CN115631356B - Method and device for identifying missing of road facility, storage medium and electronic device - Google Patents
Method and device for identifying missing of road facility, storage medium and electronic device Download PDFInfo
- Publication number
- CN115631356B CN115631356B CN202211496211.XA CN202211496211A CN115631356B CN 115631356 B CN115631356 B CN 115631356B CN 202211496211 A CN202211496211 A CN 202211496211A CN 115631356 B CN115631356 B CN 115631356B
- Authority
- CN
- China
- Prior art keywords
- facility
- road
- information
- condition
- shadow
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention provides a method and a device for identifying missing road facilities, a storage medium and an electronic device, and relates to the technical field of road facility inspection technology. The method comprises the following steps: acquiring initial image information of a target road; determining facility shadow information of a target area through a pre-trained object recognition model; under the condition that the facility shadow information meets a first position condition, carrying out first matching processing on the facility shadow information and preset facility reference information to obtain a first matching result; and determining that the road facility is missing under the condition that the first matching result does not meet a first matching condition. The invention solves the problem of low recognition precision of the loss of the road facilities, and further achieves the effect of improving the loss of the road facilities.
Description
Technical Field
The embodiment of the invention relates to the field of road facility inspection, in particular to a method and a device for identifying missing road facilities, a storage medium and an electronic device.
Background
In recent years, in order to respond to the purpose of garden-type urban construction, urban road construction in China also gradually decorates urban roads through flower boxes and the like, so that road greening is increased, and urban aesthetic feeling is improved.
Under the influence of severe weather such as typhoons, the flower box on the road is easy to lose and the like, or is influenced by traffic accidents, the flower box can be damaged, shifted and the like, particularly the shifting phenomenon, and accidents such as blockage, secondary impact and scratch on vehicles can be caused to road traffic when serious.
In the prior art, only the conditions of pit bags and the like of roads are automatically detected, and no scheme for effectively detecting the road flower box exists, so that the inspection can be performed only through a manual inspection mode, the labor is consumed, and the inspection efficiency is reduced.
Disclosure of Invention
The embodiment of the invention provides a method and a device for identifying missing road facilities, a storage medium and an electronic device, which are used for at least solving the problem of missing road flower boxes in the related technology.
According to an embodiment of the present invention, there is provided a method of identifying a loss of a road facility, including:
acquiring initial image information of a target road;
determining facility shadow information of a target area through a pre-trained object recognition model, wherein the target road comprises the target area, and the facility shadow information comprises the shadow information of road facilities of the target road;
under the condition that the facility shadow information meets a first position condition, carrying out first matching processing on the facility shadow information and preset facility reference information to obtain a first matching result;
and determining that the road facility is missing under the condition that the first matching result does not meet a first matching condition.
In an exemplary embodiment, after the determining the facility shadow information of the target area by the pre-trained object recognition model, the method further comprises:
under the condition that the facility shadow information meets a second position condition, carrying out second matching processing on the facility shadow information and the facility reference information to obtain a second matching result;
and determining that the road facility is missing under the condition that the second matching result meets the first matching condition.
In an exemplary embodiment, before the determining the facility shadow information of the target area by the pre-trained object recognition model, the method further comprises:
acquiring weather information and/or time information of the target road to determine an illumination angle of a target time period;
based on the illumination angle, the first location condition and/or the second location condition of a target time period is determined.
In an exemplary embodiment, after the obtaining weather information and/or time information of the target road to determine the illumination angle of the target time period, the method further includes:
acquiring road ponding information of the target road based on the initial image information under the condition that the weather information and/or the time information meet a first weather condition;
determining second facility shadow information of the target road based on the road water information;
performing third matching processing on the second facility shadow information and the facility shadow information to obtain a third matching result;
and determining that the road facility is missing when the third matching result does not meet the first matching condition.
In an exemplary embodiment, the method further comprises:
determining a road reference line of the target road and a facility reference line of the road facility through the object recognition model;
calculating a space included angle of the road datum line and the facility datum line to obtain a datum included angle;
and determining that the road facility has an ectopic condition under the condition that the reference included angle is larger than a first threshold value and smaller than a second threshold value.
According to another embodiment of the present invention, there is provided a facility missing identifying apparatus including:
the image acquisition module is used for acquiring initial image information of the target road;
an information determining module, configured to determine facility shadow information of a target area through a pre-trained object recognition model, where the target road includes the target area, and the facility shadow information includes shadow information of a road facility of the target road;
the first matching module is used for carrying out first matching processing on the facility shadow information and preset facility reference information under the condition that the facility shadow information meets a first position condition so as to obtain a first matching result;
and the first result judging module is used for determining that the road facility is missing under the condition that the first matching result does not meet the first matching condition.
In one exemplary embodiment, further comprising:
the second matching module is used for carrying out second matching processing on the facility shadow information and the facility reference information under the condition that the facility shadow information meets a second position condition after the facility shadow information of the target area is determined through the pre-trained object recognition model so as to obtain a second matching result;
and the second result judging module is used for determining that the road facility is missing under the condition that the second matching result meets the first matching condition.
In one exemplary embodiment, further comprising:
the weather information acquisition module is used for acquiring weather information and/or time information of the target road before the facility shadow information of the target area is determined through the pre-trained object recognition model so as to determine the illumination angle of the target time period;
and the condition generating module is used for determining the first position condition and/or the second position condition of the target time period based on the illumination angle.
According to a further embodiment of the invention, there is also provided a computer readable storage medium having stored therein a computer program, wherein the computer program is arranged to perform the steps of any of the method embodiments described above when run.
According to a further embodiment of the invention, there is also provided an electronic device comprising a memory having stored therein a computer program and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.
According to the invention, the automation of flower box identification is realized by comparing the facility shadows with the facility references, the calculation force requirement for identifying the flower box attributes is reduced, and the flower box identification efficiency is improved, so that the problem of low flower box identification precision can be solved, and the effect of improving the flower box identification precision and efficiency is achieved.
Drawings
Fig. 1 is a block diagram of a hardware configuration of a mobile terminal of a method for identifying a loss of a road facility according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method of identifying a loss of asset according to an embodiment of the invention;
FIG. 3 is a schematic diagram of a first embodiment of the present invention;
FIG. 4 is a schematic diagram II according to an embodiment of the present invention;
fig. 5 is a block diagram of a construction of a facility missing identifying apparatus according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings in conjunction with the embodiments.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order.
The method embodiments provided in the embodiments of the present application may be performed in a mobile terminal, a computer terminal or similar computing device. Taking the mobile terminal as an example, fig. 1 is a block diagram of a hardware structure of the mobile terminal of a method for identifying a loss of road facilities according to an embodiment of the present invention. As shown in fig. 1, a mobile terminal may include one or more (only one is shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a microprocessor MCU or a processing device such as a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 for communication functions and an input-output device 108. It will be appreciated by those skilled in the art that the structure shown in fig. 1 is merely illustrative and not limiting of the structure of the mobile terminal described above. For example, the mobile terminal may also include more or fewer components than shown in fig. 1, or have a different configuration than shown in fig. 1.
The memory 104 may be used to store a computer program, for example, a software program of application software and a module, such as a computer program corresponding to a method for identifying a loss of road facility in an embodiment of the present invention, and the processor 102 executes the computer program stored in the memory 104 to perform various functional applications and data processing, that is, implement the method described above. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, which may be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission means 106 is arranged to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, simply referred to as NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used to communicate with the internet wirelessly.
In this embodiment, there is provided a method for identifying a loss of a road facility, and fig. 2 is a flowchart of a method for identifying a loss of a road facility according to an embodiment of the present invention, as shown in fig. 2, the flowchart includes the steps of:
step S202, obtaining initial image information of a target road;
in this embodiment, the initial image information of the target road is acquired to identify facilities such as a flower box of the target road by means of image identification, thereby realizing automation of facility identification.
The target road comprises, but is not limited to, a road needing facility monitoring, which can be set manually according to administrative planning, can be determined according to an information acquisition range determined by equipment parameters of information acquisition equipment, and can be obtained by space division through a GIS technology; the method for acquiring the initial image information may be (but is not limited to) that an image or information acquisition is performed on a certain area by a visible light camera or a laser radar, or that an image acquisition is performed on a target road by an unmanned aerial vehicle carrying an onboard camera, and correspondingly, the initial image information also includes coordinate information of the target road, and the determination of the target road may be (but is not limited to) that the determination is performed by a trained neural network model such as yolo3 and yolo 5.
Step S204, determining facility shadow information of a target area through a pre-trained object recognition model, wherein the target road comprises the target area, and the facility shadow information comprises the shadow information of road facilities of the target road;
in this embodiment, the difficulty of recognizing shadows is smaller than that of recognizing specific objects, and the required calculation force is smaller, so that the efficiency of facility recognition can be improved, and the equipment cost required for recognition can be reduced.
The object recognition model may be, but not limited to, a model for recognizing a specific object such as CNN, RCNN, fast-RCNN, and the training process of the object recognition model may include, but is not limited to, a process of calculating intensity ratios of sunlight irradiated on three channels of RGB in the initial image information, and then performing segmentation calculation of a shadow region and a non-shadow region; the target area comprises (but is not limited to) areas 1-2m on two sides of a target road, a central shaft area of the road and the like, the road facilities comprise (but are not limited to) road flower boxes, trees, street lamps, protective fences, sound insulation screens and other road facilities, and in some special cases, special things such as vehicles, pedestrians, buildings, objects to be thrown on the road can be identified, and corresponding shadow information comprises (but is not limited to) information such as coordinate information and area information of shadows of the road facilities.
Step S206, performing first matching processing on the facility shadow information and preset facility reference information to obtain a first matching result under the condition that the facility shadow information meets a first position condition;
in this embodiment, as shown in fig. 3, in the case where the location of the road facility is normal and the shadow can be captured (i.e., the collecting device directs light), the road facility and the shadow on the road should be in one-to-one correspondence, so if the shadow is lost, it can be considered that the corresponding road facility is lost.
Wherein, the first location condition may be, but is not limited to, a location where facility shadows and road facilities may be collected at the same time, for example, as shown in fig. 3, the road facilities and the shadow information of the road facilities may be collected at the same time, where the facility shadow information satisfies the first location condition; the facility reference information includes, but is not limited to, coordinates, size, color, type, etc. of the asset.
The first matching process may (but is not limited to) calculate the illumination position of the coordinates of the road facility in the facility reference information, and then match the calculation result with the shadow coordinates included in the shadow information, or may directly match the coordinates of the road facility in the facility reference information with the shadow coordinates, and then determine whether the shadow coordinates are within the coordinate variation range of the road facility, or the like.
Step S208, determining that the road facility is missing when the first matching result does not meet a first matching condition.
In this embodiment, the first matching condition may (but is not limited to) be that the coordinates of the road facilities and the shadow information are in one-to-one correspondence, that is, the illumination position calculation may be matched to the corresponding shadow coordinates, or the coordinates of the road facilities may be matched to the corresponding shadow coordinates, and when the coordinates of the road facilities are not matched to the corresponding shadow information, it is indicated that there is a corresponding road facility missing.
Through the steps, as the shadow recognition and change calculation have small calculation force compared with the recognition of the facilities, the model training is simpler, and meanwhile, the recognition errors caused by the approximation of the facilities are avoided, so that the equipment arrangement cost and the facility inspection cost can be reduced, the problems of high recognition cost and low recognition precision of the road facilities (such as a road flower box) are solved, the recognition efficiency and precision of the road facilities are improved, and the inspection cost is reduced.
The main execution body of the above steps may be, but not limited to, a base station, a terminal, and the like.
In an alternative embodiment, after the determining the facility shadow information of the target area by the pre-trained object recognition model, the method further comprises:
step S2010, performing a second matching process on the facility shadow information and the facility reference information to obtain a second matching result when the facility shadow information meets a second location condition;
step S2012, determining that the road facility is missing if the second matching result satisfies the first matching condition.
In the present embodiment, in the case where the facility can be collected but the shadow is not collected (i.e., the device backlight is collected), the shadow is normally blocked by the facility, and at this time, if the shadow information can be collected, it is indicated that there is a defect in the facility.
In this embodiment, the second location condition may (but is not limited to) be a location where facility shadows and road facilities cannot be collected simultaneously, and the second matching condition is that coordinates of the road facilities cannot be matched to corresponding road shadow information, if the coordinates can be matched, the shadows are not blocked, so that it is indicated that there is a defect in the road equipment.
In an alternative embodiment, before the determining the facility shadow information of the target area by the pre-trained object recognition model, the method further comprises:
step S20402, obtaining weather information and/or time information of the target road to determine an illumination angle of a target time period;
step S20404, based on the illumination angle, determines the first position condition and/or the second position condition of a target period of time.
In this embodiment, since the shadows will change with the change of the sun illumination angle or be limited by the illumination of the surrounding street lamps at night, the determination of the weather information or time information of the target road can determine the shadow change range of the road facilities.
The target time period comprises a time period for acquiring initial image information (but not limited to), and the weather information comprises weather conditions (sunny days, overcast and rainy days, snowy days and the like), temperature and humidity, wind speed, wind direction and the like, wherein the acquisition of the weather information can be acquired by acquiring the publishing information of related meteorological departments through internet crawlers or directly networking with related systems of the meteorological departments, or can be acquired through other modes; the time information can be obtained by acquiring standard time in real time or by a timing module.
In an optional embodiment, after the obtaining weather information and/or time information of the target road to determine the illumination angle of the target time period, the method further includes:
step S204022, when the weather information and/or the time information satisfy the first weather condition, acquiring road water accumulation information of the target road based on the initial image information;
step S204042, determining second facility shadow information of the target road based on the road water information;
step S204026, performing a third matching process on the second facility shadow information and the facility shadow information to obtain a third matching result;
step S204028, determining that there is a loss of the road facility in the case where the third matching result does not satisfy the first matching condition.
In this embodiment, as shown in fig. 4, in the case of a rainy day, the illumination cannot form a distinct shadow, and at this time, the missing condition of the facility can be identified by collecting the road ponding and the shadow generated by the road facility in the ponding.
The first weather condition may be, but is not limited to, weather that may generate road ponding, such as rainy days, where the road ponding information includes information such as coordinates and areas of the road ponding, and the acquisition of the road ponding information may also be obtained by identifying the initial image information by using an object identification model; the third matching process may (but is not limited to) perform joint matching on the coordinates of the road water, the coordinates of the shadow information and the coordinates of the road facilities, or may be other forms of matching, and when the coordinates of the road water and the coordinates of the shadow information cannot be matched with the coordinates of the road facilities, it is indicated that the corresponding road facilities have a defect.
In an alternative embodiment, the method further comprises:
step S2002, determining a road reference line of the target road and a facility reference line of the road facility by the object recognition model;
step S2004, calculating a spatial included angle of the road datum line and the facility datum line to obtain a datum included angle;
step S2006, determining that the road facility has an ectopic position when the reference included angle is larger than a first threshold value and smaller than a second threshold value.
In this embodiment, the road facilities are generally in standard shapes and are arranged according to a certain rule, such as a street lamp is in a column shape, a sound insulation plate is in a rectangle shape and is arranged along the extending direction of the road, so that the facility datum line of the road facilities can be determined by determining the central axis of the road facilities, and then whether the corresponding road facilities are abnormal or not can be judged by determining whether the included angle between the central axis and the datum line of the road meets the preset condition or not, for example, the included angle between the street lamp and the road is generally 90 degrees, and if the included angle is smaller than 85 degrees, the possibility of toppling may exist.
The road reference line may be, but not limited to, a center axis of the road is determined after determining a boundary of the road, and the center axis is used as the road reference line, or a boundary line of the road is used as the road reference line, or a solid line or a broken line drawn in the target road is used as the road reference line, and the road reference line.
From the description of the above embodiments, it will be clear to a person skilled in the art that the method according to the above embodiments may be implemented by means of software plus the necessary general hardware platform, but of course also by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The present embodiment also provides a device for identifying a missing road facility, which is used for implementing the foregoing embodiments and preferred embodiments, and will not be described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
Fig. 5 is a block diagram showing a construction of a facility missing identifying apparatus according to an embodiment of the present invention, as shown in fig. 5, the apparatus including:
the image acquisition module 52 is used for acquiring initial image information of a target road;
an information determining module 54, configured to determine facility shadow information of a target area through a pre-trained object recognition model, where the target road includes the target area, and the facility shadow information includes shadow information of a road facility of the target road;
a first matching module 56, configured to perform a first matching process on the facility shadow information and preset facility reference information to obtain a first matching result when the facility shadow information meets a first location condition;
a first result judging module 58, configured to determine that the road facility has a defect if the first matching result does not satisfy a first matching condition.
In an alternative embodiment, the method further comprises:
a second matching module 510, configured to, after determining, by using the pre-trained object recognition model, facility shadow information of a target area, perform a second matching process on the facility shadow information and the facility reference information to obtain a second matching result when the facility shadow information meets a second location condition;
a second result judging module 512, configured to determine that the road facility has a defect if the second matching result meets the first matching condition.
In an alternative embodiment, the method further comprises:
the weather information collection module 5402 is configured to obtain weather information and/or time information of the target road before the facility shadow information of the target area is determined by the pre-trained object recognition model, so as to determine an illumination angle of a target time period;
a condition generating module 5404 for determining the first position condition and/or the second position condition of a target time period based on the illumination angle.
In an alternative embodiment, the method further comprises:
the ponding determining module 54022 is configured to obtain, after the weather information and/or the time information of the target road are obtained to determine the illumination angle of the target time period, road ponding information of the target road based on the initial image information if the weather information and/or the time information satisfies a first weather condition;
a second shadow collecting module 54044 for determining second facility shadow information of the target road based on the road water information;
a third matching module 54046, configured to perform a third matching process on the second facility shadow information and the facility shadow information to obtain a third matching result;
and a third judging module 54048, configured to determine that the road facility has a defect if the third matching result does not satisfy the first matching condition.
In an alternative embodiment, the method further comprises:
a reference determining module 5002 for determining a road reference line of the target road and a facility reference line of the road facility by the object recognition model;
the included angle determining module 5004 is configured to perform a spatial included angle calculation on the road reference line and the facility reference line to obtain a reference included angle;
and the ectopic judging module 5006 is configured to determine that the road facility is ectopic if the reference included angle is greater than a first threshold and less than a second threshold.
It should be noted that each of the above modules may be implemented by software or hardware, and for the latter, it may be implemented by, but not limited to: the modules are all located in the same processor; alternatively, the above modules may be located in different processors in any combination.
Embodiments of the present invention also provide a computer readable storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the method embodiments described above when run.
In one exemplary embodiment, the computer readable storage medium may include, but is not limited to: a usb disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing a computer program.
An embodiment of the invention also provides an electronic device comprising a memory having stored therein a computer program and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.
In an exemplary embodiment, the electronic apparatus may further include a transmission device connected to the processor, and an input/output device connected to the processor.
Specific examples in this embodiment may refer to the examples described in the foregoing embodiments and the exemplary implementation, and this embodiment is not described herein.
It will be appreciated by those skilled in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may be implemented in program code executable by computing devices, so that they may be stored in a storage device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than that shown or described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method for identifying a loss of roadway facility, comprising:
acquiring initial image information of a target road;
determining facility shadow information of a target area through a pre-trained object recognition model, wherein the target road comprises the target area, and the facility shadow information comprises the shadow information of road facilities of the target road;
under the condition that the facility shadow information meets a first position condition, carrying out first matching processing on the facility shadow information and preset facility reference information to obtain a first matching result, wherein the facility reference information comprises coordinates, sizes, colors and types of road facilities; the first location condition includes that the location of the shadow information is acquired simultaneously with the location of the asset of the target link; the first matching process at least comprises any one of the following: carrying out illumination position calculation on coordinates of the road facilities included in the facility reference information, and then matching an illumination position calculation result with shadow coordinates included in the shadow information; or matching the coordinates of the road facilities included in the facility reference information with the shadow coordinates, and judging whether the shadow coordinates are within the coordinate variation range of the road facilities included in the facility reference information;
and determining that the road facility is missing when the first matching result does not meet a first matching condition, wherein the first matching condition comprises one-to-one correspondence between shadow information and coordinates of the road facility included in the facility reference information.
2. The method of claim 1, wherein after said determining facility shadow information for the target area by the pre-trained object recognition model, the method further comprises:
performing a second matching process on the facility shadow information and the facility reference information to obtain a second matching result under the condition that the facility shadow information meets a second position condition, wherein the second position condition comprises a position where the facility shadow of the target road and the facility cannot be acquired simultaneously;
and determining that the road facility is missing under the condition that the second matching result meets a second matching condition, wherein the second matching condition comprises that coordinates of the road facility cannot be matched with corresponding road shadow information.
3. The method of claim 2, wherein prior to said determining facility shadow information for the target area by the pre-trained object recognition model, the method further comprises:
acquiring weather information and/or time information of the target road to determine an illumination angle of a target time period;
based on the illumination angle, the first location condition and/or the second location condition of a target time period is determined.
4. A method according to claim 3, wherein after the obtaining of the weather information and/or time information of the target road to determine the illumination angle of the target time period, the method further comprises:
acquiring road ponding information of the target road based on the initial image information under the condition that the weather information and/or the time information meet a first weather condition;
determining second facility shadow information of the target road based on the road water information;
performing third matching processing on the second facility shadow information and the facility shadow information to obtain a third matching result, wherein the third matching processing comprises joint matching of the second facility shadow information and coordinates of road ponding, coordinates of shadow information and coordinates of facilities included in the road ponding information;
and determining that the road facility is missing when the third matching result does not meet the first matching condition.
5. The method according to claim 1, wherein the method further comprises:
determining a road reference line of the target road and a facility reference line of the road facility through the object recognition model;
calculating a space included angle of the road datum line and the facility datum line to obtain a datum included angle;
and determining that the road facility has an ectopic condition under the condition that the reference included angle is larger than a first threshold value and smaller than a second threshold value.
6. A loss of road facility identification apparatus, comprising:
the image acquisition module is used for acquiring initial image information of the target road;
an information determining module, configured to determine facility shadow information of a target area through a pre-trained object recognition model, where the target road includes the target area, and the facility shadow information includes shadow information of a road facility of the target road;
the first matching module is used for carrying out first matching processing on the facility shadow information and preset facility reference information under the condition that the facility shadow information meets a first position condition so as to obtain a first matching result, wherein the facility reference information comprises coordinates, size, color and type of road facilities; the first location condition includes that the location of the shadow information and the location of the asset of the target link may be collected simultaneously; the first matching process at least comprises any one of the following: carrying out illumination position calculation on coordinates of the road facilities included in the facility reference information, and then matching an illumination position calculation result with shadow coordinates included in the shadow information; or matching the coordinates of the road facilities included in the facility reference information with the shadow coordinates, and judging whether the shadow coordinates are within the coordinate variation range of the road facilities included in the facility reference information;
and the first result judging module is used for determining that the road facilities have defects under the condition that the first matching result does not meet a first matching condition, wherein the first matching condition comprises one-to-one correspondence between shadow information and coordinates of the road facilities included in the facility reference information.
7. The apparatus as recited in claim 6, further comprising:
the second matching module is used for performing second matching processing on the facility shadow information and the facility reference information to obtain a second matching result under the condition that the facility shadow information meets a second position condition after the facility shadow information of the target area is determined through the pre-trained object recognition model, wherein the second position condition comprises a position where the facility shadow of the target road and the road facility cannot be acquired simultaneously;
and the second result judging module is used for determining that the road facility is missing under the condition that the second matching result meets a second matching condition, wherein the second matching condition comprises that the coordinates of the road facility cannot be matched to corresponding road shadow information.
8. The apparatus as recited in claim 7, further comprising:
the weather information acquisition module is used for acquiring weather information and/or time information of the target road before the facility shadow information of the target area is determined through the pre-trained object recognition model so as to determine the illumination angle of the target time period;
and the condition generating module is used for determining the first position condition and/or the second position condition of the target time period based on the illumination angle.
9. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program, wherein the computer program is arranged to execute the method of any of the claims 1 to 5 when run.
10. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to run the computer program to perform the method of any of the claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211496211.XA CN115631356B (en) | 2022-11-28 | 2022-11-28 | Method and device for identifying missing of road facility, storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211496211.XA CN115631356B (en) | 2022-11-28 | 2022-11-28 | Method and device for identifying missing of road facility, storage medium and electronic device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115631356A CN115631356A (en) | 2023-01-20 |
| CN115631356B true CN115631356B (en) | 2023-08-08 |
Family
ID=84911016
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211496211.XA Active CN115631356B (en) | 2022-11-28 | 2022-11-28 | Method and device for identifying missing of road facility, storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115631356B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115830032B (en) * | 2023-02-13 | 2023-05-26 | 杭州闪马智擎科技有限公司 | Road expansion joint lesion recognition method and device based on old facilities |
| CN116030065B (en) * | 2023-03-31 | 2024-06-14 | 云南琰搜电子科技有限公司 | Road quality detection method based on image recognition |
| CN116189133B (en) * | 2023-04-26 | 2023-07-28 | 宜宾闪马智通科技有限公司 | Road inspection judging method and device |
| CN116994215A (en) * | 2023-09-26 | 2023-11-03 | 上海闪马智能科技有限公司 | Road facility abnormality judgment method and device |
| CN116994354B (en) * | 2023-09-28 | 2024-01-23 | 上海闪马智能科技有限公司 | Road electric facility inspection method and device, storage medium and electronic device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107918753A (en) * | 2016-10-10 | 2018-04-17 | 腾讯科技（深圳）有限公司 | Processing Method of Point-clouds and device |
| CN108960055A (en) * | 2018-05-30 | 2018-12-07 | 广西大学 | A kind of method for detecting lane lines based on local line's stage mode feature |
| WO2019207189A1 (en) * | 2018-04-25 | 2019-10-31 | Defensya Ingeniería Internacional, S.L. | System and method for creating, modulating and detecting shadows in control systems based on a remote viewing system |
| CN112034449A (en) * | 2020-08-03 | 2020-12-04 | 河北德冠隆电子科技有限公司 | System and method for realizing vehicle running track correction based on physical space attribute |
| CN112129266A (en) * | 2020-09-28 | 2020-12-25 | 北京嘀嘀无限科技发展有限公司 | Method, apparatus, device and computer readable storage medium for processing map |
| CN114170347A (en) * | 2021-12-08 | 2022-03-11 | 武汉中海庭数据技术有限公司 | A method and system for automatically generating attribute points of road outer lines |
| CN114494505A (en) * | 2021-12-13 | 2022-05-13 | 武汉中海庭数据技术有限公司 | Method, system, electronic device and storage medium for constructing road outer line |
| CN115331190A (en) * | 2022-09-30 | 2022-11-11 | 北京闪马智建科技有限公司 | A method and device for identifying road hazards based on Raivision fusion |
-
2022
- 2022-11-28 CN CN202211496211.XA patent/CN115631356B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107918753A (en) * | 2016-10-10 | 2018-04-17 | 腾讯科技（深圳）有限公司 | Processing Method of Point-clouds and device |
| WO2019207189A1 (en) * | 2018-04-25 | 2019-10-31 | Defensya Ingeniería Internacional, S.L. | System and method for creating, modulating and detecting shadows in control systems based on a remote viewing system |
| CN108960055A (en) * | 2018-05-30 | 2018-12-07 | 广西大学 | A kind of method for detecting lane lines based on local line's stage mode feature |
| CN112034449A (en) * | 2020-08-03 | 2020-12-04 | 河北德冠隆电子科技有限公司 | System and method for realizing vehicle running track correction based on physical space attribute |
| CN112129266A (en) * | 2020-09-28 | 2020-12-25 | 北京嘀嘀无限科技发展有限公司 | Method, apparatus, device and computer readable storage medium for processing map |
| CN114170347A (en) * | 2021-12-08 | 2022-03-11 | 武汉中海庭数据技术有限公司 | A method and system for automatically generating attribute points of road outer lines |
| CN114494505A (en) * | 2021-12-13 | 2022-05-13 | 武汉中海庭数据技术有限公司 | Method, system, electronic device and storage medium for constructing road outer line |
| CN115331190A (en) * | 2022-09-30 | 2022-11-11 | 北京闪马智建科技有限公司 | A method and device for identifying road hazards based on Raivision fusion |
Non-Patent Citations (1)
| Title |
|---|
| 马雷 ; 于福莹 ; 李昊 ; .基于灰度图像的复杂环境下智能车辆道路边界识别.汽车工程.2010,(第04期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115631356A (en) | 2023-01-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115631356B (en) | Method and device for identifying missing of road facility, storage medium and electronic device | |
| CN108345822B (en) | Point cloud data processing method and device | |
| Mu et al. | Traffic light detection and recognition for autonomous vehicles | |
| US11270111B2 (en) | Automated management of potentially hazardous objects near power lines | |
| CN114413881B (en) | Construction method, device and storage medium of high-precision vector map | |
| CN107918753A (en) | Processing Method of Point-clouds and device | |
| CN106845321A (en) | The treating method and apparatus of pavement markers information | |
| CN111458721B (en) | Exposed garbage identification and positioning method, device and system | |
| CN115331190B (en) | Road hidden danger identification method and device based on radar vision fusion | |
| Ahmad et al. | A novel method for vegetation encroachment monitoring of transmission lines using a single 2D camera | |
| CN106845324A (en) | The treating method and apparatus of guideboard information | |
| CN105262983A (en) | Road monitoring system and method based on internet of lamps | |
| CN110597248B (en) | Park unmanned intelligent inspection method, device, equipment and storage medium | |
| CN111127507A (en) | Method and system for determining throwing object | |
| CN113111876A (en) | Method and system for obtaining evidence of traffic violation | |
| CN112597926A (en) | Method, device and storage medium for identifying airplane target based on FOD image | |
| CN111929672A (en) | Method and device for determining movement track, storage medium and electronic device | |
| CN111144467A (en) | Method and system for realizing scene factor acquisition | |
| CN113269175B (en) | Fire monitoring method and device | |
| CN117911754A (en) | A method, system and storage medium for detecting the degree of tree obstacle defects in transmission lines | |
| CN118225457A (en) | High-speed road section simulation test site for automatic driving test and construction method thereof | |
| Bayerl et al. | Following Dirt Roads at Night Time: Sensors and Features for Lane Recognition and Tracking | |
| CN116030065B (en) | Road quality detection method based on image recognition | |
| CN115620165B (en) | Evaluation method, device, equipment and medium for slow traffic system facilities in urban built-up areas | |
| CN115641334B (en) | Road anti-collision facility damage identification method and device |
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 |