CN114387500B - Image recognition method and system for self-propelled equipment, self-propelled equipment and readable storage medium - Google Patents
Image recognition method and system for self-propelled equipment, self-propelled equipment and readable storage medium Download PDFInfo
- Publication number
- CN114387500B CN114387500B CN202011106700.0A CN202011106700A CN114387500B CN 114387500 B CN114387500 B CN 114387500B CN 202011106700 A CN202011106700 A CN 202011106700A CN 114387500 B CN114387500 B CN 114387500B
- Authority
- CN
- China
- Prior art keywords
- contour
- image
- threshold
- preset
- preset position
- 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
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000001514 detection method Methods 0.000 claims abstract description 15
- 238000004590 computer program Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 230000005856 abnormality Effects 0.000 abstract description 7
- 241001417527 Pempheridae Species 0.000 description 3
- 230000007797 corrosion Effects 0.000 description 3
- 238000005260 corrosion Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000000926 separation method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an image identification method and system applied to self-walking equipment, the self-walking equipment and a readable storage medium; the method comprises the steps of obtaining an image of the environment of the self-walking equipment in the travelling direction of the self-walking equipment, conducting contour processing on the image to obtain a contour image with contour information, conducting contour detection on the contour image to obtain a contour block, counting characteristic values of the contour block, and comparing the characteristic values with a preset characteristic value threshold to obtain a recognition result. According to the invention, the contour image is subjected to contour detection to obtain the contour block, and the abnormality of the contour block can be effectively identified according to the characteristic value of the contour block, so that the erroneous judgment of the image is reduced.
Description
Technical Field
The present invention relates to an image recognition method and system for self-walking equipment, a self-walking equipment and a readable storage medium, and more particularly, to an image recognition method and system for self-walking equipment, a self-walking equipment and a readable storage medium capable of reducing erroneous judgment.
Background
When the existing mower is used for image recognition, whether the image comprises a non-lawn area or not can be recognized according to the chromaticity component of the image. The method for recognizing the image through the chromatic component has better effect when the color difference between the lawn and the background is larger, and is easy to cause misjudgment when the color difference between the lawn and the background is smaller.
Disclosure of Invention
The invention provides an image recognition method, an image recognition system, self-walking equipment and a readable storage medium, wherein the image recognition method, the image recognition system and the self-walking equipment can reduce misjudgment.
The invention provides an image recognition method applied to self-walking equipment, which comprises the following steps:
acquiring an image of the environment of the self-walking device in the travelling direction thereof;
Contour processing is carried out on the image to obtain a contour image with contour information;
Performing contour detection on the contour image to obtain a contour block;
Counting the characteristic values of the outline blocks;
And comparing the characteristic value with a preset characteristic value threshold value to obtain a recognition result.
Optionally, the feature values include an average luminance value, an average roughness value, and a contour size feature value, or the feature values include an average luminance value and an average roughness value.
Optionally, the contour size feature value includes a contour area, a contour diagonal length, a contour width, a contour height, or a number of pixels of the region to be identified included in the contour block.
Optionally, the counting the feature values of the contour block includes:
Acquiring the position information of the outline block;
comparing the position information of the contour block with a preset position threshold value to obtain a target contour block;
And counting the characteristic values of the target contour blocks.
Optionally, the preset position threshold includes a first preset position threshold and a second preset position threshold, and a distance between an area corresponding to the first preset position threshold in the image and the self-walking device is not equal to a distance between an area corresponding to the second preset position threshold in the image and the self-walking device, and the preset feature value threshold includes a first preset feature value threshold and a second preset feature value threshold, where the first preset position threshold corresponds to the first preset feature value threshold, the second preset position threshold corresponds to the second preset feature value threshold, and the first preset feature value threshold is different from the second preset position threshold.
Optionally, when the preset position threshold is a first preset position threshold, comparing the position information of the contour block with the preset position threshold to obtain a target contour block, and comparing the position information of the contour block with the first preset position threshold to obtain a first target contour block; the statistics of the characteristic values of the target contour blocks is that of first characteristic values of the first target contour blocks, wherein the first characteristic values comprise average brightness values, average roughness values and contour size characteristic values;
And when the preset position threshold is a second preset position threshold, comparing the position information of the contour block with the preset position threshold to obtain a target contour block, wherein the comparing the position information of the contour block with the second preset position threshold to obtain a second target contour block, and the counting of the characteristic values of the target contour block is the counting of the second characteristic values of the second target contour block, wherein the second characteristic values comprise an average brightness value and an average roughness value.
Optionally, the performing contour processing on the image to obtain a contour image with contour information includes:
separating the images to obtain v-channel images;
Performing filtering and normalization processing on the v-channel image to obtain a preprocessed image;
performing edge extraction on the preprocessed image to obtain an edge image;
and expanding, inverting and corroding the edge image to obtain a contour image.
The invention also provides an image recognition system applied to the self-walking equipment, which comprises:
an image acquisition module for acquiring an image of an environment of the walking device in a traveling direction thereof;
an image processing module for contour processing the image to obtain a contour image having contour information;
The contour detection module is used for carrying out contour detection on the contour image to obtain a contour block;
The feature processing module is used for counting the feature values of the contour blocks;
and the image recognition module is used for comparing the characteristic value with a preset characteristic value threshold value to obtain a recognition result.
The invention also provides self-walking equipment, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the image identification method applied to the self-walking equipment when executing the computer program.
The present invention also provides a readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the image recognition method applied to a self-walking device.
Compared with the prior art, the contour detection method and the device have the advantages that the contour block is obtained by carrying out contour detection on the contour image, and the abnormality of the contour block can be effectively identified according to the characteristic value of the contour block, so that the misjudgment of the image is reduced. According to the invention, the target contour block is obtained according to the position information of the contour block, and the target contour block is positioned in a region which is closer to the self-walking device in the image, so that the self-walking device can perform obstacle avoidance recognition when the self-walking device is close to an abnormality (namely, the position information of the contour block is positioned in the range of the preset position threshold), and the self-walking device does not need to perform obstacle avoidance recognition when the self-walking device is far away from the abnormality (namely, the position information of the contour block exceeds the range of the preset position threshold), so that the obstacle avoidance opportunity is reasonably selected. The invention sets the first preset position threshold value and the second preset position threshold value, and sets the first preset characteristic value threshold value and the second preset characteristic value threshold value which respectively correspond to the first preset position threshold value and the second preset characteristic value threshold value, so that the target contour blocks at different positions are compared with the corresponding preset characteristic value threshold values, and misjudgment caused by a single preset characteristic value threshold value is effectively reduced. The invention obtains the contour image after carrying out separation treatment, filtering treatment, normalization treatment, edge extraction, expansion, inversion and corrosion treatment on the image so as to improve the recognition rate of the contour image.
Drawings
FIG. 1 is a flow chart of the image recognition method of the present invention applied to self-walking equipment;
FIG. 2 is a flowchart of step S40 of FIG. 1;
FIG. 3 is a schematic diagram of acquiring image position information by an image recognition method applied to self-walking equipment;
FIG. 4 is a flowchart of step S20 of FIG. 1;
fig. 5 is an effect diagram of the contour image obtained by fig. 4;
Fig. 6 is a schematic block diagram of an image recognition system applied to a self-walking device according to the present invention.
Detailed Description
In order to make the technical solution of the present invention better understood by those skilled in the art, the technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
Referring to fig. 1-6, the invention provides an image recognition method applied to self-walking equipment, which comprises the following steps:
Step S10, acquiring an image orgMat of the environment of the self-walking device in the travelling direction of the self-walking device;
step S20, carrying out contour processing on the image to obtain a contour image dstMat with contour information;
step S30, performing contour detection on the contour image dstMat to obtain a contour block;
step S40, counting the characteristic values of the outline blocks;
and S50, comparing the characteristic value with a preset characteristic value threshold value to obtain a recognition result.
In another embodiment of the present invention, the self-walking device in the step S10 is a device such as a mower or a sweeper, the image in the step S10 is an image obtained by the mower or the sweeper in a traveling direction of the device, when the self-walking device is the mower, the preset threshold value is a threshold value related to a lawn, the identification result includes that the image has a non-lawn area, the image is an image to be screened, the image to be screened may be a lawn image, and the non-lawn area may be an abnormal area such as an obstacle or a boundary. The image recognition method applied to the self-walking equipment can screen out the images which are possibly lawns so as to facilitate the subsequent image processing. When the self-walking device is a sweeper, the preset characteristic value threshold value is a threshold value related to a road surface, the identification result comprises that a non-road surface area exists in the image, the image is an image to be screened, the image to be screened may be a road surface image, and the non-road surface area may be an abnormal area such as an obstacle or a boundary.
In another embodiment of the present invention, the contour detection in the step S30 is to detect the outermost contour blocks, the inner contour blocks included in the outermost contour blocks are ignored, and the step S30 can detect the number of contour blocks and the continuous contour points on each contour block through the findContours () function in the openCV library.
In another embodiment of the present invention, the feature values in the step S40 include an average luminance value, an average roughness value, and a contour size feature value, or the feature values include an average luminance value and an average roughness value.
In another embodiment of the present invention, the contour size feature value includes a contour area, a contour diagonal length, a contour width, a contour height, or a number of pixels of a region to be identified included in a contour block. For example, the contour image has white pixels and black pixels, the white pixels represent possible anomalies, and the area to be identified is a set of white pixels within a single contour block.
In another embodiment of the present invention, the step S40 includes:
step S410, obtaining the position information of the outline block;
Step S420, comparing the position information of the contour block with a preset position threshold value to obtain a target contour block;
and S430, counting the characteristic values of the target contour block.
The position information of the contour block in step S410 is determined by a preset coordinate system of the image, where the preset coordinate system includes an X coordinate axis and a Y coordinate axis, the X coordinate axis and the Y coordinate axis are respectively parallel to the boundary of the image, the position information of the contour block is a Y coordinate value of the contour block, the unit of the Y coordinate value is a pixel, and the Y coordinate value of the contour block indicates a distance between the contour block and the self-walking device. Assuming that the image is rectangular, one of boundary intersection points of the image is taken as a coordinate origin of a preset coordinate system, an X coordinate axis and a Y coordinate axis are intersected at the coordinate origin, a first preset position threshold value and a second preset position threshold value are set according to the extending direction of the Y coordinate axis, the Y coordinate values of the contour blocks corresponding to different preset coordinate systems are the first preset position threshold value and the second preset position threshold value, and the units of the first preset position threshold value and the second preset position threshold value are pixels.
The step S420 of comparing the position information of the contour block with a preset position threshold to obtain a target contour block includes:
Obtaining the position information of the contour block through the actual boundary or the virtual boundary of the contour block;
Judging whether the contour block is at least partially positioned in a preset position threshold according to the position information;
And when at least part of the contour blocks are positioned in a preset position threshold, the contour blocks are target contour blocks, and otherwise, the contour blocks are not target contour blocks.
The virtual boundary is generated after virtual processing of the actual boundary of the outline block, for example, the actual boundary is an irregular graph, the virtual boundary is a rectangle, the edges of the virtual boundary are respectively parallel to the X coordinate axis and the Y coordinate axis, and graphs with specific shapes can be generated according to other rules of virtual processing, and the comparison processing is facilitated through the position information acquired by the virtual boundary.
In another embodiment of the present invention, the preset position threshold includes a first preset position threshold and a second preset position threshold, and a distance between an area corresponding to the first preset position threshold in the image and the self-walking device is not equal to a distance between an area corresponding to the second preset position threshold in the image and the self-walking device, and the preset feature value threshold includes a first preset feature value threshold and a second preset feature value threshold, where the first preset position threshold corresponds to the first preset feature value threshold, the second preset position threshold corresponds to the second preset feature value threshold, and the first preset feature value threshold is different from the second preset position threshold.
In another embodiment of the present invention, when the preset position threshold is a first preset position threshold, the comparing the position information of the contour block with the preset position threshold to obtain a target contour block is comparing the position information of the contour block with the first preset position threshold to obtain a first target contour block;
And when the preset position threshold is a second preset position threshold, comparing the position information of the contour block with the preset position threshold to obtain a target contour block, wherein the comparing the position information of the contour block with the second preset position threshold to obtain a second target contour block, and the counting of the characteristic values of the target contour block is the counting of the second characteristic values of the second target contour block, wherein the second characteristic values comprise an average brightness value and an average roughness value.
In another embodiment of the present invention, the step S20 includes:
step S201, performing separation processing on the image orgMat to obtain a v-channel image;
step S202, filtering and normalizing the v-channel image to obtain a preprocessed image;
Step 203, performing edge extraction on the preprocessed image to obtain an edge image cannyMat, wherein the edge extraction can adopt canny operators and the like;
step S204, performing expansion, negation and corrosion treatment on the edge image cannyMat to obtain a contour image dstMat.
Assuming that the contour size feature value AContours i is the number of pixels of the region to be identified included in the contour block, the average brightness value BContours i =pixel value/contour size feature value AContours i, wherein the pixel value range of a single pixel point is 0-255, that is, 256 gray levels, the pixel value can be called a gray level for a single-channel image, and the larger the gray level is, the brighter the gray level is, so that the v-channel image is subjected to filtering and normalization processing to obtain a preprocessed image, and the preprocessed image can be used for calculating brightness, wherein the pixel value is the sum of the pixel values in the preprocessed image corresponding to the white pixel point position in the contour block in the contour image. Average roughness value HContours i = number of pixels/contour size feature value AContours i with pixel value >100 in the edge image. The i is the number of the contour blocks, and different contour blocks are denoted by different numbers.
Assume that the first preset position threshold is set to 60 and the second preset position threshold is set to 80.
The first comparison process corresponding to the first preset position threshold is as follows:
First preamble decision 50< BContours i <200 and YContours i >60
First subsequent determination:
Acontours i >520 and HContours i <0.02
Acontours i >1000 and HContours i <0.04
Acontours i >3000 and HContours i <0.07
Acontours i >5000 and HContours i <0.09
Acontours i >10000 and HContours i <0.15
The second comparison process corresponding to the second preset position threshold is as follows:
Second preamble decision 50< BContours i <200 and YContours i >80
Second subsequent determination HContours i <0.05
In the process of identifying whether the non-lawn area exists in the image, if the image accords with the first preamble judgment and accords with any one of the first follow-up judgment, the non-lawn area exists in the image, and if the image does not accord with the first preamble judgment or accords with the first preamble judgment but does not accord with any one of the first follow-up judgment, the image is an image to be screened, and the image to be screened possibly is a lawn image and needs to be subjected to subsequent image processing (judgment of other characteristic values in the image to be screened) so as to further identify whether the non-lawn area exists in the image.
If the image does not accord with the second preamble judgment or accords with the second preamble judgment but does not accord with the second postnatal judgment, the image is an image to be screened, and the image to be screened possibly is a lawn image and needs to be subjected to subsequent image processing (judgment of other characteristic values in the image to be screened) so as to further identify whether the image has the non-lawn area.
The invention also provides an image recognition system 1 applied to self-walking equipment, wherein the system 1 comprises:
An image acquisition module 10 for acquiring an image from an environment of the walking device in a traveling direction thereof;
An image processing module 20 for contour processing the image to obtain a contour image having contour information;
a contour detection module 30, configured to perform contour detection on the contour image to obtain a contour block;
a feature processing module 40 for counting feature values of the contour blocks;
the image recognition module 50 compares the feature value with a preset feature value threshold to obtain a recognition result.
The invention also provides self-walking equipment, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the image identification method applied to the self-walking equipment when executing the computer program.
The present invention also provides a readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the image recognition method applied to a self-walking device.
In summary, the contour detection is performed on the contour image to obtain the contour block, and the abnormality of the contour block can be effectively identified according to the feature value of the contour block, so that the erroneous judgment of the image is reduced. According to the invention, the target contour block is obtained according to the position information of the contour block, and the target contour block is positioned in a region which is closer to the self-walking device in the image, so that the self-walking device can perform obstacle avoidance recognition when the self-walking device is close to an abnormality (namely, the position information of the contour block is positioned in the range of the preset position threshold), and the self-walking device does not need to perform obstacle avoidance recognition when the self-walking device is far away from the abnormality (namely, the position information of the contour block exceeds the range of the preset position threshold), so that the obstacle avoidance opportunity is reasonably selected. The invention sets the first preset position threshold value and the second preset position threshold value, and sets the first preset characteristic value threshold value and the second preset characteristic value threshold value which respectively correspond to the first preset position threshold value and the second preset characteristic value threshold value, so that the target contour blocks at different positions are compared with the corresponding preset characteristic value threshold values, and misjudgment caused by a single preset characteristic value threshold value is effectively reduced. The invention obtains the contour image after carrying out separation treatment, filtering treatment, normalization treatment, edge extraction, expansion, inversion and corrosion treatment on the image so as to improve the recognition rate of the contour image.
Furthermore, it should be understood that although the present disclosure describes embodiments, not every embodiment is provided with a separate embodiment, and that this description is provided for clarity only, and that the skilled artisan should recognize that the embodiments may be combined as appropriate to form other embodiments that will be understood by those skilled in the art.
The above list of detailed descriptions is only specific to practical embodiments of the present invention, and is not intended to limit the scope of the present invention, and all equivalent embodiments or modifications that do not depart from the spirit of the present invention should be included in the scope of the present invention.
Claims (6)
1. An image recognition method applied to self-walking equipment is characterized in that,
The method comprises the following steps:
acquiring an image of the environment of the self-walking device in the travelling direction thereof;
Contour processing is carried out on the image to obtain a contour image with contour information;
Performing contour detection on the contour image to obtain a contour block;
Counting the characteristic values of the contour block, wherein the characteristic values comprise average brightness values, average roughness values and contour size characteristic values or the characteristic values comprise average brightness values and average roughness values, and the contour size characteristic values comprise contour areas, contour diagonal lengths, contour widths, contour heights or the number of pixels of the region to be identified, which is included in the contour block;
Comparing the characteristic value with a preset characteristic value threshold value to obtain a recognition result, wherein the recognition result is used for indicating whether an abnormal region exists in the image, and the abnormal region comprises an obstacle or a boundary;
wherein, the counting the feature values of the contour blocks includes:
Acquiring the position information of the outline block;
Comparing the position information of the contour block with a preset position threshold to obtain a target contour block, wherein the preset position threshold comprises a first preset position threshold and a second preset position threshold, the distance between a region corresponding to the first preset position threshold in the image and the self-walking equipment is not equal to the distance between a region corresponding to the second preset position threshold in the image and the self-walking equipment, the preset feature value threshold comprises a first preset feature value threshold and a second preset feature value threshold, the first preset position threshold corresponds to the first preset feature value threshold, the second preset position threshold corresponds to the second preset feature value threshold, and the first preset feature value threshold is different from the second preset position threshold;
And counting the characteristic values of the target contour blocks.
2. The image recognition method applied to the self-walking device according to claim 1, wherein,
When the preset position threshold is a first preset position threshold, comparing the position information of the contour block with the preset position threshold to obtain a target contour block, wherein the comparing the position information of the contour block with the first preset position threshold to obtain a first target contour block is performed, and the counting of the characteristic value of the target contour block is performed to count the first characteristic value of the first target contour block, wherein the first characteristic value comprises an average brightness value, an average roughness value and a contour size characteristic value;
And when the preset position threshold is a second preset position threshold, comparing the position information of the contour block with the preset position threshold to obtain a target contour block, wherein the comparing the position information of the contour block with the second preset position threshold to obtain a second target contour block, and the counting of the characteristic values of the target contour block is the counting of the second characteristic values of the second target contour block, wherein the second characteristic values comprise an average brightness value and an average roughness value.
3. The image recognition method applied to the self-walking device according to claim 1, wherein,
The contour processing the image to obtain a contour image with contour information includes:
separating the images to obtain v-channel images;
Performing filtering and normalization processing on the v-channel image to obtain a preprocessed image;
performing edge extraction on the preprocessed image to obtain an edge image;
and expanding, inverting and corroding the edge image to obtain a contour image.
4. An image recognition system applied to self-walking equipment is characterized in that,
The system comprises:
an image acquisition module for acquiring an image of an environment of the walking device in a traveling direction thereof;
an image processing module for contour processing the image to obtain a contour image having contour information;
The contour detection module is used for carrying out contour detection on the contour image to obtain a contour block;
The feature processing module is used for counting the feature values of the contour blocks;
the image recognition module is used for comparing the characteristic value with a preset characteristic value threshold value to obtain a recognition result;
The feature processing module is further used for obtaining the position information of the contour block, comparing the position information of the contour block with a preset position threshold to obtain a target contour block, wherein the preset position threshold comprises a first preset position threshold and a second preset position threshold, the distance between a region corresponding to the first preset position threshold in the image and the walking equipment is not equal to the distance between a region corresponding to the second preset position threshold in the image and the walking equipment, the preset feature value threshold comprises a first preset feature value threshold and a second preset feature value threshold, the first preset position threshold corresponds to the first preset feature value threshold, the second preset position threshold corresponds to the second preset feature value threshold, the first preset feature value threshold is different from the second preset position threshold, and the feature value of the target contour block is counted.
5. A self-walking device comprising a memory and a processor, said memory storing a computer program, characterized in that,
The processor, when executing the computer program, implements the steps of the image recognition method applied to a self-walking device as claimed in any one of claims 1-3.
6. A readable storage medium having a computer program stored thereon, characterized in that,
The computer program, when executed by a processor, implements the steps of the image recognition method applied to a self-walking device as claimed in any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011106700.0A CN114387500B (en) | 2020-10-16 | 2020-10-16 | Image recognition method and system for self-propelled equipment, self-propelled equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011106700.0A CN114387500B (en) | 2020-10-16 | 2020-10-16 | Image recognition method and system for self-propelled equipment, self-propelled equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114387500A CN114387500A (en) | 2022-04-22 |
| CN114387500B true CN114387500B (en) | 2024-12-31 |
Family
ID=81193538
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011106700.0A Active CN114387500B (en) | 2020-10-16 | 2020-10-16 | Image recognition method and system for self-propelled equipment, self-propelled equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114387500B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109344687A (en) * | 2018-08-06 | 2019-02-15 | 深圳拓邦股份有限公司 | The obstacle detection method of view-based access control model, device, mobile device |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104239909B (en) * | 2014-08-11 | 2018-03-16 | 北京捷通华声语音技术有限公司 | A kind of recognition methods of image and device |
| CN107025633B (en) * | 2016-01-29 | 2020-11-27 | 中兴通讯股份有限公司 | Image processing method and device |
| WO2018035814A1 (en) * | 2016-08-25 | 2018-03-01 | 华讯方舟科技有限公司 | Millimetre wave image-based human body foreign matter detection method and system |
| CN110503108B (en) * | 2019-07-11 | 2024-05-28 | 平安科技（深圳）有限公司 | Method and device for identifying illegal buildings, storage medium and computer equipment |
| CN110610453B (en) * | 2019-09-02 | 2021-07-06 | 腾讯科技（深圳）有限公司 | Image processing method and device and computer readable storage medium |
| CN111414853A (en) * | 2020-03-19 | 2020-07-14 | 宁波职业技术学院 | Automatic driving method, device, computer equipment and storage medium based on machine vision |
-
2020
- 2020-10-16 CN CN202011106700.0A patent/CN114387500B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109344687A (en) * | 2018-08-06 | 2019-02-15 | 深圳拓邦股份有限公司 | The obstacle detection method of view-based access control model, device, mobile device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114387500A (en) | 2022-04-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2031571B1 (en) | Vehicle type determination device, program, and method | |
| US8902053B2 (en) | Method and system for lane departure warning | |
| CN111080661B (en) | Image-based straight line detection method and device and electronic equipment | |
| CN113109368B (en) | Glass crack detection method, device, equipment and medium | |
| CN111047615B (en) | Image-based straight line detection method and device and electronic equipment | |
| US11482016B2 (en) | Division line recognition apparatus | |
| US8599257B2 (en) | Vehicle detection device, vehicle detection method, and vehicle detection program | |
| CN106991407B (en) | A kind of method and device of lane detection | |
| US11530993B2 (en) | Deposit detection device and deposit detection method | |
| CN112597846B (en) | Lane line detection method, lane line detection device, computer device, and storage medium | |
| CN103455994A (en) | Method and equipment for determining image blurriness | |
| CN107748882B (en) | Lane line detection method and device | |
| CN107844761B (en) | Traffic sign detection method and device | |
| JP6432296B2 (en) | Device and method for detecting zebra crossings in images | |
| CN114127784A (en) | Method, computer program product and computer readable medium for generating a mask for a camera stream | |
| CN112132036A (en) | Big data image processing method and system based on safe area | |
| US11354794B2 (en) | Deposit detection device and deposit detection method | |
| CN114387500B (en) | Image recognition method and system for self-propelled equipment, self-propelled equipment and readable storage medium | |
| US11037266B2 (en) | Attached substance detection device and attached substance detection method | |
| US11308624B2 (en) | Adhered substance detection apparatus | |
| US20210090260A1 (en) | Deposit detection device and deposit detection method | |
| US20200211194A1 (en) | Attached object detection apparatus | |
| CN111242051A (en) | Vehicle identification optimization method and device and storage medium | |
| CN116597415A (en) | Image processing method, device, computer readable storage medium and electronic equipment | |
| CN112785550A (en) | Image quality value determination method, image quality value determination device, storage medium, and electronic 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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230609 Address after: 215000 No. 8 Ting Rong Street, Suzhou Industrial Park, Jiangsu, China Applicant after: Suzhou Cleva Precision Machinery & Technology Co.,Ltd. Applicant after: SKYBEST ELECTRIC APPLIANCE (SUZHOU) Co.,Ltd. Address before: No.18, Huahong street, Suzhou Industrial Park, Suzhou, Jiangsu Province, 215000 Applicant before: Suzhou Cleva Precision Machinery & Technology Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |