CN107991671A - A kind of method based on radar data and vision signal fusion recognition risk object - Google Patents
A kind of method based on radar data and vision signal fusion recognition risk object Download PDFInfo
- Publication number
- CN107991671A CN107991671A CN201711178441.0A CN201711178441A CN107991671A CN 107991671 A CN107991671 A CN 107991671A CN 201711178441 A CN201711178441 A CN 201711178441A CN 107991671 A CN107991671 A CN 107991671A
- Authority
- CN
- China
- Prior art keywords
- radar
- data
- barrier
- risk object
- 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
- 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
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
Abstract
Present invention is disclosed a kind of method based on radar data and vision signal fusion recognition risk object, comprise the following steps,（1）The related data of radar equipment and video equipment is received,（2）Radar data is handled, extracts obstacle information,（3）The obstacle information of radar detection and video data are subjected to spatial synchronization,（4）Video data is analyzed and processed, demarcates area-of-interest,（5）The position for being identified as barrier in video data to radar is carried out again identifying that judgement, if the barrier still exists, risk object is identified as, if being not present, is identified as not dangerous target.The present invention will be by video and Radar Data Fusion, allow users to clearly understand road ahead situation, reduce rate of false alarm, reduce the interference to driver, even if run into night, heavy rain, dense fog, the reduction of heavy snow visibility, radar can still indicate road ahead situation, and intuitively can give risk object prompting to driver.
Description
Technical field
The present invention relates to car radar technical field, and in particular to one kind is based on radar data and vision signal fusion recognition
The method of risk object.
Background technology
Rear-ended car accident is one of accident most dangerous in most multiple and vehicle operation in highway communication, wherein
91% rear-end collision is due to caused by driver distraction's (doze off, make a phone call), if 0.5s promptings in advance are driven
The person of sailing takes measures, and 60% rear-end collision can be to avoid, and if rear-end collision avoids rate if 1s in advance reminds driver
Up to 90%.
By taking millimetre-wave radar as an example, millimetre-wave radar is operated in millimeter wave band (millimeter wave) detection
Radar.Usual millimeter wave refers to 30~300GHz frequency domains (wavelength is 1~10mm), has good target detection capabilities.And scheme
Picture sensor operating distance is near, and at a distance there are blind area, the method for realizing anti-collision system using single sensor is subject to information
Amount is few, the restriction of algorithm complexity, it is difficult to meet the highway environment of complexity.Thus, carry out vehicle front row using single-sensor
The problem of risk object detection for sailing region usually faces false drop rate, and omission factor is higher, drives radar and machine vision acquisition
Sail environmental information to be merged, and evade and identify applied to the risk object of automobile, can greatly lifting system to danger
Target detection and the accuracy of judgement.
The content of the invention
The purpose of the present invention is exactly in order to solve the above problem existing in the prior art, so that providing one kind is based on radar number
According to the method with vision signal fusion recognition risk object, it is intended to which system is detected and judged to risk object when lifting running car
Accuracy.
The present invention solution be：A kind of method based on radar data and vision signal fusion recognition risk object,
Comprising the following steps, (1) processor receives the radar data of radar equipment, and radar data is pre-processed, meanwhile, processing
Device receives the video data of video equipment, and video data is pre-processed, and (2) analyze and process radar data, sentence
Whether the target of disconnected radar detection is barrier, if being identified as barrier, extracts obstacle information, (3) detect radar
Obstacle information and video data carry out spatial synchronization, (4) analyze and process video data, demarcate area-of-interest,
(5) if the barrier of radar detection not in the region of interest, is identified as not dangerous target, if in the region of interest,
The position for being identified as barrier in video data to radar is carried out again identifying that judgement, if the barrier still exists, is known
Not Wei risk object, if being not present, be identified as not dangerous target.
Further, a kind of above-mentioned method based on radar data and vision signal fusion recognition risk object, wherein：Institute
State and concretely comprised the following steps in step (3), will be changed between radar fix and image coordinate, coordinate is established according to right hand principle
System, determines spatial relation between coordinate system, by the point (X in world coordinate system by the following formulaW,YW,ZW, 1) and transform to figure
As pixel coordinate (u, v)：
(X in formulaW,YW,ZW,1)TIt is the world coordinate system of point, corresponding video camera homogeneous coordinates are (XC,YC,ZC,
1)T, dx, dy represent the size under physical unit of each pixel on transverse and longitudinal axis respectively, and f is the focal length of video camera, and s ' is represented
Because of the obliquity factor of the mutually mutually non-orthogonal extraction of video camera imaging plane coordinates axle, R represents the orthogonal matrices of one 3 × 3, t
Represent translation vector, I is the unit matrix that element is all 1, and O=(0,0,0) T, R1 strafe flat for barrier central point to radar
The distance R1, α of the opposite radar in face are the deflection angle that barrier central point strafes plane to radar.
Further, a kind of above-mentioned method based on radar data and vision signal fusion recognition risk object, wherein：Institute
It is as follows to state region of interest domain classification method in step (4), is often projected in based on vehicle with shape on pixel planes, according to following public affairs
Formula establish can according to the dynamic area-of-interest of distance change,
In formula, h represents the height in pixel planes of the area-of-interest of division；(xlu, ylu), (xrd, yrd) it is respectively dynamic
The upper left angle point of state area-of-interest and the pixel coordinate of bottom right angle point, (x, y) are the pixel coordinate of vehicle centroid point, and W/H is
Barrier the ratio of width to height, f are focal length of camera, are camera preset parameter.The value of H is fixed tentatively as the height of general motorbus.
Further, a kind of above-mentioned method based on radar data and vision signal fusion recognition risk object, wherein：
The radar equipment is millimetre-wave radar, and the video equipment is ADVS video equipments
Further, a kind of above-mentioned method based on radar data and vision signal fusion recognition risk object, wherein：
Radar data pretreatment comprises the following steps in the step (1), and transverse width threshold value is set come to target according to lane width
Residing track is classified, and a period of time is determined according to target relative velocity and this vehicle speed and the status information in vehicle future
Inside most dangerous target, tracks this target, retains the relative velocity of its resolving, angle and range information, and obtains the generation of target
Boundary's coordinate.
Yet further, a kind of above-mentioned method based on radar data and vision signal fusion recognition risk object, wherein：
Video data pretreatment includes image segmentation, image enhancement, binaryzation and image thinning in the step (1).
Yet further, a kind of above-mentioned method based on radar data and vision signal fusion recognition risk object, its
In：, it is characterised in that：Barrier is identified in the step (5), concretely comprises the following steps and feature extraction is carried out to target, is led to
Cross improved adaptive threshold and determine that method carries out image dividing processing, and then utilize image processing method, priori and D-S
Evidence theory detects whether area-of-interest there are vehicle characteristics or pedestrian's feature.
The prominent substantive distinguishing features of the present invention and significant technique effect are embodied in：Using the present invention in automobile turning,
The distance that control system can detect radar risk object makes calculating and judgement, avoids due to millimetre-wave radar scope too far
And the situation for causing the object in reverse track to be mistaken for risk object occurs, reduce and the mistake of driver is disturbed, favorably
Driven in driver safety.
Brief description of the drawings
Fig. 1 is the Method And Principle block diagram based on radar data and vision signal fusion recognition risk object；
Fig. 2 is the method flow diagram based on radar data and vision signal fusion recognition risk object；
Fig. 3 is radar scanning figure.
Embodiment
Below by way of attached drawing combination embodiment, the present invention is described in further details.
A kind of method based on radar data and vision signal fusion recognition risk object of the present invention, need to install on car body
Radar equipment and video equipment, as shown in Figure 1, comprising the following steps：(1) processor receives the radar data of radar equipment, and
Radar data is pre-processed, meanwhile, processor receives the video data of video equipment, and video data is located in advance
Reason, (2) analyze and process radar data, and whether the target for judging radar detection is barrier, if being identified as barrier,
Obstacle information is extracted, the obstacle information and video data that (3) detect radar carry out spatial synchronization, and (4) are to video counts
According to being analyzed and processed, area-of-interest is demarcated, (5) are if the barrier of radar detection not in the region of interest, identifies
For not dangerous target, if in the region of interest, being known again to the position for being identified as barrier in video data to radar
Do not judge, if the barrier still exists, be identified as risk object, if being not present, be identified as not dangerous target.
By the target information that millimetre-wave radar detects there are null object information in above-mentioned steps (1), invalid targets information,
It must go to except the such echo signal of the overwhelming majority, therefore radar data need to be pre-processed first, specifically included according to country
Regulation lane width sets transverse width threshold value to classify track residing for target, according to target relative velocity and this speed
The status information (steering angle, acceleration) in degree and vehicle future determines target most dangerous in a period of time.Track this target,
Retain the relative velocity of its resolving, angle and range information, obtain the world coordinates of target.In order to reduce the complexity of subsequent algorithm
Degree, improves efficiency, and the pretreatment of image is generally divided into image and splits, image enhancement, binaryzation and the several parts of image thinning, its
Middle image segmentation is by image district and background separation, so as to avoid carrying out feature extraction in the region of no effective information, is accelerated
The speed of subsequent treatment, improves image characteristics extraction and matched precision；The purpose of image enhancement is to improve picture quality, is recovered
The structure of its original, the binaryzation of image be by image from greyscale image transitions be bianry image；Image thinning be clear but
Non-uniform bianry image changes into the point and line chart picture that line width is only a pixel.
As shown in Fig. 2, being provided with millimetre-wave radar and ADAS video equipments on automobile, comprise the following steps that：Above-mentioned steps
(1) comprise the following steps：1st, processor initializes each parameter, and 2, processor collection millimetre-wave radar initial data, and preserve number
Receive ADAS video data streams according to, simultaneous processor, 3, resolve millimetre-wave radar data, obtain millimetre-wave radar detected it is each
The corresponding data of a target, such as target relative velocity, distance and azimuth etc., and ADAS video data streams are handled, wrap
Include image segmentation, image enhancement, binaryzation and image thinning.
Above-mentioned steps comprise the following steps that in (2)：Millimetre-wave radar data are handled, judge that millimetre-wave radar is visited
Whether the target of survey is dangerous, if target will not cause danger, rejects the target, if target is dangerous, is identified as obstacle
Thing, preserves the data after the barrier resolves, and carries out false target processing, obtains the barrier letter that millimetre-wave radar is detected
Breath,
It is in above-mentioned steps (3) that the obstacle information that millimetre-wave radar is detected and ADAS video data streams progress space is same
Step, so that the Obstacle Position that millimetre-wave radar is detected is corresponded in ADAS video datas.Concrete principle is as follows：Due to thunder
Up to belonging to the sensor of different coordinates with video, therefore to realize the Space integration of radar and video, it is necessary to establish two biographies
The transformation model of coordinate system, i.e. conversion between radar fix and image coordinate where sensor.Radar fix system and image coordinate
There is close contact between system, coordinate system is established according to right hand principle, locus between coordinate system is determined by the following formula
Relation, by the point (X in world coordinate systemW,YW,ZW, 1) and to transform to image pixel coordinates (u, v) conversion formula as follows：
(X in formulaW,YW,ZW,1)TIt is the world coordinate system of point, corresponding video camera homogeneous coordinates are (XC,YC,ZC,
1)T, dx, dy represent the size under physical unit of each pixel on transverse and longitudinal axis respectively, and f is the focal length of video camera, and s ' is represented
Because of the obliquity factor of the mutually mutually non-orthogonal extraction of video camera imaging plane coordinates axle, R represents a spin matrix (3 × 3 positive presentate
Bit matrix), t represents translation vector, and I is the unit matrix that element is all 1, O=(0,0,0) T.
As shown in figure 3, the front obstacle information that millimetre-wave radar obtains is the two-dimensional signal under polar coordinates, it is assumed that one
A barrier P, P is transformed into rectangular coordinate system in polar two-dimensional signal, X0O0Z0 planes and generation in radar fix system
The XOZ planes of boundary's coordinate system are parallel, and the distance between two planes are Y0, and can obtain front vehicles central point by radar throws
Shadow strafes the distance and deflection angle of plane to radar, i.e. point P determines P in world coordinates with respect to the distance R1 and angle [alpha] of radar
Coordinate under system, transformational relation are as follows
Above-mentioned steps (4) handle ADAS video datas, mark area-of-interest, its principle is as follows：Due to millimeter
Ripple radar detection can detect all targets to containing, including trees, guardrail, pedestrian, the vehicle of traveling ahead, noise etc..
So the echo signal that must be first returned to millimetre-wave radar pre-processes, cancelling noise.The parameter of each target of radar is thrown
Shadow is handled ADAS video data streams into video image, calibration interesting target region, as shown in figure 3, being obtained by radar
The distance R1 and angle [alpha] of barrier are obtained, passes through the relation between the radar fix system of above-mentioned foundation and pixel coordinate system, you can obtain
Front obstacle in the projection of pixel planes, be often projected in based on vehicle with shape (the ratio of width to height) on pixel planes, foundation can
According to the dynamic area-of-interest of distance change.The ratio of width to height of general vehicle is found by counting in the range of 0.7~2.0, and
General common car, SUV, minibus, commerial vehicle the ratio of width to height are in the range of 0.7~1.3；Definition the ratio of width to height is W/H, according to
Mentioned above principle, the dynamic area-of-interest of division
In formula, h represents the height in pixel planes of the area-of-interest of division；(xlu, ylu), (xrd, yrd) it is respectively dynamic
The upper left angle point of state area-of-interest and the pixel coordinate of bottom right angle point, (x, y) are the pixel coordinate of vehicle centroid point, and W/H is
Barrier the ratio of width to height, f are focal length of camera, are camera preset parameter.The value of H is fixed tentatively as the height of general motorbus.
The Obstacle Position that above-mentioned steps (5) detect millimetre-wave radar in ADAS video datas again identifies that
Judge, after determining area-of-interest, Feature extraction and recognition need to be carried out to target, can be determined by improved adaptive threshold
Method (big law, OTSU methods) carries out image dividing processing, and then utilizes image processing method, priori and D-S evidences reason
By detecting whether that there are vehicle characteristics or pedestrian's feature to area-of-interest.If barrier throws away presence, dangerous mesh is identified as
Mark, performs and acts in next step, takes control car body or reminds driver to take corresponding safeguard measure, if the barrier is no longer deposited
Then it is being identified as not dangerous target.The above method is the prior art, at present existing many algorithms of increasing income, and which is not described herein again.
By above description as can be seen that the present invention will be by video and Radar Data Fusion so that user can be clearly
Understand road ahead situation, reduce rate of false alarm, the interference to driver is reduced, even if running into night, heavy rain, dense fog, heavy snow energy
When degree of opinion reduces, radar can still indicate road ahead situation, and intuitively can give risk object prompting to driver.
Certainly, the above is the representative instance of the present invention, and in addition, the present invention can also have other a variety of specific implementations
Mode, all technical solutions formed using equivalent substitution or equivalent transformation, is all fallen within the scope of protection of present invention.
Claims (7)
- A kind of 1. method based on radar data and vision signal fusion recognition risk object, it is characterised in that：Including following step Suddenly, (1) processor receives the radar data of radar equipment, and radar data is pre-processed, meanwhile, processor receives video The video data of equipment, and video data is pre-processed, (2) analyze and process radar data, judge that radar is visited Whether the target of survey is barrier, if being identified as barrier, extracts obstacle information, the barrier that (3) detect radar is believed Breath and video data carry out spatial synchronization, and (4) analyze and process video data, demarcate area-of-interest, (5) are if radar The barrier of detection in the region of interest, is not then identified as not dangerous target, if in the region of interest, in video data The position that barrier is identified as to radar carries out again identifying that judgement, if the barrier still exists, is identified as risk object, If being not present, not dangerous target is identified as.
- 2. a kind of method based on radar data and vision signal fusion recognition risk object according to claim 1, its It is characterized in that：Concretely comprise the following steps, will be changed between radar fix and image coordinate in the step (3), it is former according to the right hand Coordinate system is then established, spatial relation between coordinate system is determined by the following formula, by the point (X in world coordinate systemW,YW,ZW, 1) image pixel coordinates (u, v) are transformed to：(X in formulaW,YW,ZW,1)TIt is the world coordinate system of point, corresponding video camera homogeneous coordinates are (XC,YC,ZC,1)T, Dx, dy represent the size under physical unit of each pixel on transverse and longitudinal axis respectively, and f is the focal length of video camera, and s ' is represented because taking the photograph The obliquity factor of the mutually mutually non-orthogonal extraction of camera imaging plane reference axis, R represent the orthogonal matrices of one 3 × 3, and t is represented Translation vector, I are the unit matrixs that element is all 1, and O=(0,0,0) T, R1 strafe plane for barrier central point to radar Distance R1, α with respect to radar are the deflection angle that barrier central point strafes plane to radar.
- 3. a kind of method based on radar data and vision signal fusion recognition risk object according to claim 1, its It is characterized in that：Region of interest domain classification method is as follows in the step (4), and often pixel planes are projected in shape based on vehicle On, according to the following formula establish can according to the dynamic area-of-interest of distance change,In formula, h represents the height in pixel planes of the area-of-interest of division；(xlu, ylu), (xrd, yrd) it is respectively that dynamic is felt The upper left angle point in interest region and the pixel coordinate of bottom right angle point, (x, y) are the pixel coordinate of vehicle centroid point, and W/H is obstacle Thing the ratio of width to height, f are focal length of camera, are camera preset parameter.The value of H is fixed tentatively as the height of general motorbus.
- 4. a kind of method based on radar data and vision signal fusion recognition risk object according to claim 1, its It is characterized in that：The radar equipment is millimetre-wave radar, and the video equipment is ADVS video equipments.
- 5. a kind of method based on radar data and vision signal fusion recognition risk object according to claim 1, its It is characterized in that：Radar data pretreatment comprises the following steps in the step (1), and transverse width threshold value is set according to lane width To classify to track residing for target, determined according to target relative velocity and this vehicle speed and the status information in vehicle future Most dangerous target in a period of time, tracks this target, retains the relative velocity of its resolving, angle and range information, and obtains The world coordinates of target.
- 6. a kind of method based on radar data and vision signal fusion recognition risk object according to claim 1, its It is characterized in that：Video data pretreatment includes image segmentation, image enhancement, binaryzation and image thinning in the step (1).
- 7. a kind of method based on radar data and vision signal fusion recognition risk object according to claim 1, its It is characterized in that：Barrier is identified in the step (5), concretely comprises the following steps and feature extraction is carried out to target, pass through improvement Adaptive threshold determine method carry out image dividing processing, and then using image processing method, priori and D-S evidences reason By detecting whether that there are vehicle characteristics or pedestrian's feature to area-of-interest.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711178441.0A CN107991671A (en) | 2017-11-23 | 2017-11-23 | A kind of method based on radar data and vision signal fusion recognition risk object |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711178441.0A CN107991671A (en) | 2017-11-23 | 2017-11-23 | A kind of method based on radar data and vision signal fusion recognition risk object |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107991671A true CN107991671A (en) | 2018-05-04 |
Family
ID=62032731
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711178441.0A Pending CN107991671A (en) | 2017-11-23 | 2017-11-23 | A kind of method based on radar data and vision signal fusion recognition risk object |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107991671A (en) |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108639048A (en) * | 2018-05-15 | 2018-10-12 | 智车优行科技（北京）有限公司 | Automobile lane change householder method, system and automobile |
| CN108749708A (en) * | 2018-05-11 | 2018-11-06 | 长安大学 | The device and method of vehicle fog lamp is automatically turned under a kind of low visibility |
| 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 |
| CN108986510A (en) * | 2018-07-31 | 2018-12-11 | 同济大学 | A kind of local dynamic map of intelligence towards crossing realizes system and implementation method |
| CN109102702A (en) * | 2018-08-24 | 2018-12-28 | 南京理工大学 | Vehicle speed measuring method based on video encoder server and Radar Signal Fusion |
| CN109143241A (en) * | 2018-07-26 | 2019-01-04 | 清华大学苏州汽车研究院（吴江） | The fusion method and system of radar data and image data |
| CN109343050A (en) * | 2018-11-05 | 2019-02-15 | 浙江大华技术股份有限公司 | A kind of radar video monitoring method and device |
| CN109709541A (en) * | 2018-12-26 | 2019-05-03 | 杭州奥腾电子股份有限公司 | A kind of vehicle environment perception emerging system target erroneous detection processing method |
| CN109814113A (en) * | 2019-01-15 | 2019-05-28 | 北京百度网讯科技有限公司 | A kind of ultrasonic radar detection of obstacles result processing method and system |
| CN109816702A (en) * | 2019-01-18 | 2019-05-28 | 苏州矽典微智能科技有限公司 | A kind of multiple target tracking device and method |
| CN109948523A (en) * | 2019-03-18 | 2019-06-28 | 中国汽车工程研究院股份有限公司 | A kind of object recognition methods and its application based on video Yu millimetre-wave radar data fusion |
| CN110008891A (en) * | 2019-03-29 | 2019-07-12 | 厦门金龙旅行车有限公司 | A kind of pedestrian detection localization method, device, cart-mounted computing device and storage medium |
| CN110361741A (en) * | 2019-07-16 | 2019-10-22 | 扬州瑞控汽车电子有限公司 | A kind of the frontal collisions method for early warning and its system of view-based access control model and radar fusion |
| CN110531770A (en) * | 2019-08-30 | 2019-12-03 | 的卢技术有限公司 | One kind being based on improved RRT paths planning method and system |
| CN110660186A (en) * | 2018-06-29 | 2020-01-07 | 杭州海康威视数字技术股份有限公司 | Method and device for identifying target object in video image based on radar signal |
| CN110658518A (en) * | 2018-06-29 | 2020-01-07 | 杭州海康威视数字技术股份有限公司 | Target intrusion detection method and device |
| CN110687929A (en) * | 2019-10-10 | 2020-01-14 | 辽宁科技大学 | Aircraft three-dimensional space target searching system based on monocular vision and motor imagery |
| 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 |
| CN111090096A (en) * | 2020-03-19 | 2020-05-01 | 南京兆岳智能科技有限公司 | Night vehicle detection method, device and system |
| WO2020103533A1 (en) * | 2018-11-20 | 2020-05-28 | 中车株洲电力机车有限公司 | Track and road obstacle detecting method |
| CN111986232A (en) * | 2020-08-13 | 2020-11-24 | 上海高仙自动化科技发展有限公司 | Target object detection method, target object detection device, robot and storage medium |
| CN112116031A (en) * | 2020-10-29 | 2020-12-22 | 重庆长安汽车股份有限公司 | Target fusion method and system based on road side equipment, vehicle and storage medium |
| WO2020253764A1 (en) * | 2019-06-18 | 2020-12-24 | 华为技术有限公司 | Method and apparatus for determining running region information |
| CN112200087A (en) * | 2020-10-10 | 2021-01-08 | 北京理工大学 | Obstacle image automatic calibration device for vehicle collision early warning |
| CN112368598A (en) * | 2018-07-02 | 2021-02-12 | 索尼半导体解决方案公司 | Information processing apparatus, information processing method, computer program, and mobile apparatus |
| CN112590782A (en) * | 2020-12-28 | 2021-04-02 | 东风越野车有限公司 | All-weather collision early warning method and device based on multiple sensors |
| CN112784678A (en) * | 2020-12-14 | 2021-05-11 | 深兰人工智能(深圳)有限公司 | Danger prompting method and device |
| CN112835030A (en) * | 2020-12-30 | 2021-05-25 | 深圳承泰科技有限公司 | Data fusion method and device for obstacle target and intelligent automobile |
| CN113156421A (en) * | 2021-04-07 | 2021-07-23 | 南京邮电大学 | Obstacle detection method based on information fusion of millimeter wave radar and camera |
| CN113255708A (en) * | 2020-02-10 | 2021-08-13 | 富士通株式会社 | Data fusion method and device and data processing equipment |
| CN113256983A (en) * | 2021-06-21 | 2021-08-13 | 陕西易合交通科技有限公司 | Road anti-intrusion early warning method and system based on millimeter wave radar |
| CN113568522A (en) * | 2021-06-21 | 2021-10-29 | 海南雷影信息技术有限公司 | Radar touch point fusion filtering method and system, electronic equipment and storage medium |
| WO2021259344A1 (en) * | 2020-06-24 | 2021-12-30 | 中国第一汽车股份有限公司 | Vehicle detection method and device, vehicle, and storage medium |
| CN114137511A (en) * | 2021-11-24 | 2022-03-04 | 中国民用航空总局第二研究所 | Multi-source heterogeneous sensor-based airport runway foreign matter fusion detection method |
| CN115083035A (en) * | 2021-03-15 | 2022-09-20 | 北汽福田汽车股份有限公司 | Data acquisition method and device, medium, equipment and vehicle |
| CN115220005A (en) * | 2022-07-20 | 2022-10-21 | 中国科学院长春光学精密机械与物理研究所 | Automatic target identification method of photoelectric tracking equipment based on multi-source information fusion |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101025824A (en) * | 2007-03-30 | 2007-08-29 | 东南大学 | Calibrating method based on fixed parameters and variable parameters for three-dimensional scanning system |
| CN101783018A (en) * | 2010-02-04 | 2010-07-21 | 上海交通大学 | Method for calibrating camera by utilizing concentric circles |
| US20120330528A1 (en) * | 2011-06-22 | 2012-12-27 | Robert Bosch Gmbh | Driver assistance systems using radar and video |
| CN102930554A (en) * | 2011-08-11 | 2013-02-13 | 天津市亚安科技股份有限公司 | Method and system for accurately capturing target in monitored scene |
| CN104637059A (en) * | 2015-02-09 | 2015-05-20 | 吉林大学 | Night preceding vehicle detection method based on millimeter-wave radar and machine vision |
| CN105809697A (en) * | 2016-03-14 | 2016-07-27 | 四川巨源科技有限公司 | One-dimensional camera calibration device only with two mark points and calibration method thereof |
| CN106447680A (en) * | 2016-11-23 | 2017-02-22 | 湖南华诺星空电子技术有限公司 | Method for radar and vision fused target detecting and tracking in dynamic background environment |
| CN106908783A (en) * | 2017-02-23 | 2017-06-30 | 苏州大学 | Obstacle detection method based on multi-sensor information fusion |
-
2017
- 2017-11-23 CN CN201711178441.0A patent/CN107991671A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101025824A (en) * | 2007-03-30 | 2007-08-29 | 东南大学 | Calibrating method based on fixed parameters and variable parameters for three-dimensional scanning system |
| CN101783018A (en) * | 2010-02-04 | 2010-07-21 | 上海交通大学 | Method for calibrating camera by utilizing concentric circles |
| US20120330528A1 (en) * | 2011-06-22 | 2012-12-27 | Robert Bosch Gmbh | Driver assistance systems using radar and video |
| CN102930554A (en) * | 2011-08-11 | 2013-02-13 | 天津市亚安科技股份有限公司 | Method and system for accurately capturing target in monitored scene |
| CN104637059A (en) * | 2015-02-09 | 2015-05-20 | 吉林大学 | Night preceding vehicle detection method based on millimeter-wave radar and machine vision |
| CN105809697A (en) * | 2016-03-14 | 2016-07-27 | 四川巨源科技有限公司 | One-dimensional camera calibration device only with two mark points and calibration method thereof |
| CN106447680A (en) * | 2016-11-23 | 2017-02-22 | 湖南华诺星空电子技术有限公司 | Method for radar and vision fused target detecting and tracking in dynamic background environment |
| CN106908783A (en) * | 2017-02-23 | 2017-06-30 | 苏州大学 | Obstacle detection method based on multi-sensor information fusion |
Non-Patent Citations (1)
| Title |
|---|
| 江铁成: "《电视摄像技艺》", 31 December 2015, 合肥工业大学出版社 * |
Cited By (48)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108749708A (en) * | 2018-05-11 | 2018-11-06 | 长安大学 | The device and method of vehicle fog lamp is automatically turned under a kind of low visibility |
| CN108749708B (en) * | 2018-05-11 | 2021-10-22 | 长安大学 | Device and method for automatically turning on fog lamp of vehicle under low visibility |
| CN108639048A (en) * | 2018-05-15 | 2018-10-12 | 智车优行科技（北京）有限公司 | Automobile lane change householder method, system and automobile |
| 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 |
| CN110660186A (en) * | 2018-06-29 | 2020-01-07 | 杭州海康威视数字技术股份有限公司 | Method and device for identifying target object in video image based on radar signal |
| CN110660186B (en) * | 2018-06-29 | 2022-03-01 | 杭州海康威视数字技术股份有限公司 | Method and device for identifying target object in video image based on radar signal |
| CN110658518A (en) * | 2018-06-29 | 2020-01-07 | 杭州海康威视数字技术股份有限公司 | Target intrusion detection method and device |
| CN112368598A (en) * | 2018-07-02 | 2021-02-12 | 索尼半导体解决方案公司 | Information processing apparatus, information processing method, computer program, and mobile apparatus |
| US11959999B2 (en) | 2018-07-02 | 2024-04-16 | Sony Semiconductor Solutions Corporation | Information processing device, information processing method, computer program, and mobile device |
| CN109143241A (en) * | 2018-07-26 | 2019-01-04 | 清华大学苏州汽车研究院（吴江） | The fusion method and system of radar data and image data |
| CN108986510A (en) * | 2018-07-31 | 2018-12-11 | 同济大学 | A kind of local dynamic map of intelligence towards crossing realizes system and implementation method |
| CN109102702A (en) * | 2018-08-24 | 2018-12-28 | 南京理工大学 | Vehicle speed measuring method based on video encoder server and Radar Signal Fusion |
| CN109343050A (en) * | 2018-11-05 | 2019-02-15 | 浙江大华技术股份有限公司 | A kind of radar video monitoring method and device |
| WO2020103533A1 (en) * | 2018-11-20 | 2020-05-28 | 中车株洲电力机车有限公司 | Track and road obstacle detecting method |
| CN109709541A (en) * | 2018-12-26 | 2019-05-03 | 杭州奥腾电子股份有限公司 | A kind of vehicle environment perception emerging system target erroneous detection processing method |
| CN109814113B (en) * | 2019-01-15 | 2022-02-25 | 北京百度网讯科技有限公司 | Ultrasonic radar obstacle detection result processing method and system |
| CN109814113A (en) * | 2019-01-15 | 2019-05-28 | 北京百度网讯科技有限公司 | A kind of ultrasonic radar detection of obstacles result processing method and system |
| CN109816702A (en) * | 2019-01-18 | 2019-05-28 | 苏州矽典微智能科技有限公司 | A kind of multiple target tracking device and method |
| CN109948523A (en) * | 2019-03-18 | 2019-06-28 | 中国汽车工程研究院股份有限公司 | A kind of object recognition methods and its application based on video Yu millimetre-wave radar data fusion |
| CN110008891A (en) * | 2019-03-29 | 2019-07-12 | 厦门金龙旅行车有限公司 | A kind of pedestrian detection localization method, device, cart-mounted computing device and storage medium |
| US11698459B2 (en) | 2019-06-18 | 2023-07-11 | Huawei Technologies Co., Ltd. | Method and apparatus for determining drivable region information |
| WO2020253764A1 (en) * | 2019-06-18 | 2020-12-24 | 华为技术有限公司 | Method and apparatus for determining running region information |
| US20220108552A1 (en) | 2019-06-18 | 2022-04-07 | Huawei Technologies Co., Ltd. | Method and Apparatus for Determining Drivable Region Information |
| CN110361741A (en) * | 2019-07-16 | 2019-10-22 | 扬州瑞控汽车电子有限公司 | A kind of the frontal collisions method for early warning and its system of view-based access control model and radar fusion |
| CN110531770A (en) * | 2019-08-30 | 2019-12-03 | 的卢技术有限公司 | One kind being based on improved RRT paths planning method and system |
| CN110687929B (en) * | 2019-10-10 | 2022-08-12 | 辽宁科技大学 | Aircraft three-dimensional space target searching system based on monocular vision and motor imagery |
| CN110687929A (en) * | 2019-10-10 | 2020-01-14 | 辽宁科技大学 | Aircraft three-dimensional space target searching system based on monocular vision and motor imagery |
| 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 |
| 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 |
| CN113255708A (en) * | 2020-02-10 | 2021-08-13 | 富士通株式会社 | Data fusion method and device and data processing equipment |
| CN111090096A (en) * | 2020-03-19 | 2020-05-01 | 南京兆岳智能科技有限公司 | Night vehicle detection method, device and system |
| WO2021259344A1 (en) * | 2020-06-24 | 2021-12-30 | 中国第一汽车股份有限公司 | Vehicle detection method and device, vehicle, and storage medium |
| CN111986232A (en) * | 2020-08-13 | 2020-11-24 | 上海高仙自动化科技发展有限公司 | Target object detection method, target object detection device, robot and storage medium |
| CN111986232B (en) * | 2020-08-13 | 2021-09-14 | 上海高仙自动化科技发展有限公司 | Target object detection method, target object detection device, robot and storage medium |
| CN112200087A (en) * | 2020-10-10 | 2021-01-08 | 北京理工大学 | Obstacle image automatic calibration device for vehicle collision early warning |
| CN112116031B (en) * | 2020-10-29 | 2024-02-09 | 重庆长安汽车股份有限公司 | Target fusion method, system, vehicle and storage medium based on road side equipment |
| CN112116031A (en) * | 2020-10-29 | 2020-12-22 | 重庆长安汽车股份有限公司 | Target fusion method and system based on road side equipment, vehicle and storage medium |
| CN112784678A (en) * | 2020-12-14 | 2021-05-11 | 深兰人工智能(深圳)有限公司 | Danger prompting method and device |
| CN112590782A (en) * | 2020-12-28 | 2021-04-02 | 东风越野车有限公司 | All-weather collision early warning method and device based on multiple sensors |
| CN112835030A (en) * | 2020-12-30 | 2021-05-25 | 深圳承泰科技有限公司 | Data fusion method and device for obstacle target and intelligent automobile |
| CN115083035A (en) * | 2021-03-15 | 2022-09-20 | 北汽福田汽车股份有限公司 | Data acquisition method and device, medium, equipment and vehicle |
| CN113156421A (en) * | 2021-04-07 | 2021-07-23 | 南京邮电大学 | Obstacle detection method based on information fusion of millimeter wave radar and camera |
| CN113568522A (en) * | 2021-06-21 | 2021-10-29 | 海南雷影信息技术有限公司 | Radar touch point fusion filtering method and system, electronic equipment and storage medium |
| CN113568522B (en) * | 2021-06-21 | 2024-03-19 | 海南雷影信息技术有限公司 | Radar touch point fusion filtering method, system, electronic equipment and storage medium |
| CN113256983A (en) * | 2021-06-21 | 2021-08-13 | 陕西易合交通科技有限公司 | Road anti-intrusion early warning method and system based on millimeter wave radar |
| CN114137511A (en) * | 2021-11-24 | 2022-03-04 | 中国民用航空总局第二研究所 | Multi-source heterogeneous sensor-based airport runway foreign matter fusion detection method |
| CN114137511B (en) * | 2021-11-24 | 2023-11-14 | 中国民用航空总局第二研究所 | Airport runway foreign matter fusion detection method based on multi-source heterogeneous sensor |
| CN115220005A (en) * | 2022-07-20 | 2022-10-21 | 中国科学院长春光学精密机械与物理研究所 | Automatic target identification method of photoelectric tracking equipment based on multi-source information fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107991671A (en) | A kind of method based on radar data and vision signal fusion recognition risk object | |
| JP5297078B2 (en) | Method for detecting moving object in blind spot of vehicle, and blind spot detection device | |
| JP5690688B2 (en) | Outside world recognition method, apparatus, and vehicle system | |
| CN104573646B (en) | Chinese herbaceous peony pedestrian detection method and system based on laser radar and binocular camera | |
| JP3463858B2 (en) | Perimeter monitoring device and method | |
| CN111369541B (en) | Vehicle detection method for intelligent automobile under severe weather condition | |
| CN105460009B (en) | Automobile control method and device | |
| US20120300078A1 (en) | Environment recognizing device for vehicle | |
| CN108960183A (en) | A kind of bend target identification system and method based on Multi-sensor Fusion | |
| US20150298621A1 (en) | Object detection apparatus and driving assistance apparatus | |
| CN107031623A (en) | A kind of road method for early warning based on vehicle-mounted blind area camera | |
| JP2012069121A (en) | Protection system for the weak who use road | |
| KR101663574B1 (en) | Method and system for detection of sudden pedestrian crossing for safe driving during night time | |
| CN110682907B (en) | Automobile rear-end collision prevention control system and method | |
| CN109541601A (en) | Differentiating obstacle and its detection method based on millimeter wave | |
| CN114415171A (en) | Automobile travelable area detection method based on 4D millimeter wave radar | |
| Tanaka et al. | Vehicle detection based on perspective transformation using rear-view camera | |
| KR101406316B1 (en) | Apparatus and method for detecting lane | |
| Yang et al. | On-road collision warning based on multiple FOE segmentation using a dashboard camera | |
| JP3562278B2 (en) | Environment recognition device | |
| JP5593217B2 (en) | Vehicle external recognition device and vehicle system using the same | |
| KR20140104516A (en) | Lane detection method and apparatus | |
| CN110232300A (en) | Lane vehicle lane-changing intension recognizing method and system by a kind of | |
| CN115937827B (en) | Monitoring video processing method for automobile emergency active risk avoidance | |
| Jeong et al. | Autonomous detector using saliency map model and modified mean-shift tracking for a blind spot monitor in a car |
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: 20180504 |