CN114137512B - Front multi-vehicle tracking method integrating millimeter wave radar and deep learning vision - Google Patents
Front multi-vehicle tracking method integrating millimeter wave radar and deep learning vision Download PDFInfo
- Publication number
- CN114137512B CN114137512B CN202111432862.8A CN202111432862A CN114137512B CN 114137512 B CN114137512 B CN 114137512B CN 202111432862 A CN202111432862 A CN 202111432862A CN 114137512 B CN114137512 B CN 114137512B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- millimeter wave
- wave radar
- vehicles
- deep learning
- 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 37
- 238000013135 deep learning Methods 0.000 title claims abstract description 22
- 238000001514 detection method Methods 0.000 claims abstract description 33
- 238000012216 screening Methods 0.000 claims abstract description 12
- 230000000007 visual effect Effects 0.000 claims abstract description 8
- 238000004088 simulation Methods 0.000 claims abstract description 5
- 230000004927 fusion Effects 0.000 claims description 11
- 230000006855 networking Effects 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 abstract description 4
- 230000001360 synchronised effect Effects 0.000 abstract description 4
- 238000012545 processing Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
- G01S13/867—Combination of radar systems with cameras
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/66—Radar-tracking systems; Analogous systems
- G01S13/72—Radar-tracking systems; Analogous systems for two-dimensional tracking, e.g. combination of angle and range tracking, track-while-scan radar
- G01S13/723—Radar-tracking systems; Analogous systems for two-dimensional tracking, e.g. combination of angle and range tracking, track-while-scan radar by using numerical data
- G01S13/726—Multiple target tracking
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Radar Systems Or Details Thereof (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a front multi-vehicle tracking method integrating millimeter wave radar and deep learning vision, which specifically comprises the following steps: step one, positioning coordinates; step two, body appearance recognition; step three, route simulation; step four, radar screening; the invention relates to the technical field of radar detection. According to the front multi-vehicle tracking method integrating millimeter wave radar and deep learning vision, scene division is carried out on a video scene by setting standard grids, a three-dimensional space coordinate system is constructed, the millimeter wave radar and a camera are used as information acquisition sources, numerical conversion of a vehicle moving track is achieved, accurate judgment is carried out on the vehicle moving track, feedback information of a target vehicle is timely acquired by matching with data acquisition of the millimeter wave radar, and then the adjacent millimeter wave radar is synchronized, specific coordinate values of the target vehicle in a visual field area are determined through comparison of the feedback information, and therefore efficient continuous tracking of the target vehicle is achieved.
Description
Technical Field
The invention relates to the technical field of radar detection, in particular to a front multi-vehicle tracking method integrating millimeter wave radar and deep learning vision.
Background
On a road running at a high speed, tracking and identifying a specific vehicle have certain difficulty, particularly for continuous tracking with the specific vehicle, the position of the target vehicle can be obtained only in a staged way, and then the staged position points are connected, so that the approximate running track of the vehicle is simulated, the effective judgment on the specific running track of the characteristic vehicle cannot be effectively ensured, and the difficulty of continuous and accurate tracking of the vehicle is increased due to larger calculation processing capacity when the vehicle is tracked for multiple vehicles.
Disclosure of Invention
(One) solving the technical problems
Aiming at the defects of the prior art, the invention provides a front multi-vehicle tracking method integrating millimeter wave radar and deep learning vision, which solves the problems.
(II) technical scheme
In order to achieve the above purpose, the present invention provides the following technical solutions: a millimeter wave radar and deep learning vision fusion front multi-vehicle tracking method specifically comprises the following steps:
Step one, coordinate positioning: after the millimeter wave radar and the camera are constructed, a view field picture of a corresponding area is obtained, a standard area range is set as a standard lattice of a unit, the standard lattice is used as a coordinate point of the view field picture, a three-dimensional space coordinate system is established by taking the millimeter wave radar and the camera as information sources, and the coordinate point of a running vehicle in the corresponding area is monitored;
step two, body appearance recognition: substituting the heights of license plates of different vehicle types into the three-dimensional space coordinate system established in the first step as height coordinates, inputting vehicle type data into an image pickup processor of a camera as final distinguishing data, collecting characteristic data of different vehicle types and identifying the vehicle types as basis;
Step three, route simulation: after the vehicle type is identified, the spatial position of the vehicle license plate in a corresponding three-dimensional space coordinate system is monitored, the vehicle license plate is identified and determined as a target vehicle license plate number, the positioning of the target vehicle is completed, and after the vehicle is positioned, the moving route of the vehicle is outlined according to the coordinate change of the vehicle in the three-dimensional space coordinate system;
Step four, radar screening: according to the detected data of the millimeter wave radar, obviously uncorrelated vehicles are screened out to serve as hidden vehicles, the vehicles are directly hidden on an acquisition picture of a camera, meanwhile, detection is carried out on the target vehicles, detection information of the target vehicles is acquired, the detection data are memorized, the memorized detection data are transmitted to the millimeter wave radar of an adjacent area to serve as detection comparison basis, and after feedback comparison is carried out on the detection data, the target vehicles are found out, and continuous tracking of the target vehicles is carried out.
By adopting the technical scheme, scene division is carried out on the field pictures through setting standard grids, a three-dimensional space coordinate system is constructed, wherein millimeter wave radars and cameras are used as information acquisition sources, numerical conversion of vehicle movement tracks is realized, accurate judgment is carried out on the vehicle movement tracks, feedback information of a target vehicle is timely acquired by matching with data acquisition of the millimeter wave radars, and then the feedback information is synchronized to adjacent millimeter wave radars, and specific coordinate values of the target vehicle in a field area are determined through comparison of the feedback information, so that efficient continuous tracking of the target vehicle is realized.
The invention is further provided with: the standard cell size of one unit in the first step is set to be 0.1 x 0.2m space region.
By adopting the technical scheme, the standard size of the video field picture is finely divided, the accurate judgment of the vehicle when moving in the three-dimensional space coordinate system is ensured, the height value is used as the Z-axis value, license plates of different vehicle types are conveniently monitored, the limit range is defined for the information acquisition of license plates, the corresponding license plate information is simply and rapidly acquired, and convenience is provided for accurate positioning of the target vehicle.
The invention is further provided with: the specific steps of establishing a three-dimensional space coordinate system by taking the millimeter wave radar and the camera as information sources in the first step include: and the coordinate scale of the standard lattice position appearing in the detection picture of the camera is used, the position of the camera is used as the origin of coordinates, a three-dimensional coordinate system is constructed, and then millimeter wave radar coordinates are input into the three-dimensional coordinate system for coordinate perfection, so that a three-dimensional space coordinate system in the imaging visual field range is constructed.
The invention is further provided with: and step two, the height information of license plates of different vehicle types is the height of the license plates of different vehicle types above the ground through networking retrieval and is stored in a local library.
The invention is further provided with: and in the second step, feature data of different vehicle types are collected to screen out appearance feature composition pictures of the different vehicle types in a networking screening mode, and the feature composition pictures are stored in a body library for providing data reference for vehicle type identification.
By adopting the technical scheme, the characteristic data pictures and license plate ground clearance information of different vehicle types are acquired in a networking mode and stored in a local library to serve as standby data, so that the retrieval time for positioning the target vehicle is shortened, and the positioning of the target vehicle is accelerated.
The invention is further provided with: the method for identifying and determining the license plate number of the target vehicle in the third step comprises the following steps: and acquiring license plate number information corresponding to the license plate height in the image shot by the camera, adjusting the license plate number information to be uniform in size, and performing image overlapping comparison with the target license plate number to completely coincide so as to obtain the target vehicle.
By adopting the technical scheme, the license plate numbers are directly compared in a mode of image superposition comparison, the license plate numbers of the target vehicles are simply, rapidly and stably screened out, the positioning speed of the license plate numbers is improved while the processing is simple, and convenience is provided for tracking of multiple vehicles.
The invention is further provided with: and in the fourth step, screening out the obviously uncorrelated vehicles as hidden vehicles, wherein the obviously uncorrelated vehicles are vehicles with the size obviously larger or smaller than the size of the target vehicle.
The invention is further provided with: the memory detection data in the fourth step are specifically feedback information after the appearance detection of the vehicle.
(III) beneficial effects
The invention provides a front multi-vehicle tracking method integrating millimeter wave radar and deep learning vision. The beneficial effects are as follows:
(1) According to the front multi-vehicle tracking method integrating millimeter wave radar and deep learning vision, scene division is carried out on a video scene through setting standard grids, a three-dimensional space coordinate system is constructed, wherein the millimeter wave radar and a camera are used as information acquisition sources, numerical conversion of a vehicle moving track is achieved, accurate judgment is carried out on the vehicle moving track, data acquisition of the millimeter wave radar is matched, feedback information of a target vehicle is timely acquired, and then the feedback information is synchronized to an adjacent millimeter wave radar, and specific coordinate values of the target vehicle in a visual field area are determined through comparison of the feedback information, so that efficient continuous tracking of the target vehicle is achieved.
(2) According to the front multi-vehicle tracking method integrating millimeter wave radar and deep learning vision, through fine division of standard sizes of the video images, accurate judgment of vehicles moving in a three-dimensional space coordinate system is guaranteed, the height value is used as a Z-axis value, license plates of different vehicle types are monitored conveniently, a limited range is acquired for license plate number information, corresponding license plate information is acquired simply and rapidly, and convenience is provided for accurate positioning of target vehicles.
(3) According to the front multi-vehicle tracking method integrating millimeter wave radar and deep learning vision, the characteristic data pictures and license plate ground clearance information of different vehicle types are collected in a networking mode and stored in a local library to serve as standby data, so that the retrieval time when a target vehicle is positioned is shortened, and the positioning of the target vehicle is accelerated.
(4) The millimeter wave radar and deep learning vision fusion type front multi-vehicle tracking method directly carries out license plate number comparison in an image superposition comparison mode, screens out license plates of target vehicles simply, rapidly and stably, processes the license plates simply, improves the positioning speed of the license plates, and provides convenience for tracking of multiple vehicles.
Drawings
FIG. 1 is a schematic flow chart of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the following two technical schemes are provided in the embodiment of the present invention:
Embodiment 1,
A millimeter wave radar and deep learning vision fusion front multi-vehicle tracking method specifically comprises the following steps:
Step one, coordinate positioning: after the millimeter wave radar and the camera are constructed, a view field picture of a corresponding area is obtained, a standard area range is set as a standard lattice of a unit, the standard lattice is used as a coordinate point of the view field picture, a three-dimensional space coordinate system is established by taking the millimeter wave radar and the camera as information sources, and the coordinate point of a running vehicle in the corresponding area is monitored;
step two, body appearance recognition: substituting the heights of license plates of different vehicle types into the three-dimensional space coordinate system established in the first step as height coordinates, inputting vehicle type data into an image pickup processor of a camera as final distinguishing data, collecting characteristic data of different vehicle types and identifying the vehicle types as basis;
Step three, route simulation: after the vehicle type is identified, the spatial position of the vehicle license plate in a corresponding three-dimensional space coordinate system is monitored, the vehicle license plate is identified and determined as a target vehicle license plate number, the positioning of the target vehicle is completed, and after the vehicle is positioned, the moving route of the vehicle is outlined according to the coordinate change of the vehicle in the three-dimensional space coordinate system;
Step four, radar screening: according to the detected data of the millimeter wave radar, obviously uncorrelated vehicles are screened out to serve as hidden vehicles, the vehicles are directly hidden on an acquisition picture of a camera, meanwhile, detection is carried out on the target vehicles, detection information of the target vehicles is acquired, the detection data are memorized, the memorized detection data are transmitted to millimeter wave radars of adjacent areas and are used as detection comparison basis, the target vehicles are found after feedback comparison is carried out on the detection data, continuous tracking of the target vehicles is carried out, further, a standard grid is set for carrying out scene division on the visual field picture, a three-dimensional space coordinate system is constructed, wherein numerical conversion of moving tracks of the vehicles is realized by taking the millimeter wave radars and the camera as information acquisition sources, accurate judgment is carried out on the tracks of the vehicles, feedback information of the target vehicles is acquired in time in cooperation with the data acquisition of the millimeter wave radars, and then the feedback information is synchronized to the adjacent millimeter wave radars, and specific coordinate values of the target vehicles in the visual field area are determined through comparison of the feedback information, and therefore high-efficiency continuous tracking of the target vehicles is realized.
Embodiment II,
The embodiment is an improvement of the previous embodiment, and is a front multi-vehicle tracking method with millimeter wave radar and deep learning vision fusion, specifically comprising the following steps:
Step one, coordinate positioning: after the millimeter wave radar and the camera are constructed, a view field picture of a corresponding area is obtained, a standard area range is set as a standard lattice of a unit, the standard lattice size of one unit is set to be 0.1 x 0.2m space area, the standard lattice is used as a coordinate point of the view field picture, and the millimeter wave radar and the camera are used as information sources to establish a three-dimensional space coordinate system, and the method specifically comprises the following steps: the method comprises the steps of constructing a three-dimensional coordinate system by using a standard grid position coordinate scale appearing in a detection picture of a camera and using a position of the camera as a coordinate origin, inputting millimeter wave radar coordinates into the three-dimensional coordinate system for coordinate perfection, constructing a three-dimensional space coordinate system within an imaging visual field range, and monitoring coordinate points of a running vehicle in a corresponding area;
Step two, body appearance recognition: the method comprises the steps of storing height information of license plates of different vehicle types in a local library, substituting the height information of the license plates of the different vehicle types into a three-dimensional space coordinate system established in the first step as height coordinates, inputting vehicle type data into an image taking processor of a camera as final distinguishing data, screening out appearance characteristic composition pictures of the different vehicle types in a networking screening mode, storing the characteristic composition pictures in a body library, providing data reference for vehicle type identification, collecting characteristic data of the different vehicle types, and carrying out vehicle type identification according to the collected characteristic data;
Step three, route simulation: after the vehicle type is identified, the spatial position of the vehicle license plate in the corresponding three-dimensional spatial coordinate system is monitored, and the vehicle license plate is identified and determined as the target vehicle license plate number, which comprises the following steps: the method comprises the steps of obtaining license plate number information of corresponding license plate heights in a camera shooting picture, adjusting the license plate number information to be uniform in size, performing image overlapping comparison with a target license plate number, completely overlapping to obtain a target vehicle, positioning the target vehicle, and outlining a moving route of the vehicle according to coordinate changes of the vehicle in a three-dimensional space coordinate system after positioning the vehicle;
Step four, radar screening: screening out obviously uncorrelated vehicles according to detected data of the millimeter wave radar, wherein the obviously uncorrelated vehicles are vehicles with the size obviously larger or smaller than that of the target vehicle, and are used as hidden vehicles, the hidden vehicles are directly hidden on a camera acquisition picture, meanwhile, detection is carried out on the target vehicle, detection information of the target vehicle is acquired, feedback information after appearance detection of the vehicle is memorized, the memorized detection data are transmitted to the millimeter wave radar of an adjacent area and are used as detection comparison basis, and after feedback comparison is carried out on the memorized detection data, the target vehicle is found out, and continuous tracking of the target vehicle is carried out.
The advantages of the embodiment over the first embodiment are: the visual field picture is finely divided in standard size, so that accurate judgment on the movement of the vehicle in a three-dimensional space coordinate system is guaranteed, the height value is used as a Z-axis value, license plates of different vehicle types are conveniently monitored, a limited range is obtained for license plate information, corresponding license plate information is simply and rapidly obtained, convenience is provided for accurate positioning of the target vehicle, characteristic data pictures of different vehicle types and license plate ground clearance height information are collected in a networking mode and stored in a local library, the search time for positioning the target vehicle is reduced as standby data, positioning of the target vehicle is accelerated, license plate number comparison is directly carried out in a mode of image superposition comparison, the license plate number of the target vehicle is simply, rapidly and stably screened out, the positioning speed of the license plate number is improved while the processing is simple, and convenience is provided for tracking of multiple vehicles.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (8)
1. A forward multi-vehicle tracking method integrating millimeter wave radar and deep learning vision is characterized by comprising the following steps of: the method specifically comprises the following steps:
Step one, coordinate positioning: after the millimeter wave radar and the camera are constructed, a view field picture of a corresponding area is obtained, a standard area range is set as a standard lattice of a unit, the standard lattice is used as a coordinate point of the view field picture, a three-dimensional space coordinate system is established by taking the millimeter wave radar and the camera as information sources, and the coordinate point of a running vehicle in the corresponding area is monitored;
step two, body appearance recognition: substituting the heights of license plates of different vehicle types into the three-dimensional space coordinate system established in the first step as height coordinates, inputting vehicle type data into an image pickup processor of a camera as final distinguishing data, collecting characteristic data of different vehicle types and identifying the vehicle types as basis;
Step three, route simulation: after the vehicle type is identified, the spatial position of the vehicle license plate in a corresponding three-dimensional space coordinate system is monitored, the vehicle license plate is identified and determined as a target vehicle license plate number, the positioning of the target vehicle is completed, and after the vehicle is positioned, the moving route of the vehicle is outlined according to the coordinate change of the vehicle in the three-dimensional space coordinate system;
Step four, radar screening: according to the detected data of the millimeter wave radar, obviously uncorrelated vehicles are screened out to serve as hidden vehicles, the vehicles are directly hidden on an acquisition picture of a camera, meanwhile, detection is carried out on the target vehicles, detection information of the target vehicles is acquired, the detection data are memorized, the memorized detection data are transmitted to the millimeter wave radar of an adjacent area to serve as detection comparison basis, and after feedback comparison is carried out on the detection data, the target vehicles are found out, and continuous tracking of the target vehicles is carried out.
2. The front multi-vehicle tracking method based on the fusion of millimeter wave radar and deep learning vision according to claim 1, wherein the method comprises the following steps: the standard cell size of one unit in the first step is set to be 0.1 x 0.2m space region.
3. The front multi-vehicle tracking method based on the fusion of millimeter wave radar and deep learning vision according to claim 1, wherein the method comprises the following steps: the specific steps of establishing a three-dimensional space coordinate system by taking the millimeter wave radar and the camera as information sources in the first step include: and the coordinate scale of the standard lattice position appearing in the detection picture of the camera is used, the position of the camera is used as the origin of coordinates, a three-dimensional coordinate system is constructed, and then millimeter wave radar coordinates are input into the three-dimensional coordinate system for coordinate perfection, so that a three-dimensional space coordinate system in the imaging visual field range is constructed.
4. The front multi-vehicle tracking method based on the fusion of millimeter wave radar and deep learning vision according to claim 1, wherein the method comprises the following steps: and step two, the height information of license plates of different vehicle types is the height of the license plates of different vehicle types above the ground through networking retrieval and is stored in a local library.
5. The front multi-vehicle tracking method based on the fusion of millimeter wave radar and deep learning vision according to claim 1, wherein the method comprises the following steps: and in the second step, feature data of different vehicle types are collected to screen out appearance feature composition pictures of the different vehicle types in a networking screening mode, and the feature composition pictures are stored in a body library for providing data reference for vehicle type identification.
6. The front multi-vehicle tracking method based on the fusion of millimeter wave radar and deep learning vision according to claim 1, wherein the method comprises the following steps: the method for identifying and determining the license plate number of the target vehicle in the third step comprises the following steps: and acquiring license plate number information corresponding to the license plate height in the image shot by the camera, adjusting the license plate number information to be uniform in size, and performing image overlapping comparison with the target license plate number to completely coincide so as to obtain the target vehicle.
7. The front multi-vehicle tracking method based on the fusion of millimeter wave radar and deep learning vision according to claim 1, wherein the method comprises the following steps: and in the fourth step, screening out the obviously uncorrelated vehicles as hidden vehicles, wherein the obviously uncorrelated vehicles are vehicles with the size obviously larger or smaller than the size of the target vehicle.
8. The front multi-vehicle tracking method based on the fusion of millimeter wave radar and deep learning vision according to claim 1, wherein the method comprises the following steps: the memory detection data in the fourth step are specifically feedback information after the appearance detection of the vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111432862.8A CN114137512B (en) | 2021-11-29 | 2021-11-29 | Front multi-vehicle tracking method integrating millimeter wave radar and deep learning vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111432862.8A CN114137512B (en) | 2021-11-29 | 2021-11-29 | Front multi-vehicle tracking method integrating millimeter wave radar and deep learning vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114137512A CN114137512A (en) | 2022-03-04 |
| CN114137512B true CN114137512B (en) | 2024-04-26 |
Family
ID=80389284
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111432862.8A Active CN114137512B (en) | 2021-11-29 | 2021-11-29 | Front multi-vehicle tracking method integrating millimeter wave radar and deep learning vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114137512B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116363623B (en) * | 2023-01-28 | 2023-10-20 | 苏州飞搜科技有限公司 | Vehicle detection method based on millimeter wave radar and vision fusion |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20170080480A (en) * | 2015-12-30 | 2017-07-10 | 건아정보기술 주식회사 | The vehicle detecting system by converging radar and image |
| CN109459750A (en) * | 2018-10-19 | 2019-03-12 | 吉林大学 | A kind of more wireless vehicle trackings in front that millimetre-wave radar is merged with deep learning vision |
| WO2020149576A1 (en) * | 2019-01-17 | 2020-07-23 | 주식회사 엠제이비전테크 | Artificial intelligence-based vehicle search system |
| CN111862157A (en) * | 2020-07-20 | 2020-10-30 | 重庆大学 | Multi-vehicle target tracking method integrating machine vision and millimeter wave radar |
| CN113129592A (en) * | 2021-04-16 | 2021-07-16 | 江西方兴科技有限公司 | Holographic sensing system and method for traffic state of highway tunnel |
| WO2021223368A1 (en) * | 2020-05-08 | 2021-11-11 | 泉州装备制造研究所 | Target detection method based on vision, laser radar, and millimeter-wave radar |
-
2021
- 2021-11-29 CN CN202111432862.8A patent/CN114137512B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20170080480A (en) * | 2015-12-30 | 2017-07-10 | 건아정보기술 주식회사 | The vehicle detecting system by converging radar and image |
| CN109459750A (en) * | 2018-10-19 | 2019-03-12 | 吉林大学 | A kind of more wireless vehicle trackings in front that millimetre-wave radar is merged with deep learning vision |
| WO2020149576A1 (en) * | 2019-01-17 | 2020-07-23 | 주식회사 엠제이비전테크 | Artificial intelligence-based vehicle search system |
| WO2021223368A1 (en) * | 2020-05-08 | 2021-11-11 | 泉州装备制造研究所 | Target detection method based on vision, laser radar, and millimeter-wave radar |
| CN111862157A (en) * | 2020-07-20 | 2020-10-30 | 重庆大学 | Multi-vehicle target tracking method integrating machine vision and millimeter wave radar |
| CN113129592A (en) * | 2021-04-16 | 2021-07-16 | 江西方兴科技有限公司 | Holographic sensing system and method for traffic state of highway tunnel |
Non-Patent Citations (2)
| Title |
|---|
| 基于毫米波雷达和机器视觉信息融合的障碍物检测;翟光耀;陈蓉;张剑锋;张继光;吴澄;汪一鸣;;物联网学报;20170930(第02期);全文 * |
| 基于毫米波雷达和机器视觉的夜间前方车辆检测;金立生;程蕾;成波;;汽车安全与节能学报;20160615(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114137512A (en) | 2022-03-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109919974B (en) | Online multi-target tracking method based on R-FCN frame multi-candidate association | |
| CN102291569B (en) | Double-camera automatic coordination multi-target eagle eye observation system and observation method thereof | |
| CN111462200A (en) | Cross-video pedestrian positioning and tracking method, system and equipment | |
| CN101344965A (en) | Tracking system based on binocular camera shooting | |
| CN102447835A (en) | Non-blind-area multi-target cooperative tracking method and system | |
| CN111161313B (en) | Multi-target tracking method and device in video stream | |
| CN103646257B (en) | A kind of pedestrian detection and method of counting based on video monitoring image | |
| CN112241969A (en) | Target detection tracking method and device based on traffic monitoring video and storage medium | |
| CN105608417A (en) | Traffic signal lamp detection method and device | |
| CN109446917A (en) | A kind of vanishing Point Detection Method method based on cascade Hough transform | |
| CN106504274A (en) | A kind of visual tracking method and system based under infrared camera | |
| CN111199556A (en) | Indoor pedestrian detection and tracking method based on camera | |
| CN105740835A (en) | Preceding vehicle detection method based on vehicle-mounted camera under night-vision environment | |
| CN105913459A (en) | Moving object detection method based on high resolution continuous shooting images | |
| CN104200492A (en) | Automatic detecting and tracking method for aerial video target based on trajectory constraint | |
| CN101894380A (en) | Method for tracing target object in panoramic video automatically | |
| CN113256731A (en) | Target detection method and device based on monocular vision | |
| CN114137512B (en) | Front multi-vehicle tracking method integrating millimeter wave radar and deep learning vision | |
| CN107506753B (en) | Multi-vehicle tracking method for dynamic video monitoring | |
| CN106558069A (en) | A kind of method for tracking target and system based under video monitoring | |
| CN110864670B (en) | Method and system for acquiring position of target obstacle | |
| Liu et al. | Multi-view vehicle detection and tracking in crossroads | |
| CN110335308B (en) | Binocular vision odometer calculation method based on parallax constraint and bidirectional annular inspection | |
| Du et al. | Particle filter based object tracking of 3D sparse point clouds for autopilot | |
| CN116092035A (en) | Lane line detection method, lane line detection device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |