CN109615870A - A kind of traffic detection system based on millimetre-wave radar and video - Google Patents
A kind of traffic detection system based on millimetre-wave radar and video Download PDFInfo
- Publication number
- CN109615870A CN109615870A CN201811653251.4A CN201811653251A CN109615870A CN 109615870 A CN109615870 A CN 109615870A CN 201811653251 A CN201811653251 A CN 201811653251A CN 109615870 A CN109615870 A CN 109615870A
- Authority
- CN
- China
- Prior art keywords
- target
- millimetre
- wave radar
- data
- video
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
- G08G1/054—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed photographing overspeeding vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/056—Detecting movement of traffic to be counted or controlled with provision for distinguishing direction of travel
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The traffic detection system based on millimetre-wave radar and video that the invention discloses a kind of, belongs to the data acquisition and processing (DAP) technical field in intelligent transportation.The present invention acquires target information by millimetre-wave radar sensor and video sensor, it carries out world coordinates and is converted into plane of delineation coordinate, determine the position of target projection that millimetre-wave radar sensor acquisition testing arrives on the image plane, target type is identified by image machine learning, by the data fusion of video sensor and millimetre-wave radar acquisition, speed, coordinate, the type of target are exported.The present invention reduces the data difficulty in computation of system, simplifies system flow.Video sensor carries out real time data with the data that millimetre-wave radar detects and merges, and fused target information is sent to system platform, alleviates the calculation amount of system, accelerates the response time of system, improves detection accuracy.
Description
Technical field
The invention belongs to the data acquisition and processing (DAP) technical fields in intelligent transportation, and in particular to one kind is based on millimeter wave thunder
Up to the traffic detection system with video.
Background technique
Video sensor is all used in existing traffic detection system mostly, single video sensor is smart in detection effect
Exactness is not high, and the delay of image procossing is big, and its precision is easy to be influenced by environment such as rain, mists.Later Vehicle Detection system
It is gradually added into the sensors such as other types of sensor, such as millimetre-wave radar, earth magnetism, laser radar in system, utilizes not simultaneous interpretation
The advantage of sensor carries out Fusion, substantially increases the detection performance of system.Radar sensor can accomplish reality
When detect the position and speed information of target, data processing can reach 20 times per second, and environmental suitability is strong, can be round-the-clock, complete
It when work, drawback is can not to visualize.And video sensor is capable of handling image information, if carrying out analysis meter to image
It calculates, needs to take a long time by transcoding, can not accomplish real-time response, and environmental suitability is not high.
Using the advantage of both sensors, Data Fusion can be carried out using radar and video as detection front end.But
Since the data format that both sensors respectively independently carry out data acquisition and output is inconsistent, system is finally by multiple biographies
The much information of the collected same target of sensor is lengthy and jumbled together, huge to the treating capacity of initial data, and it is flat to have aggravated system
The data processing work of platform.And in current system, radar and video camera are needed when information merges due to its installation site difference
The coordinate system of two kinds of sensors is associated, and two sensor coordinates associations are related with their relative position, if its
In a sensor have movement slightly, need associated coordinates again.Due to two sensors in use often by
Shake, installation site has deviation after a period of time, leads to being not fixed for distance and angle, needs periodically to re-start coordinate
Match, so installation and debugging difficulty is big, it is often necessary to safeguard.
Summary of the invention
The present invention is provided for prior art mechanism complexity and ineffective problem, is provided a kind of based on millimeter wave
The traffic detection system of radar and video.
Specifically, the present invention adopts the following technical solutions realize: the traffic detection system include data acquisition
Unit, data processing unit, data storage cell, data communication units and system platform；
The data acquisition unit includes millimetre-wave radar sensor and video sensor, and millimetre-wave radar sensor is real-time
The acquisition coordinate position of target, the speed of target, the length of target are sent to data processing unit；Video sensor acquires in real time
High-definition image data are sent to data processing unit；
The data processing unit includes microprocessor and embedded neural network processor, to same target from milli
It is defeated finally to be pressed unified format by the data information fusion that metre wave radar and video sensor detect for the complete information of same target
Out to system platform；
The implementation of the traffic detection system the following steps are included:
Step 1: millimetre-wave radar sensor acquires target information, the target information includes the identifier of target, speed
Degree, coordinate, length, video sensor acquire the image information on road surface, and the millimetre-wave radar sensor and the video are passed
The collected initial data of sensor is sent to data processing unit；
Step 2: world coordinates is converted into plane of delineation coordinate；Millimetre-wave radar sensor collects coordinates of targets, then
The camera of internal reference and outer ginseng to the camera of video sensor is corrected, and obtains turn of coordinates of targets and plane of delineation coordinate
Matrix is changed, road surface world coordinates is converted into plane of delineation coordinate, determines the mesh that millimetre-wave radar sensor acquisition testing arrives
The position of mark projection on the image plane；
Step 3: using the target type in image captured by neural network framework identification video sensor；It is being embedded in
Neural network framework algorithm is run in formula neural network processor, it is by image machine learning, the image on road surface is unstructured
Data conversion at target type and color structural data；
Step 4: millimetre-wave radar sensor is detected using the coordinate conversion of step 2 and the image recognition of step 3
To target of the target in the image that camera takes corresponded to, get all parameter informations of each target, scheming
Superposition target component is merged as in, and the parameter information includes speed, coordinate, the target type of each target；
Step 5: the fused target component is sent to system platform.
Furthermore, world coordinates described in step 2 is converted into plane of delineation coordinate, i.e., by mesh in world coordinate system
The conversion of point of the target point into image coordinate system is divided into the realization of two steps:
(1) coordinate (X of the target for detecting millimetre-wave radar sensor in world coordinate systemw, Yw, Zw) transform to
Camera coordinates system (Xc, Yc, Zc), transformation for mula are as follows:
In formula,For by the spin matrix of world coordinate system to camera coordinates system；
I.e.
α wherein is rotated to be around X-axis, β is rotated to be around Y-axis, rotates to be θ about the z axis；
For by the translation matrix of world coordinate system to camera coordinates system, due to millimetre-wave radar sensor in the present apparatus
With it is close at a distance from video sensor, the length of translation is equivalent to 0, i.e.,
It can acquire:
Target can be obtained by the coordinate (X in world coordinate systemw, Yw, Zw) transform to camera coordinates system (Xc, Yc, Zc)
XC=cos (β) cos (θ) XW+cos(β)sin(θ)YW-sin(β)ZW
YC=(- cos (α) sin (θ)+sin (α) sin (θ) cos (θ)) XW+(cos(α)cos(θ)+sin(α)sin(β)sin
(θ))YW
+sin(α)cos(β)ZW
ZC=(sin (α) sin (θ)+cos (α) sin (β) cos (θ)) XW+(-sin(α)cos(θ)+cos(α)sin(β)sin
(θ))Yw+cos(α)cos(β)ZW
(2) target that will test again transforms to image coordinate system by camera coordinates system, determines that target is passed in the video
Projected position (X in picture captured by sensorS, YS), realize the millimetre-wave radar sensor target that detects on the image
Positioning:
ω is the horizontal view angle of target in the camera,For the vertical angle of view of target in the camera, v is the lateral ruler of image
Very little, h is the vertical size of image.
Furthermore, in step 3, video sensor identifies the data after target type, in data processing unit
The calculating of traffic flow statistics data is carried out, the target that simultaneously tracing detection arrives is counted, each period in a certain specified region is calculated
The traffic flow statistics data of interior each vehicle.
Furthermore, the data processing unit is detected according to millimetre-wave radar sensor target velocity, coordinate
Judge target with the presence or absence of hypervelocity, drive in the wrong direction, disobey and the traffic events such as stop；If traffic events occur, the data processing unit is sent
Instruction allows video sensor to be taken pictures, enrolls video evidence obtaining, and the text information of event, image data, video data are passed
To system platform.
Beneficial effects of the present invention are as follows: the present invention is based on the traffic detection systems of millimetre-wave radar and video, reduce system
The data difficulty in computation of system simplifies system flow.The collected raw image data of video sensor is sent to data processing list
Member needs not move through Video coding and decoding operate, thus the no-delay phenomenon of data, the data that can be detected with millimetre-wave radar
Carry out real time data fusion.The preliminary fusion treatment that the two data are carried out in data processing unit, fused target is believed
Breath is sent to system platform, alleviates the calculation amount of system, accelerates the response time of system, improve detection accuracy.
Detailed description of the invention
Fig. 1 is system construction drawing of the invention.
Fig. 2 is system flow chart of the invention.
Fig. 3 is the camera calibration schematic diagram of video sensor in the present invention.
Fig. 4 be in the present invention target from camera coordinates system to the schematic diagram of image coordinate system projection relation.
Specific embodiment
Below with reference to embodiment and referring to attached drawing, present invention is further described in detail.
Embodiment 1:
One embodiment of the present of invention is a kind of traffic detection system based on millimetre-wave radar and video, referring to Fig.1,
Fig. 2, Fig. 3 and Fig. 4, the traffic detection system based on millimetre-wave radar and video include data acquisition unit, data processing unit,
Data storage cell, data communication units and system platform.
Data acquisition unit: data acquisition unit includes millimetre-wave radar sensor and video sensor.Millimetre-wave radar
Sensor acquires target information in real time, and the data content detected includes the coordinate position of target, the speed of target, the length of target
Degree etc., is sent to data processing unit for collected target information.Video sensor acquires high-definition image data in real time, will adopt
The image information collected is sent to data processing unit.
Data processing unit: data processing unit includes ARM microprocessor and embedded neural network processor (NPU).
Embedded neural network processor (NPU) is responsible for the processing of image data, identifies the type (pedestrian, automobile, truck etc.) of target,
And by the data of the collected target information of millimetre-wave radar (coordinate position of target, the speed of target, length of target etc.)
It is superimposed upon in video image.ARM microprocessor is responsible for counting the information of all traffic flows and traffic events identification.Data processing
In unit to real-time reception to target information carry out same target coordinate convert, by same target come from millimetre-wave radar
The data information fusion detected with video sensor is finally exported the complete information of same target to system by unified format
Platform.
Data storage cell: data storage cell includes built-in multimedia storage card (EMMC) and SD card.Including insertion
Formula multimedia storage card (EMMC) is used for storage program area, and SD card is for storing traffic flow data library and traffic event information.
Data communication units: communication unit includes network (ETH) interface and RS485 interface, network (ETH) interface be used for
System platform transmits telecommunication flow information, traffic event information, video image information.RS485 interface for dock bayonet camera and
Crossing traffic controls semaphore.
As shown in Fig. 2, the implementation of the traffic detection system based on millimetre-wave radar and video the following steps are included:
Step 1: millimetre-wave radar sensor and video sensor carry out the letter of target and road surface as environment sensing front end
Breath acquisition, acquires target information and pavement image information, and millimetre-wave radar sensor and video sensor are collected respectively
Initial data be sent to data processing unit.Wherein the collected information of millimetre-wave radar sensor includes the identifier of target
(ID), speed, coordinate, length etc., video sensor collect the image information on road surface.
Step 2: world coordinates is converted into plane of delineation coordinate.Millimetre-wave radar sensor collects coordinates of targets, then
The camera of internal reference and outer ginseng to the camera of video sensor is corrected, and obtains turn of coordinates of targets and plane of delineation coordinate
Matrix (i.e. spin matrix and translation matrix) is changed, road surface world coordinates is converted into plane of delineation coordinate, may thereby determine that out
The position of the target projection that millimetre-wave radar sensor acquisition testing arrives on the image plane.
The conversion process of point of the point of target into image coordinate system is realized in two steps in world coordinate system:
(1) coordinate (X of the target for detecting millimetre-wave radar sensor in world coordinate systemw, Yw, Zw) transform to
Camera coordinates system (Xc, Yc, Zc), transformation for mula are as follows:
In formula,For by the spin matrix of world coordinate system to camera coordinates system.
I.e.
As shown in figure 3, wherein rotating to be α around X-axis, β is rotated to be around Y-axis, rotates to be θ about the z axis.
For by the translation matrix of world coordinate system to camera coordinates system, due to millimetre-wave radar sensor in the present apparatus
With it is close at a distance from video sensor, the length of translation is equivalent to 0, i.e.,
It can acquire:
Target can be obtained by the coordinate (X in world coordinate systemw, Yw, Zw) transform to camera coordinates system (Xc, Yc, Zc)
XC=cos (β) cos (θ) XW+cos(β)sin(θ)YW-sin(β)ZW
YC=(- cos (α) sin (θ)+sin (α) sin (θ) cos (θ)) XW+ (cos (α) cos (θ)+sin (α) sin (β)
sin(θ))YW
+sin(α)cos(β)ZW
ZC=(sin (α) sin (θ)+cos (α) sin (β) cos (θ)) XW+(-sin(α)cos(θ)+cos(α)sin(β)sin
(θ))Yw+cos(α)cos(β)ZW
(2) target that will test again transforms to image coordinate system by camera coordinates system, determines target in video sensor
Projected position (X in captured pictureS, YS), realize the target that detects of millimetre-wave radar sensor determining on the image
Position.
As shown in figure 4, ω is the horizontal view angle of target in the camera,For the vertical angle of view of target in the camera, v is figure
The lateral dimension of picture, h are the vertical size of image.
Step 3: using the target type in image captured by neural network framework YOLO identification video sensor.Depending on
Frequency detector only needs to identify the classification of target, and the calculating complicated without other reduces the delay of transcoding, accelerates system
Response time.YOLO algorithm is run in neural processing unit (NPU), neural processing unit (NPU) is using " data-driven is parallel
The image unstructured data on road surface is converted into the knot of target type and color by image machine learning by the framework of calculating "
Structure data.
Step 4: using the coordinate conversion of step 2 and the image recognition of step 3, it can be by millimetre-wave radar sensor
Target of the target detected in the image that camera takes is corresponded to, and all parameter informations of each target are got,
It is superimposed the parameter of target in the picture, parameter includes the speed of each target, coordinate, target type (including vehicle, the letter such as color
Breath).The target data that two sensors of fusion calculation detect, increases available target component type, improves system
Detection accuracy.
Step 5: fused target component (speed, coordinate, type etc.) is sent to system platform.Two are sensed
The initial data that device detects carries out rough estimates processing, and the initial data without detecting front-end collection unit, which is all transmitted to, is
System platform, greatly reduces the calculation amount of system.
Data after identifying target type using video sensor, can also further traffic flow in data processing unit
Statistical data calculates.The target that simultaneously tracing detection arrives is counted, each vehicle in a certain specified region in each period is calculated
(non-motor vehicle, car, bus, lorry) crosses the traffic flow statistics such as vehicle flowrate, average speed, occupation rate, time headway
Data.
In data processing unit target can also be judged according to target velocity that millimetre-wave radar sensor detects, coordinate
With the presence or absence of hypervelocity, drives in the wrong direction, disobeys and the traffic events such as stop.If traffic events occur, data processing unit, which sends instruction, allows video to pass
Sensor is taken pictures, enrolls video evidence obtaining, and the text information of event, image data, video data are reached system platform.
Although the present invention has been described by way of example and in terms of the preferred embodiments, embodiment is not for the purpose of limiting the invention.Not
It is detached from the spirit and scope of the present invention, any equivalent change or retouch done also belongs to the protection scope of the present invention.Cause
This protection scope of the present invention should be based on the content defined in the claims of this application.
Claims (4)
1. a kind of traffic detection system based on millimetre-wave radar and video, which is characterized in that the traffic detection system includes
Data acquisition unit, data processing unit, data storage cell, data communication units and system platform；
The data acquisition unit includes millimetre-wave radar sensor and video sensor, and millimetre-wave radar sensor acquires in real time
The coordinate position of target, the speed of target, the length of target are sent to data processing unit；Video sensor acquires high definition in real time
Image data is sent to data processing unit；
The data processing unit includes microprocessor and embedded neural network processor, comes from millimeter wave to same target
The fusion of data information that radar and video sensor detect, finally by the complete information of same target by unified format export to
System platform；
The implementation of the traffic detection system the following steps are included:
Step 1: millimetre-wave radar sensor acquires target information, the target information includes identifier, speed, the seat of target
Mark, length, video sensor acquire the image information on road surface, the millimetre-wave radar sensor and the video sensor are adopted
The initial data collected is sent to data processing unit；
Step 2: world coordinates is converted into plane of delineation coordinate；Millimetre-wave radar sensor collects coordinates of targets, then to view
The internal reference of the camera of video sensor and the camera of outer ginseng are corrected, and obtain the conversion square of coordinates of targets Yu plane of delineation coordinate
Battle array, is converted into plane of delineation coordinate for road surface world coordinates, determines that the target that millimetre-wave radar sensor acquisition testing arrives is thrown
The position of shadow on the image plane；
Step 3: using the target type in image captured by neural network framework identification video sensor；In embedded mind
Through running neural network framework algorithm in network processing unit, by image machine learning, by the image unstructured data on road surface
It is converted into the structural data of target type and color；
Step 4: millimetre-wave radar sensor is detected using the coordinate conversion of step 2 and the image recognition of step 3
Target of the target in the image that camera takes is corresponded to, and gets all parameter informations of each target, in the picture
Superposition target component is merged, and the parameter information includes speed, coordinate, the target type of each target；
Step 5: the fused target component is sent to system platform.
2. the traffic detection system according to claim 1 based on millimetre-wave radar and video, it is characterised in that: step 2
Described in world coordinates be converted into plane of delineation coordinate, i.e. the point by the point of target in world coordinate system into image coordinate system
Conversion is divided into the realization of two steps:
(1) coordinate (X of the target for detecting millimetre-wave radar sensor in world coordinate systemw, Yw, Zw) transform to camera
Coordinate system (Xc, Yc, Zc), transformation for mula are as follows:
In formula,For by the spin matrix of world coordinate system to camera coordinates system；
I.e.
α wherein is rotated to be around X-axis, β is rotated to be around Y-axis, rotates to be θ about the z axis；
Due to millimetre-wave radar sensor in the present apparatus and to regard by the translation matrix of world coordinate system to camera coordinates system
The distance of video sensor is close, and the length of translation is equivalent to 0, i.e.,
It can acquire:
Target can be obtained by the coordinate (X in world coordinate systemw, Yw, Zw) transform to camera coordinates system (Xc, Yc, Zc)
Xc=cos (β) cos (θ) Xw+cos(β)sin(θ)Yw-sin(β)Zw
Yc=(- cos (α) sin (θ)+sin (α) sin (θ) cos (θ)) Xw+(cos(α)cos(θ)+sin(α)sin(β)sin(θ))
Yw+sin(α)cos(β)Zw
Zc=(sin (α) sin (θ)+cos (α) sin (β) cos (θ)) Xw+(-sin(α)cos(θ)+cos(α)sin(β)sin(θ))
Yw+cos(α)cos(β)Zw
(2) target that will test again transforms to image coordinate system by camera coordinates system, determines target in the video sensor
Projected position (X in captured pictures, Ys), realize the target that detects of millimetre-wave radar sensor determining on the image
Position:
ω is the horizontal view angle of target in the camera,For the vertical angle of view of target in the camera, v is the lateral dimension of image, h
For the vertical size of image.
3. the traffic detection system according to claim 1 based on millimetre-wave radar and video, it is characterised in that: in step
In three, video sensor identifies the data after target type, and the calculating of traffic flow statistics data, system are carried out in data processing unit
The target that simultaneously tracing detection arrives is counted, the traffic flow statistics number of each vehicle in a certain specified region in each period is calculated
According to.
4. the traffic detection system according to claim 1 based on millimetre-wave radar and video, it is characterised in that: the number
The target velocity that is detected according to processing unit according to millimetre-wave radar sensor, coordinate judge target with the presence or absence of hypervelocity, drive in the wrong direction,
Disobey stop equal traffic events；If traffic events occur, the data processing unit, which sends instruction, allows video sensor to be taken pictures, be recorded
It takes video to collect evidence, and the text information of event, image data, video data is reached into system platform.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811653251.4A CN109615870A (en) | 2018-12-29 | 2018-12-29 | A kind of traffic detection system based on millimetre-wave radar and video |
| PCT/CN2019/113964 WO2020134512A1 (en) | 2018-12-29 | 2019-10-29 | Traffic detection system based on millimeter wave radar and video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811653251.4A CN109615870A (en) | 2018-12-29 | 2018-12-29 | A kind of traffic detection system based on millimetre-wave radar and video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109615870A true CN109615870A (en) | 2019-04-12 |
Family
ID=66016540
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811653251.4A Pending CN109615870A (en) | 2018-12-29 | 2018-12-29 | A kind of traffic detection system based on millimetre-wave radar and video |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109615870A (en) |
| WO (1) | WO2020134512A1 (en) |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109613537A (en) * | 2019-01-16 | 2019-04-12 | 南京奥杰智能科技有限公司 | A kind of hologram radar |
| CN110288832A (en) * | 2019-07-10 | 2019-09-27 | 南京慧尔视智能科技有限公司 | It is merged based on microwave with the multiple-object information of video and visual presentation method |
| CN110341621A (en) * | 2019-07-10 | 2019-10-18 | 北京百度网讯科技有限公司 | A kind of obstacle detection method and device |
| CN110428626A (en) * | 2019-08-13 | 2019-11-08 | 舟山千眼传感技术有限公司 | A kind of wagon detector and its installation method of microwave and video fusion detection |
| CN110515073A (en) * | 2019-08-19 | 2019-11-29 | 南京慧尔视智能科技有限公司 | The trans-regional networking multiple target tracking recognition methods of more radars and device |
| CN110738846A (en) * | 2019-09-27 | 2020-01-31 | 同济大学 | Vehicle behavior monitoring system based on radar and video group and implementation method thereof |
| CN110796868A (en) * | 2019-12-02 | 2020-02-14 | 江苏中路工程技术研究院有限公司 | Video and microwave integrated traffic incident monitoring system and method |
| CN110794405A (en) * | 2019-10-18 | 2020-02-14 | 北京全路通信信号研究设计院集团有限公司 | Target detection method and system based on camera and radar fusion |
| CN110865366A (en) * | 2019-10-12 | 2020-03-06 | 深圳市布谷鸟科技有限公司 | Intelligent driving radar and image fusion man-machine interaction method |
| CN111127877A (en) * | 2019-11-19 | 2020-05-08 | 华为技术有限公司 | Road condition information monitoring method and device |
| CN111178215A (en) * | 2019-12-23 | 2020-05-19 | 深圳成谷科技有限公司 | Sensor data fusion processing method and device |
| WO2020134512A1 (en) * | 2018-12-29 | 2020-07-02 | 南京慧尔视智能科技有限公司 | Traffic detection system based on millimeter wave radar and video |
| CN111427038A (en) * | 2020-03-23 | 2020-07-17 | 厦门大学 | Target identification method based on vision and 77GHz radar in garage environment |
| CN111476099A (en) * | 2020-03-09 | 2020-07-31 | 深圳市人工智能与机器人研究院 | Target detection method, target detection device and terminal equipment |
| CN111753901A (en) * | 2020-06-23 | 2020-10-09 | 国汽(北京)智能网联汽车研究院有限公司 | Data fusion method, device and system and computer equipment |
| CN111830470A (en) * | 2019-04-16 | 2020-10-27 | 杭州海康威视数字技术股份有限公司 | Combined calibration method and device, and target object detection method, system and device |
| CN112115810A (en) * | 2020-08-31 | 2020-12-22 | 南京理工大学 | Target identification method, system, computer equipment and storage medium based on information fusion |
| CN112150799A (en) * | 2020-08-19 | 2020-12-29 | 上海图丽信息技术有限公司 | Method for collecting road vehicle traffic big data by fusing radar videos |
| CN112258834A (en) * | 2020-09-29 | 2021-01-22 | 航天科工广信智能技术有限公司 | Traffic incident identification and processing system based on multi-sensor data fusion technology |
| CN112364678A (en) * | 2019-09-30 | 2021-02-12 | 山东省科学院海洋仪器仪表研究所 | Buoy identification and positioning method based on NPU board card and shipborne device thereof |
| CN112379362A (en) * | 2020-10-23 | 2021-02-19 | 连云港杰瑞电子有限公司 | Event self-adaptive acquisition equipment and method based on multi-source data fusion |
| CN112447058A (en) * | 2019-09-03 | 2021-03-05 | 比亚迪股份有限公司 | Parking method, parking device, computer equipment and storage medium |
| CN112863183A (en) * | 2021-01-14 | 2021-05-28 | 深圳尚桥信息技术有限公司 | Traffic flow data fusion method and system |
| CN113109805A (en) * | 2021-03-31 | 2021-07-13 | 中国船舶重工集团公司第七二三研究所 | Fusion processing method based on radio frequency echo information |
| CN113343849A (en) * | 2021-06-07 | 2021-09-03 | 西安恒盛安信智能技术有限公司 | Fusion sensing equipment based on radar and video |
| CN113359125A (en) * | 2020-03-05 | 2021-09-07 | 富士通株式会社 | Data fusion method and device and data processing equipment |
| CN113390429A (en) * | 2020-10-28 | 2021-09-14 | 腾讯科技（深圳）有限公司 | Navigation method and device |
| CN113420805A (en) * | 2021-06-21 | 2021-09-21 | 车路通科技(成都)有限公司 | Dynamic track image fusion method, device, equipment and medium for video and radar |
| CN113705495A (en) * | 2021-09-01 | 2021-11-26 | 南京慧尔视智能科技有限公司 | Large and small vehicle classification method and device based on target identification frame |
| CN114067594A (en) * | 2020-08-05 | 2022-02-18 | 北京万集科技股份有限公司 | Planning method and device of driving path, computer equipment and storage medium |
| CN114202730A (en) * | 2022-01-08 | 2022-03-18 | 深圳安锐科技有限公司 | High-speed train type dynamic recognition control system based on deep learning and multi-sensor data fusion |
| CN114758511A (en) * | 2022-06-14 | 2022-07-15 | 深圳市城市交通规划设计研究中心股份有限公司 | Sports car overspeed detection system, method, electronic equipment and storage medium |
| WO2022179197A1 (en) * | 2021-02-27 | 2022-09-01 | 华为技术有限公司 | Information processing method and related device |
| CN115440056A (en) * | 2022-08-02 | 2022-12-06 | 天津光电聚能专用通信设备有限公司 | Intelligent safety protection system based on millimeter wave radar and vision fusion |
| CN114078331B (en) * | 2020-08-19 | 2023-02-17 | 北京万集科技股份有限公司 | Overspeed detection method, overspeed detection device, visual sensor and storage medium |
| CN116189116A (en) * | 2023-04-24 | 2023-05-30 | 江西方兴科技股份有限公司 | Traffic state sensing method and system |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022093860A1 (en) | 2020-10-26 | 2022-05-05 | Mohammad Amin Arbabian | Centralized tracking system with distributed fixed sensors |
| CN112866645A (en) * | 2021-01-12 | 2021-05-28 | 二连浩特赛乌素机场管理有限公司 | Anti-invasion artificial intelligence radar video monitoring system |
| CN113189583B (en) * | 2021-04-26 | 2022-07-01 | 天津大学 | Time-space synchronization millimeter wave radar and visual information fusion method |
| CN113524198B (en) * | 2021-09-07 | 2021-12-14 | 广东新粤交通投资有限公司 | Road construction initiative intelligence anticollision early warning robot |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103559791A (en) * | 2013-10-31 | 2014-02-05 | 北京联合大学 | Vehicle detection method fusing radar and CCD camera signals |
| CN105711597A (en) * | 2016-02-25 | 2016-06-29 | 江苏大学 | System and method for sensing local driving environment in front |
| US20180218228A1 (en) * | 2017-01-31 | 2018-08-02 | Denso Corporation | Apparatus and method for controlling vehicle |
| CN108648462A (en) * | 2018-05-10 | 2018-10-12 | 芜湖航飞科技股份有限公司 | A kind of vehicle identification method blended based on radar and visual information |
| CN108847026A (en) * | 2018-05-31 | 2018-11-20 | 安徽四创电子股份有限公司 | A method of it is converted based on matrix coordinate and realizes that data investigation is shown |
| CN108922188A (en) * | 2018-07-24 | 2018-11-30 | 河北德冠隆电子科技有限公司 | The four-dimensional outdoor scene traffic of radar tracking positioning perceives early warning monitoring management system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5047515B2 (en) * | 2006-03-20 | 2012-10-10 | 株式会社ゼンリン | Road image creation system, road image creation method, and road image composition apparatus |
| CN106710240B (en) * | 2017-03-02 | 2019-09-27 | 公安部交通管理科学研究所 | The passing vehicle for merging multiple target radar and video information tracks speed-measuring method |
| CN109615870A (en) * | 2018-12-29 | 2019-04-12 | 南京慧尔视智能科技有限公司 | A kind of traffic detection system based on millimetre-wave radar and video |
-
2018
- 2018-12-29 CN CN201811653251.4A patent/CN109615870A/en active Pending
-
2019
- 2019-10-29 WO PCT/CN2019/113964 patent/WO2020134512A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103559791A (en) * | 2013-10-31 | 2014-02-05 | 北京联合大学 | Vehicle detection method fusing radar and CCD camera signals |
| CN105711597A (en) * | 2016-02-25 | 2016-06-29 | 江苏大学 | System and method for sensing local driving environment in front |
| US20180218228A1 (en) * | 2017-01-31 | 2018-08-02 | Denso Corporation | Apparatus and method for controlling vehicle |
| CN108648462A (en) * | 2018-05-10 | 2018-10-12 | 芜湖航飞科技股份有限公司 | A kind of vehicle identification method blended based on radar and visual information |
| CN108847026A (en) * | 2018-05-31 | 2018-11-20 | 安徽四创电子股份有限公司 | A method of it is converted based on matrix coordinate and realizes that data investigation is shown |
| CN108922188A (en) * | 2018-07-24 | 2018-11-30 | 河北德冠隆电子科技有限公司 | The four-dimensional outdoor scene traffic of radar tracking positioning perceives early warning monitoring management system |
Non-Patent Citations (1)
| Title |
|---|
| JIA-PING LIN 等: "A YOLO-based Traffic Counting System", 《2018 CONFERENCE ON TECHNOLOGIES AND APPLICATIONS OF ARTIFICIAL INTELLIGENCE》 * |
Cited By (50)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020134512A1 (en) * | 2018-12-29 | 2020-07-02 | 南京慧尔视智能科技有限公司 | Traffic detection system based on millimeter wave radar and video |
| CN109613537A (en) * | 2019-01-16 | 2019-04-12 | 南京奥杰智能科技有限公司 | A kind of hologram radar |
| CN111830470A (en) * | 2019-04-16 | 2020-10-27 | 杭州海康威视数字技术股份有限公司 | Combined calibration method and device, and target object detection method, system and device |
| CN110288832A (en) * | 2019-07-10 | 2019-09-27 | 南京慧尔视智能科技有限公司 | It is merged based on microwave with the multiple-object information of video and visual presentation method |
| CN110341621A (en) * | 2019-07-10 | 2019-10-18 | 北京百度网讯科技有限公司 | A kind of obstacle detection method and device |
| CN110428626A (en) * | 2019-08-13 | 2019-11-08 | 舟山千眼传感技术有限公司 | A kind of wagon detector and its installation method of microwave and video fusion detection |
| CN110515073A (en) * | 2019-08-19 | 2019-11-29 | 南京慧尔视智能科技有限公司 | The trans-regional networking multiple target tracking recognition methods of more radars and device |
| CN112447058B (en) * | 2019-09-03 | 2022-09-06 | 比亚迪股份有限公司 | Parking method, parking device, computer equipment and storage medium |
| CN112447058A (en) * | 2019-09-03 | 2021-03-05 | 比亚迪股份有限公司 | Parking method, parking device, computer equipment and storage medium |
| CN110738846A (en) * | 2019-09-27 | 2020-01-31 | 同济大学 | Vehicle behavior monitoring system based on radar and video group and implementation method thereof |
| CN110738846B (en) * | 2019-09-27 | 2022-06-17 | 同济大学 | Vehicle behavior monitoring system based on radar and video group and implementation method thereof |
| CN112364678B (en) * | 2019-09-30 | 2023-04-07 | 山东省科学院海洋仪器仪表研究所 | Buoy identification and positioning method based on NPU board card and shipborne device thereof |
| CN112364678A (en) * | 2019-09-30 | 2021-02-12 | 山东省科学院海洋仪器仪表研究所 | Buoy identification and positioning method based on NPU board card and shipborne device thereof |
| CN110865366A (en) * | 2019-10-12 | 2020-03-06 | 深圳市布谷鸟科技有限公司 | Intelligent driving radar and image fusion man-machine interaction method |
| CN110865366B (en) * | 2019-10-12 | 2023-04-18 | 深圳市布谷鸟科技有限公司 | Intelligent driving radar and image fusion man-machine interaction method |
| CN110794405A (en) * | 2019-10-18 | 2020-02-14 | 北京全路通信信号研究设计院集团有限公司 | Target detection method and system based on camera and radar fusion |
| CN110794405B (en) * | 2019-10-18 | 2022-06-10 | 北京全路通信信号研究设计院集团有限公司 | Target detection method and system based on camera and radar fusion |
| CN111127877A (en) * | 2019-11-19 | 2020-05-08 | 华为技术有限公司 | Road condition information monitoring method and device |
| CN110796868A (en) * | 2019-12-02 | 2020-02-14 | 江苏中路工程技术研究院有限公司 | Video and microwave integrated traffic incident monitoring system and method |
| CN111178215B (en) * | 2019-12-23 | 2024-03-08 | 深圳成谷科技有限公司 | Sensor data fusion processing method and device |
| CN111178215A (en) * | 2019-12-23 | 2020-05-19 | 深圳成谷科技有限公司 | Sensor data fusion processing method and device |
| CN113359125A (en) * | 2020-03-05 | 2021-09-07 | 富士通株式会社 | Data fusion method and device and data processing equipment |
| CN111476099A (en) * | 2020-03-09 | 2020-07-31 | 深圳市人工智能与机器人研究院 | Target detection method, target detection device and terminal equipment |
| CN111476099B (en) * | 2020-03-09 | 2024-04-16 | 深圳市人工智能与机器人研究院 | Target detection method, target detection device and terminal equipment |
| CN111427038A (en) * | 2020-03-23 | 2020-07-17 | 厦门大学 | Target identification method based on vision and 77GHz radar in garage environment |
| CN111753901A (en) * | 2020-06-23 | 2020-10-09 | 国汽(北京)智能网联汽车研究院有限公司 | Data fusion method, device and system and computer equipment |
| CN111753901B (en) * | 2020-06-23 | 2023-08-15 | 国汽(北京)智能网联汽车研究院有限公司 | Data fusion method, device, system and computer equipment |
| CN114067594A (en) * | 2020-08-05 | 2022-02-18 | 北京万集科技股份有限公司 | Planning method and device of driving path, computer equipment and storage medium |
| CN114067594B (en) * | 2020-08-05 | 2023-02-17 | 北京万集科技股份有限公司 | Method and device for planning driving path, computer equipment and storage medium |
| CN112150799A (en) * | 2020-08-19 | 2020-12-29 | 上海图丽信息技术有限公司 | Method for collecting road vehicle traffic big data by fusing radar videos |
| CN114078331B (en) * | 2020-08-19 | 2023-02-17 | 北京万集科技股份有限公司 | Overspeed detection method, overspeed detection device, visual sensor and storage medium |
| CN112115810A (en) * | 2020-08-31 | 2020-12-22 | 南京理工大学 | Target identification method, system, computer equipment and storage medium based on information fusion |
| CN112258834A (en) * | 2020-09-29 | 2021-01-22 | 航天科工广信智能技术有限公司 | Traffic incident identification and processing system based on multi-sensor data fusion technology |
| CN112379362A (en) * | 2020-10-23 | 2021-02-19 | 连云港杰瑞电子有限公司 | Event self-adaptive acquisition equipment and method based on multi-source data fusion |
| CN112379362B (en) * | 2020-10-23 | 2024-06-04 | 连云港杰瑞电子有限公司 | Event self-adaptive acquisition equipment and method based on multi-source data fusion |
| CN113390429B (en) * | 2020-10-28 | 2024-01-26 | 腾讯科技（深圳）有限公司 | Navigation method and device |
| CN113390429A (en) * | 2020-10-28 | 2021-09-14 | 腾讯科技（深圳）有限公司 | Navigation method and device |
| CN112863183B (en) * | 2021-01-14 | 2022-04-08 | 深圳尚桥信息技术有限公司 | Traffic flow data fusion method and system |
| CN112863183A (en) * | 2021-01-14 | 2021-05-28 | 深圳尚桥信息技术有限公司 | Traffic flow data fusion method and system |
| WO2022179197A1 (en) * | 2021-02-27 | 2022-09-01 | 华为技术有限公司 | Information processing method and related device |
| CN113109805A (en) * | 2021-03-31 | 2021-07-13 | 中国船舶重工集团公司第七二三研究所 | Fusion processing method based on radio frequency echo information |
| CN113343849A (en) * | 2021-06-07 | 2021-09-03 | 西安恒盛安信智能技术有限公司 | Fusion sensing equipment based on radar and video |
| CN113420805A (en) * | 2021-06-21 | 2021-09-21 | 车路通科技(成都)有限公司 | Dynamic track image fusion method, device, equipment and medium for video and radar |
| CN113705495A (en) * | 2021-09-01 | 2021-11-26 | 南京慧尔视智能科技有限公司 | Large and small vehicle classification method and device based on target identification frame |
| CN113705495B (en) * | 2021-09-01 | 2024-04-16 | 南京慧尔视智能科技有限公司 | Method and device for classifying big and small vehicles based on target identification frame |
| CN114202730A (en) * | 2022-01-08 | 2022-03-18 | 深圳安锐科技有限公司 | High-speed train type dynamic recognition control system based on deep learning and multi-sensor data fusion |
| CN114758511A (en) * | 2022-06-14 | 2022-07-15 | 深圳市城市交通规划设计研究中心股份有限公司 | Sports car overspeed detection system, method, electronic equipment and storage medium |
| CN115440056A (en) * | 2022-08-02 | 2022-12-06 | 天津光电聚能专用通信设备有限公司 | Intelligent safety protection system based on millimeter wave radar and vision fusion |
| CN116189116A (en) * | 2023-04-24 | 2023-05-30 | 江西方兴科技股份有限公司 | Traffic state sensing method and system |
| CN116189116B (en) * | 2023-04-24 | 2024-02-23 | 江西方兴科技股份有限公司 | Traffic state sensing method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020134512A1 (en) | 2020-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109615870A (en) | A kind of traffic detection system based on millimetre-wave radar and video | |
| CN111145545B (en) | Road traffic behavior unmanned aerial vehicle monitoring system and method based on deep learning | |
| CN105711597B (en) | Front locally travels context aware systems and method | |
| CN103559791B (en) | A kind of vehicle checking method merging radar and ccd video camera signal | |
| US9292750B2 (en) | Method and apparatus for detecting traffic monitoring video | |
| WO2018177026A1 (en) | Device and method for determining road edge | |
| CN110285793A (en) | A kind of Vehicular intelligent survey track approach based on Binocular Stereo Vision System | |
| CN102013159A (en) | High-definition video detection data-based region dynamic origin and destination (OD) matrix acquiring method | |
| Nguyen et al. | Compensating background for noise due to camera vibration in uncalibrated-camera-based vehicle speed measurement system | |
| CN104280036A (en) | Traffic information detection and positioning method, device and electronic equipment | |
| CN104751119A (en) | Rapid detecting and tracking method for pedestrians based on information fusion | |
| Zhang et al. | Background filtering and vehicle detection with roadside lidar based on point association | |
| WO2023240805A1 (en) | Connected vehicle overspeed early warning method and system based on filtering correction | |
| CN109427216A (en) | To lock ship information real-time monitoring system | |
| Qu et al. | Improving maritime traffic surveillance in inland waterways using the robust fusion of AIS and visual data | |
| CN111160132B (en) | Method and device for determining lane where obstacle is located, electronic equipment and storage medium | |
| CN110969864A (en) | Vehicle speed detection method, vehicle driving event detection method and electronic equipment | |
| CN110111018B (en) | Method, device, electronic equipment and storage medium for evaluating vehicle sensing capability | |
| CN106960193A (en) | A kind of lane detection apparatus and method | |
| CN114067287A (en) | Foreign matter identification and early warning system based on vehicle side road side data perception fusion | |
| CN105869413A (en) | Method for measuring traffic flow and speed based on camera video | |
| CN113468911B (en) | Vehicle-mounted red light running detection method and device, electronic equipment and storage medium | |
| KR102256205B1 (en) | Device and method for calculation vehicle position in an image, and traffic analysis system using the same | |
| CN113160299A (en) | Vehicle video speed measurement method based on Kalman filtering and computer readable storage medium | |
| Horani et al. | A framework for vision-based lane line detection in adverse weather conditions using vehicle-to-infrastructure (V2I) communication |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190412 |