embodiment, the second initial area with successfully matched feature data is used as a supplement to the normal recognition result, the location area where the mileage number area may exist is expanded into the target area, and the recall rate of target detection can be increased from 95% to 96% during the test.
It can be appreciated that the recall rate of target detection is improved by combining the second initial region successfully matched with the first initial region to supplement the normal recognition result.
It should be noted that, if there is no standard template diagram associated with the image to be detected, the embodiment of the present application may directly perform secondary screening based on the first initial area to obtain the predicted area of the mileage display area.
S250, performing secondary screening on each target area to obtain a predicted area of the mileage display area.
Referring to a schematic diagram of a mileage display area detection process shown in fig. 3, the target detection process is mainly implemented by two modules, namely, a standard feature vector offline calculation module and a center console mileage area online detection module. The target detection model selects RETINAFACE algorithm (a single-stage target detection algorithm special for detecting the face) model, and uses a high-resolution network as a backbone network, and the target detection model outputs confidence, a regression frame, coordinate points and a final layer of characteristic diagram of the backbone network, wherein the outputs are in one-to-one correspondence; the data quantity of the feature vectors stored in each standard template diagram is not more than n×256 floating point numbers, namely, the number of the feature vectors in each standard template diagram is less than n (for example, n can be 20), and the length of each feature vector is 256, so that the occupied storage space and the reading time are greatly reduced.
Specifically, fig. 3 exemplarily shows a center console mileage detection method based on deep learning feature similarity matching, and the implementation process of the method mainly includes two stages: the first stage is common confidence level screening under higher confidence level, and x positions can be obtained; and in the second stage, calculating the most similar feature vector under lower confidence coefficient, merging the second detection result (n results are selected from y results) corresponding to the feature vector in the standard template diagram in the feature matching result, which is the highest in feature vector matching degree, into the first stage result, and then adopting an NMS algorithm to process the expanded first stage result (n+x results) to obtain a final detection result, thereby improving the recall rate of target detection.
On the basis of the embodiment, the method and the device for detecting the target clearly determine the process of target detection, and input the image to be detected into a target detection model based on a first confidence threshold to obtain at least one first initial area associated with a mileage display area in the image to be detected; inputting the image to be detected into the target detection model based on a second confidence threshold value to obtain at least one second initial region associated with a mileage display region in the image to be detected and initial feature data corresponding to each second initial region; wherein the second confidence threshold is less than the first confidence threshold; and performing feature matching on the initial feature data corresponding to at least one second initial region and the standard feature data of the standard template diagram associated with the image to be detected. According to the technical scheme, based on the first confidence threshold and the second confidence threshold, the initial areas with different numbers can be obtained, the initial feature data corresponding to at least one second initial area under lower confidence level are subjected to feature matching with the standard feature data of the standard template image associated with the image to be detected, the second initial area with successfully matched features is reserved, the position area with the possible driving mileage area is effectively identified, the condition that the target area is omitted under higher confidence level is avoided, the target detection process is optimized through secondary screening on each target area, and the recall rate of target detection is improved.
Example III
Fig. 4 is a flowchart of a mileage display area detecting method according to a third embodiment of the present application, where the embodiment optimizes the above scheme based on the above embodiment.
Further, adding operation' acquires vehicle attribute data of a target vehicle corresponding to the image to be detected; wherein the vehicle attribute data comprises a vehicle type, a vehicle system and a year; and selecting a standard template diagram' from at least one candidate standard template diagram associated with the target vehicle according to the vehicle attribute data so as to perfect the selection process of the standard template diagram associated with the image to be detected.
Wherein the same or corresponding terms as those of the above-described embodiments are not explained in detail herein.
Referring to fig. 4, the mileage display area detecting method provided in the present embodiment includes:
s310, inputting the image to be detected into a target detection model based on a first confidence threshold value, and obtaining at least one first initial area associated with a mileage display area in the image to be detected.
S320, inputting the image to be detected into a target detection model based on a second confidence threshold value, and obtaining at least one second initial region associated with a mileage display region in the image to be detected and initial feature data corresponding to each second initial region; wherein the second confidence threshold is less than the first confidence threshold.
S330, acquiring vehicle attribute data of a target vehicle corresponding to the image to be detected; wherein, the vehicle attribute data includes a vehicle model, a train and a year.
In this embodiment, the target vehicle is a vehicle in the image to be detected, and the image to be detected may be identified by an image processing technology, so as to identify vehicle attribute data of the target vehicle, including a vehicle type, a vehicle system and a year.
In some embodiments, a manual labeling manner may also be adopted to determine vehicle attribute data of the target vehicle corresponding to the image to be detected, for example, the vehicle attribute data is stored in association with the image to be detected by means of a keyword field, and when the image to be detected is read, the vehicle attribute data of the target vehicle corresponding to the image to be detected can be automatically obtained.
S340, selecting a standard template diagram from at least one candidate standard template diagram associated with the target vehicle according to the vehicle attribute data.
In this embodiment, if a manual labeling manner is adopted to perform predetermined determination on vehicle attribute data of a target vehicle corresponding to an image to be detected and perform predetermined determination on vehicle attribute data of a vehicle standard template map in the candidate standard template map, a standard template map associated with the image to be detected may be determined by a field matching manner.
It can be understood that the characteristics among the images of the vehicles of the same type are more similar, so that the target detection of the image to be detected is facilitated, and the accuracy of the target detection can be effectively improved.
In some embodiments, if the vehicle attribute data is not determined for each image in advance, the image to be detected may be identified by an image processing technique, and the vehicle attribute data of the vehicle may be identified from the image. However, in the image recognition method, there are cases where the recognition fails, such as the year of the vehicle cannot be recognized specifically.
Thus, in some embodiments, a standard template map may also be provided that determines proximity associated with the image to be detected in the event that the age of the vehicle cannot be accurately identified.
Optionally, the selecting a standard template map from at least one candidate standard template map associated with the target vehicle according to the vehicle attribute data includes: and if at least one candidate standard template map associated with the target vehicle does not contain the candidate standard template map corresponding to the annual fee of the target vehicle, selecting the candidate standard template map adjacent to the annual fee or the annual fee without the annual fee of the target vehicle as the standard template map.
In this embodiment, an annual fee-free comprehensive candidate standard template map may be determined for selection according to requirements and actual conditions, for example, features of vehicle template maps of the same vehicle type and vehicle system within a set time may be fused to construct a corresponding annual fee-free candidate standard template map. In addition, when the candidate standard template images corresponding to the years are not matched, the candidate standard template images of the adjacent years can be selected as standard template images, and the types of the vehicle template images of the adjacent years are relatively close, so that the selection can be directly performed.
It can be understood that the matching of the vehicle type and the vehicle system can be performed besides the strict matching of the vehicle type, the vehicle system and the year money, the standard template diagram related to the image to be detected is determined from the candidate standard template diagrams, and the flexibility of the standard template diagram determining process is improved.
And S350, performing feature matching on at least one piece of initial feature data and the standard feature data of the standard template diagram associated with the image to be detected.
S360, performing primary screening on each initial area according to the feature matching result to obtain at least one target area.
And S370, performing secondary screening on each target area to obtain a predicted area of the mileage display area.
On the basis of the embodiment, the method and the device for determining the standard template map are clear in the determining process of the standard template map related to the image to be detected, and vehicle attribute data of the target vehicle corresponding to the image to be detected are obtained; wherein the vehicle attribute data comprises a vehicle type, a vehicle system and a year; and selecting a standard template diagram from at least one candidate standard template diagram associated with the target vehicle according to the vehicle attribute data. Through the technical scheme, the standard template diagram associated with the image to be detected is determined, feature matching can be performed according to the standard feature data of the determined standard template diagram, data support is provided for performing feature matching on the standard feature data of the standard template diagram associated with the image to be detected and the initial feature data, and the target detection process is optimized.
Example IV
Fig. 5 is a schematic structural diagram of a mileage display area detecting device according to a fourth embodiment of the present application. Referring to fig. 5, an apparatus for detecting a mileage display area according to an embodiment of the present application includes: an image processing module 410, a matching module 420, a target region screening module 430, and a prediction region determination module 440.
The image processing module 410 is configured to process an image to be detected to obtain at least one initial region associated with a mileage display region in the image to be detected and initial feature data corresponding to the at least one initial region respectively;
The matching module 420 is configured to perform feature matching on at least one of the initial feature data and standard feature data of a standard template map associated with the image to be detected, so as to obtain a feature matching result;
The target area screening module 430 is configured to perform primary screening on each of the initial areas according to the feature matching result, so as to obtain at least one target area;
And the prediction area determining module 440 is configured to perform secondary screening on each target area to obtain a prediction area of the mileage display area.
According to the embodiment of the application, the image to be detected is processed to obtain at least one initial area associated with a mileage display area in the image to be detected and initial characteristic data corresponding to the at least one initial area respectively; performing feature matching on at least one piece of initial feature data and standard feature data of a standard template diagram associated with the image to be detected, and obtaining a feature matching result; performing primary screening on each initial region according to the feature matching result to obtain at least one target region; and carrying out secondary screening on each target area to obtain a predicted area of the mileage display area. According to the technical scheme, based on the feature matching result of the initial feature data and the standard feature data, the position areas with the possible driving mileage areas are initially screened, the position areas with the greater probability of the driving mileage areas are screened from the initial areas, the number of the initial areas is reduced, meanwhile, the initial areas can be screened in a purposeful manner, the target detection process is optimized, the recall rate of target detection is improved, and meanwhile, the target detection speed is also improved.
Further, the image processing module 410 includes:
The image processing first unit is used for inputting the image to be detected into a target detection model based on a first confidence threshold value to obtain at least one first initial area associated with a mileage display area in the image to be detected;
The image processing second unit is used for inputting the image to be detected into the target detection model based on a second confidence threshold value to obtain at least one second initial region associated with a mileage display region in the image to be detected and initial feature data corresponding to each second initial region; wherein the second confidence threshold is less than the first confidence threshold;
Accordingly, the matching module 420 includes:
And the feature matching unit is used for carrying out feature matching on the initial feature data corresponding to at least one second initial region and the standard feature data of the standard template image associated with the image to be detected, and obtaining a feature matching result.
Further, the target area screening module 430 includes:
and the target area screening unit is used for combining the second initial area successfully matched with the first initial area to obtain at least one target area.
Further, the matching module 420 includes:
And the hamming distance calculation unit is used for calculating the hamming distance of at least one standard characteristic data of the standard template diagram related to the image to be detected and the initial characteristic data.
Further, the apparatus further comprises: the standard characteristic data acquisition module comprises:
the standard region determining unit is used for inputting the standard template diagram into the target detection model based on a preset confidence threshold value to obtain at least one standard region;
the standard characteristic data acquisition unit is used for acquiring standard characteristic data corresponding to each standard region.
Further, the apparatus further comprises: a template map determination module, the template map determination module comprising:
the attribute data acquisition unit is used for acquiring vehicle attribute data of the target vehicle corresponding to the image to be detected; wherein the vehicle attribute data comprises a vehicle type, a vehicle system and a year;
and the template diagram determining unit is used for selecting a standard template diagram from at least one candidate standard template diagram associated with the target vehicle according to the vehicle attribute data.
Further, the template map determining unit includes:
And the template diagram determining subunit is used for selecting the candidate standard template diagram adjacent to the annual money or the annual money-free standard template diagram of the target vehicle as the standard template diagram if the candidate standard template diagram corresponding to the annual money of the target vehicle is not contained in at least one candidate standard template diagram associated with the target vehicle.
The mileage display area detection device provided by the embodiment of the application can execute the mileage display area detection method provided by any embodiment of the application, and has the corresponding functional modules and beneficial effects of the execution method.
Example five
Fig. 6 is a block diagram of an electronic device according to a fifth embodiment of the present application. Fig. 6 illustrates a block diagram of an exemplary electronic device 512 suitable for use in implementing embodiments of the present application. The electronic device 512 shown in fig. 6 is merely an example, and should not be construed as limiting the functionality and scope of use of embodiments of the present application.
As shown in FIG. 6, the electronic device 512 is in the form of a general purpose computing device. Components of electronic device 512 may include, but are not limited to: one or more processors or processing units 516, a system memory 528, a bus 518 that connects the various system components (including the system memory 628 and the processing unit 516).
Bus 518 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, micro channel architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Electronic device 512 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by electronic device 512 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 528 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 530 and/or cache memory 532. The electronic device 512 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 534 may be used to read from or write to a non-removable, nonvolatile magnetic medium (not shown in FIG. 6, commonly referred to as a "hard disk drive"). Although not shown in fig. 6, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In such cases, each drive may be coupled to bus 518 through one or more data media interfaces. The system memory 528 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of embodiments of the application.
A program/utility 540 having a set (at least one) of program modules 542 may be stored in, for example, the system memory 528, such program modules 542 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 542 generally perform the functions and/or methods in the described embodiments of the application.
The electronic device 512 may also communicate with one or more external devices 514 (e.g., keyboard, pointing device, display 524, etc.), one or more devices that enable a user to interact with the electronic device 512, and/or any devices (e.g., network card, modem, etc.) that enable the electronic device 512 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 522. Also, the electronic device 512 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through the network adapter 520. As shown, network adapter 520 communicates with other modules of electronic device 512 over bus 518. It should be appreciated that although not shown in fig. 6, other hardware and/or software modules may be used in connection with electronic device 512, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
The processing unit 516 performs various functional applications and data processing by running at least one of other programs among a plurality of programs stored in the system memory 528, for example, implementing any one of the mileage display area detecting methods provided by the embodiments of the present application.
Example six
The sixth embodiment of the present application also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a mileage display area detecting method provided by any one of the embodiments of the present application, the method comprising:
Processing an image to be detected to obtain at least one initial region associated with a mileage display region in the image to be detected and initial characteristic data corresponding to the at least one initial region respectively; performing feature matching on at least one piece of initial feature data and standard feature data of a standard template diagram associated with the image to be detected, and obtaining a feature matching result; performing primary screening on each initial region according to the feature matching result to obtain at least one target region; and carrying out secondary screening on each target area to obtain a predicted area of the mileage display area.
From the above description of embodiments, it will be clear to a person skilled in the art that the present application may be implemented by means of software and necessary general purpose hardware, but of course also by means of hardware, although in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a FLASH Memory (FLASH), a hard disk, or an optical disk of a computer, etc., and include several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments of the present application.
It should be noted that, in the embodiment of the mileage display area detecting apparatus, each unit and module included are only divided according to the functional logic, but not limited to the above division, so long as the corresponding functions can be implemented; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present application.
Note that the above is only a preferred embodiment of the present application and the technical principle applied. It will be understood by those skilled in the art that the present application is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the application. Therefore, while the application has been described in connection with the above embodiments, the application is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the application, which is set forth in the following claims.
Claims (8)
1. A mileage display area detecting method, characterized by comprising:
Processing an image to be detected to obtain at least one initial region associated with a mileage display region in the image to be detected and initial characteristic data corresponding to the at least one initial region respectively;
Performing feature matching on at least one piece of initial feature data and standard feature data of a standard template diagram associated with the image to be detected, and obtaining a feature matching result;
performing primary screening on each initial region according to the feature matching result to obtain at least one target region;
performing secondary screening on each target area by using an NMS algorithm to obtain a predicted area of the mileage display area;
the processing the image to be detected to obtain at least one initial region associated with a mileage display region in the image to be detected and initial feature data corresponding to the at least one initial region respectively, including:
inputting the image to be detected into a target detection model based on a first confidence threshold value to obtain at least one first initial area associated with a mileage display area in the image to be detected;
inputting the image to be detected into the target detection model based on a second confidence threshold value to obtain at least one second initial region associated with a mileage display region in the image to be detected and initial feature data corresponding to each second initial region; wherein the second confidence threshold is less than the first confidence threshold;
Correspondingly, the feature matching of at least one initial feature data with the standard feature data of the standard template diagram associated with the image to be detected comprises the following steps:
performing feature matching on initial feature data corresponding to at least one second initial region and standard feature data of a standard template diagram associated with the image to be detected;
And performing preliminary screening on each initial region according to the feature matching result to obtain at least one target region, wherein the preliminary screening comprises the following steps:
and combining the second initial region successfully matched with the first initial region to obtain at least one target region.
2. The method of claim 1, wherein the feature matching of at least one of the initial feature data with standard feature data of a standard template map associated with the image to be detected comprises:
and calculating the Hamming distance between at least one piece of initial characteristic data and the standard characteristic data of the standard template diagram associated with the image to be detected.
3. The method of claim 1, wherein the standard feature data of the standard template map is determined by:
inputting the standard template diagram into a target detection model based on a preset confidence threshold to obtain at least one standard region;
and obtaining standard characteristic data corresponding to each standard region.
4. The method according to claim 1, wherein the standard template map associated with the image to be detected is determined by:
acquiring vehicle attribute data of a target vehicle corresponding to the image to be detected; wherein the vehicle attribute data comprises a vehicle type, a vehicle system and a year;
And selecting a standard template diagram from at least one candidate standard template diagram associated with the target vehicle according to the vehicle attribute data.
5. The method of claim 4, wherein selecting a standard template map from at least one candidate standard template map associated with the target vehicle based on the vehicle attribute data comprises:
And if at least one candidate standard template map associated with the target vehicle does not contain the candidate standard template map corresponding to the annual fee of the target vehicle, selecting the candidate standard template map adjacent to the annual fee or the annual fee without the annual fee of the target vehicle as the standard template map.
6. A mileage display area detecting apparatus, comprising:
The image processing module is used for processing the image to be detected to obtain at least one initial area associated with a mileage display area in the image to be detected and initial characteristic data corresponding to the at least one initial area respectively;
the matching module is used for carrying out feature matching on at least one piece of initial feature data and the standard feature data of the standard template diagram associated with the image to be detected, and obtaining a feature matching result;
the target area screening module is used for carrying out primary screening on each initial area according to the matching result to obtain at least one target area;
the prediction area determining module is used for carrying out secondary screening on each target area by utilizing an NMS algorithm to obtain a prediction area of the mileage display area;
The image processing module further includes:
The image processing first unit is used for inputting the image to be detected into a target detection model based on a first confidence threshold value to obtain at least one first initial area associated with a mileage display area in the image to be detected;
The image processing second unit is used for inputting the image to be detected into the target detection model based on a second confidence threshold value to obtain at least one second initial region associated with a mileage display region in the image to be detected and initial feature data corresponding to each second initial region; wherein the second confidence threshold is less than the first confidence threshold;
The matching module further comprises:
The feature matching unit is used for performing feature matching on initial feature data corresponding to at least one second initial region and standard feature data of a standard template diagram associated with the image to be detected;
the target area screening module further includes:
and the target area screening unit is used for combining the second initial area successfully matched with the first initial area to obtain at least one target area.
7. An electronic device, comprising:
One or more processors;
Storage means for storing one or more programs,
The one or more programs, when executed by the one or more processors, cause the one or more processors to implement a mileage display area detecting method according to any one of claims 1-5.
8. A computer-readable storage medium having stored thereon a computer program, wherein the program when executed by a processor implements a mileage display area detecting method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110635677.2A CN113361413B (en) | 2021-06-08 | 2021-06-08 | Mileage display area detection method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110635677.2A CN113361413B (en) | 2021-06-08 | 2021-06-08 | Mileage display area detection method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113361413A CN113361413A (en) | 2021-09-07 |
| CN113361413B true CN113361413B (en) | 2024-06-18 |
Family
ID=77533039
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110635677.2A Active CN113361413B (en) | 2021-06-08 | 2021-06-08 | Mileage display area detection method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113361413B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114241011A (en) * | 2022-02-22 | 2022-03-25 | 阿里巴巴达摩院(杭州)科技有限公司 | Object detection method, device, device and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255336A (en) * | 2018-09-29 | 2019-01-22 | 南京理工大学 | Arrester recognition methods based on crusing robot |
| CN110245544A (en) * | 2018-09-26 | 2019-09-17 | 浙江大华技术股份有限公司 | A kind of method and device of determining dead ship condition |
Family Cites Families (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9317752B2 (en) * | 2013-06-20 | 2016-04-19 | Xerox Corporation | Method for detecting large size and passenger vehicles from fixed cameras |
| CN105957345B (en) * | 2016-06-08 | 2017-10-31 | 南京航空航天大学 | Vehicle operation data processing method |
| CN107145833A (en) * | 2017-04-11 | 2017-09-08 | 腾讯科技（上海）有限公司 | The determination method and apparatus of human face region |
| CN106960207A (en) * | 2017-04-26 | 2017-07-18 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of car steering position gauge field multipointer instrument automatic recognition system and method based on template matches |
| US20200193225A1 (en) * | 2017-04-28 | 2020-06-18 | Toyota Motor Europe | System and method for detecting objects in a digital image, and system and method for rescoring object detections |
| CN109409385B (en) * | 2018-10-16 | 2021-02-19 | 南京鑫和汇通电子科技有限公司 | Automatic identification method for pointer instrument |
| CN109559300A (en) * | 2018-11-19 | 2019-04-02 | 上海商汤智能科技有限公司 | Image processing method, electronic equipment and computer readable storage medium |
| CN109670532B (en) * | 2018-11-23 | 2022-12-09 | 腾讯医疗健康(深圳)有限公司 | Method, device and system for identifying abnormality of biological organ tissue image |
| CN109815868B (en) * | 2019-01-15 | 2022-02-01 | 腾讯科技（深圳）有限公司 | Image target detection method and device and storage medium |
| CN109766878B (en) * | 2019-04-11 | 2019-06-28 | 深兰人工智能芯片研究院（江苏）有限公司 | A kind of method and apparatus of lane detection |
| CN110146121B (en) * | 2019-05-24 | 2021-02-09 | 安徽扬远信息科技有限公司 | Instrument panel performance evaluation control system |
| CN110222780B (en) * | 2019-06-12 | 2021-06-11 | 北京百度网讯科技有限公司 | Object detection method, device, equipment and storage medium |
| CN110378258B (en) * | 2019-07-04 | 2021-02-09 | 上海眼控科技股份有限公司 | Image-based vehicle seat information detection method and device |
| CN110517259A (en) * | 2019-08-30 | 2019-11-29 | 北京百度网讯科技有限公司 | A detection method, device, equipment and medium for product surface state |
| CN110991305B (en) * | 2019-11-27 | 2023-04-07 | 厦门大学 | Airplane detection method under remote sensing image and storage medium |
| CN111401424B (en) * | 2020-03-10 | 2024-01-26 | 北京迈格威科技有限公司 | Target detection method, device and electronic system |
| CN111239158A (en) * | 2020-03-13 | 2020-06-05 | 苏州鑫睿益荣信息技术有限公司 | Automobile instrument panel detection system and detection method based on machine vision |
| CN111523414B (en) * | 2020-04-13 | 2023-10-24 | 绍兴埃瓦科技有限公司 | Face recognition method, device, computer equipment and storage medium |
| WO2021212482A1 (en) * | 2020-04-24 | 2021-10-28 | 华为技术有限公司 | Method and apparatus for mining difficult case during target detection |
| CN111709416B (en) * | 2020-05-15 | 2024-02-02 | 珠海亿智电子科技有限公司 | License plate positioning method, device, system and storage medium |
| CN111832557A (en) * | 2020-06-04 | 2020-10-27 | 北京百度网讯科技有限公司 | Power grid inspection method and device, electronic equipment and storage medium |
| CN111768392B (en) * | 2020-06-30 | 2022-10-14 | 创新奇智(广州)科技有限公司 | Target detection method and device, electronic equipment and storage medium |
| CN112580657B (en) * | 2020-12-23 | 2022-11-01 | 陕西天诚软件有限公司 | Self-learning character recognition method |
-
2021
- 2021-06-08 CN CN202110635677.2A patent/CN113361413B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110245544A (en) * | 2018-09-26 | 2019-09-17 | 浙江大华技术股份有限公司 | A kind of method and device of determining dead ship condition |
| CN109255336A (en) * | 2018-09-29 | 2019-01-22 | 南京理工大学 | Arrester recognition methods based on crusing robot |
Non-Patent Citations (1)
| Title |
|---|
| 汽车里程表读数自动识别系统的研究与实现;李健 等;《新型工业化》;第6卷(第4期);第1-7页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113361413A (en) | 2021-09-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12227169B2 (en) | Method and apparatus for detecting parking space and direction and angle thereof, device and medium | |
| US11182592B2 (en) | Target object recognition method and apparatus, storage medium, and electronic device | |
| CN109344899B (en) | Multi-target detection method and device and electronic equipment | |
| CN110781885A (en) | Text detection method, device, medium and electronic equipment based on image processing | |
| WO2019033574A1 (en) | Electronic device, dynamic video face recognition method and system, and storage medium | |
| CN110807491A (en) | License plate image definition model training method, definition detection method and device | |
| CN110660102B (en) | Speaker recognition method, device and system based on artificial intelligence | |
| CN108428248B (en) | Vehicle window positioning method, system, equipment and storage medium | |
| CN112906823B (en) | Target object recognition model training method, recognition method and recognition device | |
| CN110598686A (en) | Invoice identification method, system, electronic equipment and medium | |
| CN102279926A (en) | Techniques in optical character recognition | |
| CN109409288B (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| CN114255381B (en) | Training method of image recognition model, image recognition method, device and medium | |
| CN113762455B (en) | Detection model training method, single word detection method, device, equipment and medium | |
| CN111275040B (en) | Positioning method and device, electronic device, computer-readable storage medium | |
| CN111723865A (en) | Method, apparatus and medium for evaluating performance of image recognition model and attack method | |
| JP6255944B2 (en) | Image analysis apparatus, image analysis method, and image analysis program | |
| CN113378852A (en) | Key point detection method and device, electronic equipment and storage medium | |
| CN116777899B (en) | Industrial image key point detection method, system and platform based on regression model | |
| CN111950345B (en) | Camera identification method and device, electronic equipment and storage medium | |
| CN113361413B (en) | Mileage display area detection method, device, equipment and storage medium | |
| CN111444911A (en) | Training method and device of license plate recognition model and license plate recognition method and device | |
| CN114445697A (en) | Target detection method and device, electronic equipment and storage medium | |
| CN109934858A (en) | Image registration method and device | |
| CN111860512B (en) | Vehicle identification method, device, electronic equipment and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |