CN102542843A - Early warning method for preventing vehicle collision and device - Google Patents
Early warning method for preventing vehicle collision and device Download PDFInfo
- Publication number
- CN102542843A CN102542843A CN2010105872145A CN201010587214A CN102542843A CN 102542843 A CN102542843 A CN 102542843A CN 2010105872145 A CN2010105872145 A CN 2010105872145A CN 201010587214 A CN201010587214 A CN 201010587214A CN 102542843 A CN102542843 A CN 102542843A
- Authority
- CN
- China
- Prior art keywords
- characteristic information
- information
- characteristic
- target
- barrier target
- 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
Images
Landscapes
- Traffic Control Systems (AREA)
- Image Processing (AREA)
Abstract
The invention provides an early warning method for preventing vehicle collision and a device. The method includes steps of acquiring video image information of the front of a vehicle, and obtaining first characteristic information of an obstacle target of the front of the vehicle according to the video image information; acquiring radar measurement information of the front of the vehicle, and determining second characteristic information of the obstacle target of the front of the vehicle according to the radar measurement information; fusing characteristics of the first characteristic information and the second characteristic information so as to determine final characteristic information of the obstacle target of the front of the vehicle; estimating collision risks to the obstacle target according to the final characteristic information, and realizing early warning for a driver according to a collision risk estimation result. The obstacle target of the front of the vehicle and state information of the obstacle target are identified by means of fusing information, which are acquired by double cameras and a radar device, of the front of the vehicle, target identification precision is improved, and a collision preventive alarm function of the vehicle can be well realized.
Description
Technical field
The present invention relates to the automobile active safety technical field, particularly a kind of method for early warning and device that prevents vehicle collision.
Background technology
Along with the develop rapidly of auto industry and highway, the automobile car accident is serious day by day, so the automobile collision preventing warning becomes extremely important.
Anti-collision system for automobile is the active automobile safety system of a kind of intellectuality, it can remedy the people perception, judge even control the deficiency of aspect.The greatest problem that anti-collision system for automobile need solve is exactly The Recognition of Multiple Targets problem and false-alarm problem.Because the working environment of anti-collision system for automobile is the complex environment of dynamic, multiobject, a wide sensing range, how multiple goal is differentiated and is accurately measured their distance, relative velocity and position angle, will face very big challenge.
The method in a kind of analysis comparatively commonly used at present and the judgement vehicle front visual field is to use the video image of two camera collection vehicle fronts, according to the parallax of two cameras; Confirm a plurality of barrier targets of vehicle front, for example, traffic sign, pedestrian, vehicle and other barrier; And definite barrier clarification of objective information; For example, the distance of the size of target and target range vehicle etc., and in view of the above the driver is reported to the police.The problem that this method exists is, can't realize the analysis to the vehicle front visual field accurately, and the collection of video image receives the influence of weather conditions easily, causes producing bigger error, can't carry out early warning to the driver exactly.
Summary of the invention
The object of the invention is intended to solve at least one of above-mentioned technological deficiency, particularly proposes a kind ofly can judge method for early warning and device to prevent vehicle collision accurately to the multiple goal of vehicle front.
For achieving the above object; One aspect of the present invention proposes a kind of method for early warning that prevents vehicle collision; It is characterized in that, may further comprise the steps: the video image information in collection vehicle the place ahead, and obtain first characteristic information of the barrier target of said vehicle front according to said video image information; Obtain the radargrammetry information of said vehicle front, and confirm second characteristic information of the barrier target of said vehicle front according to said radargrammetry information; Said first characteristic information and said second characteristic information are carried out the final characteristic information of Feature Fusion with the barrier target of definite said vehicle front; And according to said final characteristic information said barrier target is carried out risk of collision and estimate, and the driver is carried out early warning according to said risk of collision results estimated.
The present invention also proposes a kind of prior-warning device that prevents vehicle collision on the other hand, comprising: image capture module is used for the video image information in collection vehicle the place ahead; Image processing module is used for obtaining according to said video image information first characteristic information of the barrier target of said vehicle front; The information acquisition module is used to obtain the radargrammetry information of vehicle front; The Radar Signal Processing module is used for confirming according to said radargrammetry information second characteristic information of the barrier target of said vehicle front; The information fusion module; Be used to receive first characteristic information of said image processing module output and second characteristic information of said Radar Signal Processing module output, and said first characteristic information and said second characteristic information are merged the final characteristic information with the barrier target of confirming said vehicle front; And the early warning module, be used for said barrier target being carried out risk of collision and estimate, and the driver is carried out early warning according to said risk of collision results estimated according to said final characteristic information.
The information of the present invention through vehicle front that dual camera and radar are collected merges the barrier target of discerning vehicle front and the status information of barrier target, has improved the precision of Target Recognition, can realize the collision-proof alarm of automobile better.
Aspect that the present invention adds and advantage part in the following description provide, and part will become obviously from the following description, or recognize through practice of the present invention.
Description of drawings
Above-mentioned and/or additional aspect of the present invention and advantage are from obviously with easily understanding becoming the description of embodiment below in conjunction with accompanying drawing, wherein:
Fig. 1 is the process flow diagram of the method for early warning that prevents vehicle collision of the embodiment of the invention;
Fig. 2 is the synoptic diagram of the structure that is used for Image Information Processing of a specific embodiment of the present invention;
Fig. 3 carries out the process flow diagram of Image Information Processing for the structure of using Fig. 2; And
Fig. 4 is the structural representation of the prior-warning device that prevents vehicle collision of the embodiment of the invention.
Embodiment
Describe embodiments of the invention below in detail, the example of said embodiment is shown in the drawings, and wherein identical from start to finish or similar label is represented identical or similar elements or the element with identical or similar functions.Be exemplary through the embodiment that is described with reference to the drawings below, only be used to explain the present invention, and can not be interpreted as limitation of the present invention.
Be illustrated in figure 1 as the process flow diagram of the method for early warning that prevents vehicle collision of the embodiment of the invention, this method may further comprise the steps:
Step S101, the video image information in collection vehicle the place ahead, and obtain first characteristic information of the barrier target of vehicle front according to video image information.
In one embodiment of the invention, through the video image of two camera collection vehicle fronts, according to the parallax of two cameras; Tell barrier target (hereinafter, will be called video object), and obtain first characteristic information of video object according to the barrier target that video image information is confirmed; Wherein, First characteristic information comprises: the size of video object, shape, video object should be understood that with respect to the distance of vehicle and speed etc. this is merely schematic example; Be not limited to the present invention, also can confirm other characteristic informations according to video image information.
Particularly, at first, right to the image that the image information of two camera collections is carried out after image matees with acquisition coupling; Then, the right stereoscopic parallax of computed image to be setting up stereoscopic parallax figure, and calculates first characteristic information of barrier target according to stereoscopic parallax figure.Detailed matching process and computation process are identical with existing image processing method based on binocular vision, here for simplicity, are not described in detail.
It should be noted that; In one embodiment of the invention, in order to let the driver can understand the situation in the vehicle front visual field more intuitively, passing through two camera collections behind the video image of vehicle front; To one of them camera collection to image information duplicate; In the image information after duplicating a road directly sent to display interface shows, another camera collection of another Lu Zeyu to image information deposit in the buffer memory, so together; After determining first characteristic information of video object and video object, also can be on display interface video object be drawn a circle to approve out and indicates their distances with respect to vehicle.In addition, in another embodiment of the present invention, video image information is carried out two-level cache, thereby the real-time of the system of assurance makes the video image information collection of front end and the video information process of rear end relatively independently to carry out.
Fig. 2 is the structural representation that is used for Image Information Processing of a specific embodiment of the present invention, and Fig. 3 carries out the process flow diagram of Image Information Processing for the structure of using Fig. 2.As shown in Figure 2; The digital image information that sends from binocular CMOS camera carries out pre-service in FPGA (Field-Programmable Gate Array, field programmable gate array), except the copying image with one of them camera collection becomes two-way; One the tunnel exports LCD to shows; One the tunnel deposits outside the frame buffer with the digital image information of another camera collection, and FPGA also carries out the processing of binocular image redundant information, through the search of lane boundary line; Road surface and complex redundancy background are separated, keep the digital image information in road surface and the above scope thereof.Pretreated image information is saved in the frame buffer, and wait DSP (Digital Signal Processor, digital signal processor) reading of data is handled.FPGA can also be used for the sequential of control of video collection and processing module; As shown in Figures 2 and 3, FPGA counts row, the field sync signal of CMOS camera, after confirming to have gathered the complete picture signal of a frame; Image after FPGA will handle is stored in the frame buffer 1; And the DSP processing of from frame buffer 2, fetching data is transferred to the data of frame buffer 1 in the frame buffer 2 again after handling, and so just makes the collection of view data and the processing of view data all carry out simultaneously.
DSP reads the digital image information from two CMOS cameras that has separated redundant background from frame buffer, calculate the barrier clarification of objective information of vehicle front through following method.
At first; Can adopt based on the Region Matching Algorithm of gray scale difference the binocular image is carried out three-dimensional coupling: the point to be matched with reference map (image of a camera collection) is that a window is created at the center; Certain a bit is the onesize moving window of center establishment on the corresponding outer polar curve in align (image of another camera collection), characterizes center pixel with the grey value profile of neighbor in the window.Moving window outside on the polar curve unit picture element move, calculate the window match measure at each displacement point place, the minimum value of estimating through search matched obtains optimal match point, wherein,
Wherein, C
SADBe match measure, d is the moving window displacement, w
pBe match window, I
l(x, y) and I
r(x+d y) is respectively the gray-scale value of match window center pixel in the image of two camera collections.
After obtaining the three-dimensional match point of two images, just can the right stereoscopic parallax of computed image, and set up stereoscopic parallax figure with this.In disparity map, can utilize 4-a little to be communicated with the target that character is sought connection, thus the separation barrier thing, and whether have barrier in definite image-region.Calculate the gray scale difference of 4 adjoint point r in each some p and its 4-neighborhood, if the gray scale difference that obtains, explains then that a some p is communicated with this adjoint point less than certain pre-set threshold.Calculating successively goes down just can obtain connected region, is the place of barrier.According to binocular camera shooting head parallel optical axis modular concept, the computing method of the relative position of barrier and vehicle:
In the formula, f is the focal length of cam lens, and b is two distances between the cam lens center, x
1-x
2Be the parallax of image to coordinate, z is the required distance of finding the solution.
After detecting the position of barrier, can also follow the tracks of, adopt kalman filtering theory to estimate radial distance, speed, the acceleration of barrier to moving target.Can also on the LCD images displayed, draw a circle to approve, and demarcate the range information of each barrier with respect to vehicle to barrier.
Step S102 obtains the radargrammetry information of vehicle front, and according to second characteristic information of the barrier target of radargrammetry information acquisition vehicle front.
Use the linear frequency modulation continuous wave radar; Use different frequency modulation matching process that radargrammetry information is carried out matching treatment; A plurality of barrier targets of telling vehicle front are (in order to distinguish with video object; To be called radar target according to the barrier target that radargrammetry information is confirmed hereinafter) and second characteristic information of radar target, wherein, second characteristic information comprises distance, speed and the position angle etc. of barrier target.Concrete disposal route is identical with the disposal route of prior art, here for simplicity, is not described in detail.
Should be understood that identical characteristic item in first characteristic information that can comprise in second characteristic information of radar target with video object, also can comprise with second characteristic information in the different character item.For example, comprise the size of barrier target in first characteristic information of video object, do not comprise the speed of barrier target, and do not comprise the size of barrier target in second characteristic information of radar target, comprise the speed of barrier target.Therefore, gather two kinds of information collecting methods through camera collection and radar, can obtain the more comprehensively information of barrier target, making can be more accurate about the judgement of barrier target.In addition; Because do not receive the influence of weather conditions during the radar Information Monitoring, and because the advantage of radar self, therefore; Utilize radar information can confirm the barrier target and the barrier clarification of objective information of vehicle front more accurately; And, accurately providing on the remote complaint message, radar also has bigger advantage.
Step S103 carries out the final characteristic information of Feature Fusion with the barrier target of definite vehicle front to first characteristic information and second characteristic information.
Particularly, for how first characteristic information and second characteristic information being carried out Feature Fusion, the present invention proposes following method.Need to prove that those skilled in the art can make modification or the variation that is equal to following method, these all should be included within protection scope of the present invention.
At first, carry out the target registration.
In one embodiment of the invention; Respective items in second characteristic information of each characteristic item in first characteristic information of video object and radar target is compared; For example, with the distance of video object and the distance comparison of radar target, the deflection of video object and the deflection of radar target are compared; Whether the difference of characteristic information value of judging corresponding characteristic item is in predefined difference range; If the difference of the characteristic information value of each corresponding characteristic item all in predefined difference range, then judges it is same target, otherwise continue the next target of registration.By that analogy, up to all targets all registration come out.Wherein, predefined difference range is relevant with the precision of camera, and when the precision of the camera that adopts changed, predefined difference became also and can adjust accordingly.
Then, first characteristic information and each characteristic item in second characteristic information to same target carries out the final characteristic information of Feature Fusion with the barrier target of definite said vehicle front.
In one embodiment of the invention, for first characteristic information of same target and the same characteristic features item in second characteristic information, the first characteristic information value and the second characteristic information value are carried out weighted sum to obtain final characteristic information value.For example, suppose that confirm that through video image information this pedestrian is 10.5m with respect to the distance of vehicle, deflection is 60 ° for same pedestrian; Confirm that through radargrammetry information this pedestrian is 10.6m with respect to the distance of vehicle, deflection is 61 °, so, can confirm that this pedestrian is 10.5/2+10.6/2=10.55m with respect to the distance of vehicle, and deflection is 60/2+61/2=60.5 °.For first characteristic information of same target and the different characteristic item in second characteristic information, with the first characteristic information value or the second characteristic information value as final characteristic information value.
Should be understood that and can set up the target information matrix according to all characteristic informations of each target, each row of matrix is represented a target, and each row is represented a kind of characteristic information of target.And the kind of the characteristic information that collects in the process according to information acquisition can increase the columns of information matrix arbitrarily.
Step S104 carries out risk of collision according to final characteristic information value to the barrier target and estimates, and according to the risk of collision results estimated driver carried out early warning.
In one embodiment of the invention, the final characteristic information of each barrier target that step S103 is definite is input to and carries out the risk of collision estimation in the existing safe distance model, and according to estimating that the result who comes out carries out early warning to the driver.Particularly, according to the distance of vehicle self speed, vehicle and the place ahead barrier target and the speed of barrier target, judge whether vehicle can clash into the barrier target.In addition, can also under the situation that the driver does not have enough time to make a response, start the clamping device of automobile automatically, thereby guarantee vehicle and occupant's safety.
In another embodiment of the present invention; Before the final characteristic information of each barrier target that step S103 is confirmed is input to the safe distance model; Also can be earlier whether be traffic sign according to the shape disturbance in judgement thing target of barrier target; If disturbance in judgement thing target is a traffic sign; Then confirm the implication of traffic sign,, then barrier clarification of objective information is input to and carries out the risk of collision estimation in the safe distance model if disturbance in judgement thing target is not a traffic sign according to the traffic sign database.
In order to realize the foregoing description, the present invention also provides a kind of prior-warning device that prevents vehicle collision.Be illustrated in figure 2 as the structural representation of the prior-warning device that prevents vehicle collision of the embodiment of the invention, this device comprises: image capture module 10, image processing module 20, information acquisition module 30, Radar Signal Processing module 40, information fusion module 50 and early warning module 60.
Wherein, image capture module 10 is used for the video image information in collection vehicle the place ahead.The video image information that image processing module 20 is used for collecting according to image capture module 10 obtains first characteristic information of the barrier target of vehicle front.Information acquisition module 30 is used to obtain the radargrammetry information of vehicle front.Second characteristic information of the barrier target of the radargrammetry information acquisition vehicle front that Radar Signal Processing module 40 is used for obtaining according to information acquisition module 30.Information fusion module 50 is used to receive first characteristic information of image processing module 20 outputs and second characteristic information of Radar Signal Processing module 40 outputs, and first characteristic information and second characteristic information are merged the final characteristic information with the barrier target of confirming vehicle front.Early warning module 60 is used for according to final characteristic information the barrier target being carried out risk of collision to be estimated, and according to the risk of collision results estimated driver is carried out early warning.
In one embodiment of the invention, image capture module 10 can comprise two cameras.
According to one embodiment of present invention, image processing module 20 can comprise: matching unit 210 and computing unit 220.It is right with the image that obtains after the coupling to coupling that matching unit 210 is used for that the image information of two camera collections is carried out image.Computing module 220 is used for the right stereoscopic parallax of computed image setting up stereoscopic parallax figure, and according to first characteristic information of stereoscopic parallax figure dyscalculia thing target.
In one embodiment of the invention, image processing module 20 also can comprise copied cells 230.Copied cells 230 is used for duplicating an image information that collects of two cameras.
In one embodiment of the invention, prior-warning device also can comprise display interface 70.Display interface 70 be used for behind the displaying duplication image information a road, can be used for also showing that barrier target and barrier target under first characteristic information that computing module 220 calculates is with respect to the distance of vehicle.
In one embodiment of the invention, image processing module 20 also can comprise buffer unit 240.Another image information that collects in another road of image information after buffer unit 240 is used for buffer memory and duplicates and two cameras.
In one embodiment of the invention, buffer unit 240 can comprise first buffer and second buffer, makes the video image acquisition of front end and the video information process of rear end relatively independently to move.
In one embodiment of the invention, information fusion module 50 can comprise: target registration unit 510 and Feature Fusion unit 520.Whether target registration unit 510 is used for according to first characteristic information and barrier target under second characteristic information is judged first characteristic information identical with barrier target under second characteristic information.Feature Fusion unit 520 is used for barrier target under target registration unit 510 is judged first characteristic information when identical with barrier target under second characteristic information, and each characteristic item in first characteristic information and second characteristic information is carried out the final characteristic information of Feature Fusion with the barrier target of confirming vehicle front.Particularly, at first the characteristic information value with the same characteristic features item in first characteristic information and second characteristic information compares, and confirms the difference of the characteristic information value of each same characteristic features item; Whether the difference of characteristic information value of judging each same characteristic features item is all in predefined scope, and wherein, predefined range storage is among target registration unit 510; If the difference of characteristic information value of judging each same characteristic features item judges that then the described barrier target of first characteristic information is identical with the described barrier target of second characteristic information all in predefined scope.For first characteristic information of same target and the same characteristic features item in second characteristic information, the first characteristic information value and the second characteristic information value are carried out weighted sum to obtain final characteristic information value; For first characteristic information of same target and the different characteristic item in second characteristic information, with the first characteristic information value or the second characteristic information value as final characteristic information value.
In one embodiment of the invention, early warning module 60 can comprise: assessment unit 610 and prewarning unit 620.Assessment unit 610 is used for according to final characteristic information the barrier target being carried out risk of collision and estimates.Prewarning unit 620 is used for according to the estimated result of assessment unit 610 driver being carried out early warning.Under the situation that the driver does not have enough time to react, can also start clamping device 80 automatically, thereby guarantee vehicle and occupant's safety.
In one embodiment of the invention, early warning module 60 also can comprise judge module 630.Whether the shape disturbance in judgement thing target that judge module 630 is used for according to the barrier target is traffic sign; If disturbance in judgement thing target is a traffic sign, then confirm the implication of said barrier target according to the traffic sign database; If disturbance in judgement thing target is not a traffic sign, then barrier clarification of objective information is sent to assessment unit 610 and carries out the risk of collision estimation.
The information of the present invention through vehicle front that dual camera and radar are collected merges the barrier target of discerning vehicle front and the status information of barrier target, has improved the precision of Target Recognition, can realize the collision-proof alarm of automobile better.
Although illustrated and described embodiments of the invention; For those of ordinary skill in the art; Be appreciated that under the situation that does not break away from principle of the present invention and spirit and can carry out multiple variation, modification, replacement and modification that scope of the present invention is accompanying claims and be equal to and limit to these embodiment.
Claims (26)
1. a method for early warning that prevents vehicle collision is characterized in that, may further comprise the steps:
The video image information in collection vehicle the place ahead, and obtain first characteristic information of the barrier target of said vehicle front according to said video image information;
Obtain the radargrammetry information of said vehicle front, and according to second characteristic information of the barrier target of the said vehicle front of said radargrammetry information acquisition;
Said first characteristic information and said second characteristic information are merged the final characteristic information with the barrier target of confirming said vehicle front; And
According to said final characteristic information said barrier target is carried out risk of collision and estimate, and the driver is carried out early warning according to said risk of collision results estimated.
2. the method for early warning that prevents vehicle collision according to claim 1 is characterized in that, said video image information comprises first image information of obtaining through first camera and second image information of obtaining through second camera.
3. the method for early warning that prevents vehicle collision according to claim 2 is characterized in that, saidly obtains first characteristic information of the barrier target of said vehicle front according to video image information, specifically comprises:
It is right with the image that obtains after the coupling to coupling that said first image information and second image information are carried out image;
Calculate the right stereoscopic parallax of said image to set up stereoscopic parallax figure;
Calculate first characteristic information of said barrier target according to said stereoscopic parallax figure.
4. the method for early warning that prevents vehicle collision according to claim 3; It is characterized in that the size, shape, said barrier target that said first characteristic information comprises said barrier target is with respect in the distance and bearing angle of said vehicle one or more.
5. the method for early warning that prevents vehicle collision according to claim 1 is characterized in that, said second characteristic information comprises that said barrier target is with respect in distance, speed and the position angle of said vehicle one or more.
6. the method for early warning that prevents vehicle collision according to claim 3 is characterized in that, also comprises:
Said first image information is duplicated to obtain two-way first image information;
Export a road in said two-way first image information to display interface, and another road and said second video image information of said two-way first image information carried out buffer memory.
7. the method for early warning that prevents vehicle collision according to claim 6 is characterized in that, another road and said second video image information of said two-way first video image information carried out buffer memory, specifically comprises:
Another road and second video image information to said two-way first video image information carry out two-level cache.
8. the method for early warning that prevents vehicle collision according to claim 1 is characterized in that, said first characteristic information and second characteristic information is merged the final characteristic information with the barrier target of confirming vehicle front, specifically comprises:
Whether identical according to said first characteristic information and barrier target under said second characteristic information is judged said first characteristic information with barrier target under said second characteristic information;
If judge identically, then each characteristic item in said first characteristic information and second characteristic information is carried out the final characteristic information of Feature Fusion with the barrier target of confirming said vehicle front.
9. the method for early warning that prevents vehicle collision according to claim 8; It is characterized in that; Said whether identical with barrier target under second characteristic information according to first characteristic information and barrier target under second characteristic information is judged first characteristic information, specifically comprise:
The characteristic information value of the same characteristic features item in said first characteristic information and said second characteristic information is compared, confirm the difference of the characteristic information value of each same characteristic features item;
Whether the difference of characteristic information value of judging each same characteristic features item is all in predefined scope;
If the difference of characteristic information value of judging each same characteristic features item judges that then the barrier target under said first characteristic information is identical with the barrier target under second characteristic information all in predefined scope.
10. the method for early warning that prevents vehicle collision according to claim 8; It is characterized in that; Said each characteristic item in said first characteristic information and second characteristic information is carried out the final characteristic information of Feature Fusion with the barrier target of confirming said vehicle front, specifically comprises:
Same characteristic features item in said first characteristic information and second characteristic information is carried out weighted sum obtaining final characteristic information value, and the different characteristic item in said first characteristic information and second characteristic information is added into said final characteristic information.
11. the method for early warning that prevents vehicle collision according to claim 1 is characterized in that, carry out the risk of collision estimation according to said final characteristic information before, also comprises:
Judge according to the shape of said barrier target whether said barrier target is traffic sign;
If judging said barrier target is traffic sign, then confirm the implication of said traffic sign according to the traffic sign database;
Be not traffic sign if judge said barrier target, then carry out risk of collision and estimate according to said final characteristic information.
12. the method for early warning that prevents vehicle collision according to claim 1 is characterized in that, also comprises:
Judging that said vehicle has under the situation of risk of collision the automatically starting vehicle clamping device.
13. a prior-warning device that prevents vehicle collision is characterized in that, comprising:
Image capture module is used for the video image information in collection vehicle the place ahead;
Image processing module is used for confirming that according to said video image information the video image information of said image collection module collection obtains first characteristic information of the barrier target of vehicle front;
The information acquisition module is used to obtain the radargrammetry information of vehicle front;
The Radar Signal Processing module, second characteristic information of the barrier target of the said vehicle front of radargrammetry information acquisition that is used for obtaining according to said information acquisition module;
The information fusion module; Be used to receive first characteristic information of said image processing module output and second characteristic information of said Radar Signal Processing module output, and said first characteristic information and said second characteristic information are merged the final characteristic information with the barrier target of confirming said vehicle front; And
The early warning module is used for according to said final characteristic information said barrier target being carried out risk of collision and estimates, and according to said risk of collision results estimated the driver carried out early warning.
14. the prior-warning device that prevents vehicle collision according to claim 13; It is characterized in that; Said image capture module comprises first camera and second camera, obtains first image information through first camera, obtains second image information through second camera.
15. the prior-warning device that prevents vehicle collision according to claim 14 is characterized in that, said image processing module specifically comprises:
Matching unit, it is right with the image that obtains after the coupling to coupling to be used for that said first image information and second image information are carried out image;
Computing module is used to calculate the right stereoscopic parallax of said image setting up stereoscopic parallax figure, and calculates first characteristic information of said barrier target according to said stereoscopic parallax figure.
16. the prior-warning device that prevents vehicle collision according to claim 15; It is characterized in that the size, shape, said barrier target that said first characteristic information comprises said barrier target is with respect in the distance and bearing angle of said vehicle one or more.
17. the prior-warning device that prevents vehicle collision according to claim 15 is characterized in that, said second characteristic information comprises that said barrier target is with respect in distance, speed and the position angle of said vehicle one or more.
18. the prior-warning device that prevents vehicle collision according to claim 15 is characterized in that said image processing module also comprises copied cells, said copied cells is used to duplicate said first image information to obtain two-way first image information.
19. the prior-warning device that prevents vehicle collision according to claim 18 is characterized in that said image processing module also comprises buffer unit, said buffer unit is used for a road and said second image information of said two-way first image information of buffer memory.
20. the prior-warning device that prevents vehicle collision according to claim 19 is characterized in that, said buffer unit comprises first buffer and second buffer.
21. the prior-warning device that prevents vehicle collision according to claim 20; It is characterized in that; Said prior-warning device also comprises display interface; Be used for showing another road of said two-way first image information, and show that barrier target and said barrier target under said first characteristic information is with respect to the distance of said vehicle.
22. the prior-warning device that prevents vehicle collision according to claim 13 is characterized in that, said information fusion module specifically comprises:
Whether the target registration unit is used for according to said first characteristic information and barrier target under said second characteristic information is judged said first characteristic information identical with barrier target under said second characteristic information;
The Feature Fusion unit; Be used for when said target registration unit judges that barrier target under said first characteristic information is identical with the barrier target under said second characteristic information, each characteristic item in said first characteristic information and second characteristic information is carried out the final characteristic information of Feature Fusion with the barrier target of confirming said vehicle front.
23. the prior-warning device that prevents vehicle collision according to claim 22; It is characterized in that; Whether said target registration unit is identical with barrier target under second characteristic information according to first characteristic information and barrier target under second characteristic information is judged first characteristic information, specifically comprises:
The characteristic information value of the same characteristic features item in said first characteristic information and said second characteristic information is compared, confirm the difference of the characteristic information value of each same characteristic features item;
Whether the difference of characteristic information value of judging each same characteristic features item is all in predefined scope, and said predefined range storage is among said target registration unit;
If the difference of characteristic information value of judging each same characteristic features item judges that then the barrier target under said first characteristic information is identical with the barrier target under second characteristic information all in predefined scope.
24. the prior-warning device that prevents vehicle collision according to claim 22; It is characterized in that; Said Feature Fusion unit carries out the final characteristic information of Feature Fusion with the barrier target of definite said vehicle front to first characteristic information and each characteristic item in second characteristic information of same target, specifically comprises:
Same characteristic features item in said first characteristic information and second characteristic information is carried out weighted sum obtaining final characteristic information value, and the different characteristic item in said first characteristic information and second characteristic information is added into said final characteristic information.
25. the prior-warning device that prevents vehicle collision according to claim 13 is characterized in that, said early warning module specifically comprises:
Assessment unit is used for according to the final characteristic information of said barrier target said barrier target being carried out the risk of collision estimation; And
Prewarning unit is used for according to the estimated result of said assessment unit the driver being carried out early warning.
26. the prior-warning device that prevents vehicle collision according to claim 25; It is characterized in that; Said early warning module also comprises judge module; Said judge module is used for judging according to the shape of said barrier target whether said barrier target is traffic sign, is traffic sign if judge said barrier target, then confirms the implication of said barrier target according to the traffic sign database; Be not traffic sign if judge said barrier target, then said barrier clarification of objective information be sent to said assessment unit and carry out the risk of collision estimation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010105872145A CN102542843A (en) | 2010-12-07 | 2010-12-07 | Early warning method for preventing vehicle collision and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010105872145A CN102542843A (en) | 2010-12-07 | 2010-12-07 | Early warning method for preventing vehicle collision and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102542843A true CN102542843A (en) | 2012-07-04 |
Family
ID=46349631
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010105872145A Pending CN102542843A (en) | 2010-12-07 | 2010-12-07 | Early warning method for preventing vehicle collision and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102542843A (en) |
Cited By (68)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103287372A (en) * | 2013-06-19 | 2013-09-11 | 贺亮才 | Automobile anti-collision safe protecting method based on image processing |
| CN103366483A (en) * | 2013-06-27 | 2013-10-23 | 深圳市智美达科技有限公司 | Monitoring alarm system |
| CN103400499A (en) * | 2013-07-22 | 2013-11-20 | 青岛海信网络科技股份有限公司 | Ultra-high definition intelligent video electronic police system and vehicle violation judging method of ultra-high definition intelligent video electronic police system |
| CN104149729A (en) * | 2013-05-13 | 2014-11-19 | 上海汽车集团股份有限公司 | Method and system for recognizing barrier around driving vehicle |
| CN104200542A (en) * | 2014-09-24 | 2014-12-10 | 西安酷派软件科技有限公司 | Vehicle pre-warning method, vehicle pre-warning device, terminal and travelling data recorder |
| CN104200689A (en) * | 2014-08-28 | 2014-12-10 | 长城汽车股份有限公司 | Road early warning method and device |
| CN104574376A (en) * | 2014-12-24 | 2015-04-29 | 重庆大学 | Anti-collision method based on joint verification of binocular vision and laser radar in congested traffic |
| CN104603855A (en) * | 2012-09-03 | 2015-05-06 | 丰田自动车株式会社 | Collision determination device and collision determination method |
| CN104599530A (en) * | 2013-09-19 | 2015-05-06 | 罗伯特·博世有限公司 | Driver assistance system for a motor vehicle |
| CN104620297A (en) * | 2012-09-03 | 2015-05-13 | 丰田自动车株式会社 | Speed calculating device and speed calculating method, and collision determination device |
| CN104899855A (en) * | 2014-03-06 | 2015-09-09 | 株式会社日立制作所 | Three-dimensional obstacle detection method and apparatus |
| CN104908743A (en) * | 2015-06-03 | 2015-09-16 | 奇瑞汽车股份有限公司 | Vehicle collision prevention prewarning system and control method thereof |
| CN105159888A (en) * | 2014-06-08 | 2015-12-16 | 上海能感物联网有限公司 | Controller device for performing remote automatic navigation and driving automobile through Chinese speech |
| CN105161101A (en) * | 2014-06-08 | 2015-12-16 | 苗码信息科技(上海)股份有限公司 | Method of achieving automatic navigation and driving automobile through on-site speaker-independent foreign language voice |
| CN105204444A (en) * | 2014-06-08 | 2015-12-30 | 上海能感物联网有限公司 | Chinese text on-site automatic navigation and automobile driving controller device |
| CN105224523A (en) * | 2014-06-08 | 2016-01-06 | 上海能感物联网有限公司 | The sound remote self-navigation of unspecified person foreign language the control device driven a car |
| CN105242643A (en) * | 2014-06-08 | 2016-01-13 | 苗码信息科技(上海)股份有限公司 | Method for automatically navigating and driving automobile remotely through Chinese speech |
| CN105247592A (en) * | 2013-05-31 | 2016-01-13 | 丰田自动车株式会社 | Driving assistance device for vehicles and onboard computer |
| CN105264587A (en) * | 2013-07-08 | 2016-01-20 | 本田技研工业株式会社 | Object recognition device |
| CN105280185A (en) * | 2014-06-08 | 2016-01-27 | 苗码信息科技(上海)股份有限公司 | Speaker-independent foreign language speech remote automatic navigation and automobile driving method |
| CN105302082A (en) * | 2014-06-08 | 2016-02-03 | 上海能感物联网有限公司 | Controller apparatus for on-site automatic navigation and car driving by non-specific person foreign language speech |
| CN105302799A (en) * | 2014-06-08 | 2016-02-03 | 上海能感物联网有限公司 | Controller apparatus of field automatic navigating and automobile driving by using foreign natural-language text |
| CN105302081A (en) * | 2014-06-08 | 2016-02-03 | 上海能感物联网有限公司 | Controller apparatus for remote automatic navigation and car driving by spoken foreign language text |
| CN105320648A (en) * | 2014-06-08 | 2016-02-10 | 苗码信息科技(上海)股份有限公司 | Method for remote automatic navigation and automobile driving by utilizing foreign language natural language text |
| CN105466438A (en) * | 2014-09-25 | 2016-04-06 | 通用汽车环球科技运作有限责任公司 | Sensor odometry and application in crash avoidance vehicle |
| CN105480227A (en) * | 2015-12-29 | 2016-04-13 | 大连楼兰科技股份有限公司 | Information fusion method based on infrared radar and video image in active driving technique |
| CN105980880A (en) * | 2014-02-10 | 2016-09-28 | 株式会社电装 | Axis deviation detection device for beam sensor |
| CN106255997A (en) * | 2014-05-15 | 2016-12-21 | 本田技研工业株式会社 | Auxiliary device for moving |
| CN106291523A (en) * | 2015-06-24 | 2017-01-04 | 宏达国际电子股份有限公司 | Hand-held device, object localization method and computer-readable record medium |
| CN106408940A (en) * | 2016-11-02 | 2017-02-15 | 南京慧尔视智能科技有限公司 | Microwave and video data fusion-based traffic detection method and device |
| US9582886B2 (en) | 2013-07-08 | 2017-02-28 | Honda Motor Co., Ltd. | Object recognition device |
| CN106816036A (en) * | 2017-04-01 | 2017-06-09 | 北京中鼎思宏科技有限公司 | The method for early warning and system of vehicle collision risk |
| CN107991677A (en) * | 2017-11-28 | 2018-05-04 | 广州汽车集团股份有限公司 | A kind of pedestrian detection method |
| CN108263324A (en) * | 2016-12-30 | 2018-07-10 | 现代自动车株式会社 | Pedestrian detection and pedestrian impact preventing mean and method based on pose information |
| CN108710828A (en) * | 2018-04-18 | 2018-10-26 | 北京汽车集团有限公司 | The method, apparatus and storage medium and vehicle of identification object |
| CN108846336A (en) * | 2018-05-31 | 2018-11-20 | 深圳市易成自动驾驶技术有限公司 | Object detection method, device and computer readable storage medium |
| CN109457654A (en) * | 2018-12-21 | 2019-03-12 | 吉林大学 | A kind of sprinkling truck preventing from mistake in jetting system based on pedestrian detection |
| CN109521426A (en) * | 2017-09-18 | 2019-03-26 | 比亚迪股份有限公司 | The method and device thereof of the angle of target are obtained based on car radar |
| CN109697861A (en) * | 2019-02-21 | 2019-04-30 | 武昌理工学院 | A kind of road barricade identification device and recognition methods |
| CN109727188A (en) * | 2017-10-31 | 2019-05-07 | 比亚迪股份有限公司 | Image processing method and its device, safe driving method and its device |
| CN109839634A (en) * | 2019-01-25 | 2019-06-04 | 中国汽车技术研究中心有限公司 | A kind of subject fusion method of vehicle-mounted camera and radar |
| CN109901156A (en) * | 2019-01-25 | 2019-06-18 | 中国汽车技术研究中心有限公司 | A kind of subject fusion method and apparatus of vehicle millimetre-wave radar and camera |
| CN110046569A (en) * | 2019-04-12 | 2019-07-23 | 北京百度网讯科技有限公司 | A kind of data processing method, device and electronic equipment |
| CN110356325A (en) * | 2019-09-04 | 2019-10-22 | 魔视智能科技(上海)有限公司 | A kind of urban transportation passenger stock blind area early warning system |
| CN110582803A (en) * | 2017-04-26 | 2019-12-17 | 三菱电机株式会社 | Processing device and object identification information generation method |
| CN110633625A (en) * | 2019-07-31 | 2019-12-31 | 北京木牛领航科技有限公司 | Identification method and system |
| CN110816527A (en) * | 2019-11-27 | 2020-02-21 | 奇瑞汽车股份有限公司 | Vehicle-mounted night vision safety method and system |
| CN110888135A (en) * | 2018-08-15 | 2020-03-17 | 比亚迪股份有限公司 | Target identification method and device, storage medium and vehicle |
| CN111031231A (en) * | 2018-10-10 | 2020-04-17 | 富泰华工业（深圳）有限公司 | Electronic device and method for judging three-dimensional object |
| CN111081061A (en) * | 2018-10-22 | 2020-04-28 | 杭州海康威视数字技术股份有限公司 | Collision early warning method and device |
| CN111137283A (en) * | 2019-12-27 | 2020-05-12 | 奇瑞汽车股份有限公司 | Sensor data fusion method and device, advanced driving assistance system and vehicle |
| CN111409584A (en) * | 2020-02-27 | 2020-07-14 | 广汽蔚来新能源汽车科技有限公司 | Pedestrian protection method, device, computer equipment and storage medium |
| CN111599216A (en) * | 2020-05-18 | 2020-08-28 | 合肥杰代机电科技有限公司 | Auxiliary driving method, device and system based on image recognition and UWB (ultra-wideband) tag |
| CN111762152A (en) * | 2019-03-30 | 2020-10-13 | 上海欧菲智能车联科技有限公司 | Parking method, parking device, parking equipment, vehicle and computer-readable storage medium |
| CN111923898A (en) * | 2019-05-13 | 2020-11-13 | 广州汽车集团股份有限公司 | Obstacle detection method and device |
| CN112101316A (en) * | 2020-11-17 | 2020-12-18 | 北京中科原动力科技有限公司 | Target detection method and system |
| CN112349142A (en) * | 2020-10-29 | 2021-02-09 | 深圳市元征科技股份有限公司 | Vehicle rear-end collision early warning method and related equipment thereof |
| CN112489496A (en) * | 2020-12-25 | 2021-03-12 | 深圳市爱培科技术股份有限公司 | Vehicle safety early warning method and device based on video identification |
| 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 |
| CN113077520A (en) * | 2021-03-19 | 2021-07-06 | 中移智行网络科技有限公司 | Collision prediction method and device and edge calculation server |
| US11066067B2 (en) * | 2018-06-29 | 2021-07-20 | Baidu Usa Llc | Planning parking trajectory for self-driving vehicles |
| US11148663B2 (en) | 2019-10-02 | 2021-10-19 | Ford Global Technologies, Llc | Enhanced collision mitigation |
| CN113701642A (en) * | 2021-07-30 | 2021-11-26 | 的卢技术有限公司 | Method and system for calculating appearance size of vehicle body |
| CN114407845A (en) * | 2021-12-24 | 2022-04-29 | 阿波罗智能技术(北京)有限公司 | Brake control method, brake control device, vehicle, electronic device, and storage medium |
| CN114550475A (en) * | 2020-11-24 | 2022-05-27 | 通用汽车环球科技运作有限责任公司 | Method and system for interactive hypothesis estimation for multi-vehicle traffic for autonomous driving |
| CN114604239A (en) * | 2022-03-15 | 2022-06-10 | 安徽科技学院 | Vehicle backing anti-collision system based on Internet of things |
| CN115421113A (en) * | 2022-09-29 | 2022-12-02 | 成都环泰睿诚科技有限公司 | A testing arrangement for millimeter wave radar |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001134769A (en) * | 1999-11-04 | 2001-05-18 | Honda Motor Co Ltd | Object recognizing device |
| JP2007226680A (en) * | 2006-02-24 | 2007-09-06 | Toyota Motor Corp | Object detection system |
| CN101739843A (en) * | 2009-12-04 | 2010-06-16 | 河海大学常州校区 | Device and method for real-time three-dimensionally sensing safe driving of vehicle having mixed multi-visual information |
| JP2010143578A (en) * | 2005-05-12 | 2010-07-01 | Denso Corp | Driver condition detecting device, in-vehicle alarm system and drive assistance system |
| CN101837782A (en) * | 2009-01-26 | 2010-09-22 | 通用汽车环球科技运作公司 | Be used to collide the multiple goal Fusion Module of preparation system |
-
2010
- 2010-12-07 CN CN2010105872145A patent/CN102542843A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001134769A (en) * | 1999-11-04 | 2001-05-18 | Honda Motor Co Ltd | Object recognizing device |
| JP2010143578A (en) * | 2005-05-12 | 2010-07-01 | Denso Corp | Driver condition detecting device, in-vehicle alarm system and drive assistance system |
| JP2007226680A (en) * | 2006-02-24 | 2007-09-06 | Toyota Motor Corp | Object detection system |
| CN101837782A (en) * | 2009-01-26 | 2010-09-22 | 通用汽车环球科技运作公司 | Be used to collide the multiple goal Fusion Module of preparation system |
| CN101739843A (en) * | 2009-12-04 | 2010-06-16 | 河海大学常州校区 | Device and method for real-time three-dimensionally sensing safe driving of vehicle having mixed multi-visual information |
Cited By (90)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104620297B (en) * | 2012-09-03 | 2017-03-22 | 丰田自动车株式会社 | Speed calculating device and speed calculating method, and collision determination device |
| CN104603855A (en) * | 2012-09-03 | 2015-05-06 | 丰田自动车株式会社 | Collision determination device and collision determination method |
| CN104603855B (en) * | 2012-09-03 | 2016-06-22 | 丰田自动车株式会社 | Collision determination device and collision determination method |
| CN104620297A (en) * | 2012-09-03 | 2015-05-13 | 丰田自动车株式会社 | Speed calculating device and speed calculating method, and collision determination device |
| CN104149729B (en) * | 2013-05-13 | 2017-07-21 | 上海汽车集团股份有限公司 | The method and system of identification traveling vehicle periphery barrier |
| CN104149729A (en) * | 2013-05-13 | 2014-11-19 | 上海汽车集团股份有限公司 | Method and system for recognizing barrier around driving vehicle |
| CN105247592A (en) * | 2013-05-31 | 2016-01-13 | 丰田自动车株式会社 | Driving assistance device for vehicles and onboard computer |
| CN105247592B (en) * | 2013-05-31 | 2017-07-07 | 丰田自动车株式会社 | The drive supporting device of vehicle and the driving support method of vehicle |
| CN103287372A (en) * | 2013-06-19 | 2013-09-11 | 贺亮才 | Automobile anti-collision safe protecting method based on image processing |
| CN103287372B (en) * | 2013-06-19 | 2015-09-23 | 贺亮才 | A kind of automobile collision preventing method for security protection based on image procossing |
| CN103366483A (en) * | 2013-06-27 | 2013-10-23 | 深圳市智美达科技有限公司 | Monitoring alarm system |
| CN103366483B (en) * | 2013-06-27 | 2016-02-24 | 深圳市智美达科技有限公司 | monitoring and alarming system |
| CN105264587B (en) * | 2013-07-08 | 2017-04-26 | 本田技研工业株式会社 | Object recognition device |
| US9582886B2 (en) | 2013-07-08 | 2017-02-28 | Honda Motor Co., Ltd. | Object recognition device |
| CN105264587A (en) * | 2013-07-08 | 2016-01-20 | 本田技研工业株式会社 | Object recognition device |
| CN103400499B (en) * | 2013-07-22 | 2015-04-22 | 青岛海信网络科技股份有限公司 | Ultra-high definition intelligent video electronic police system and vehicle violation judging method of ultra-high definition intelligent video electronic police system |
| CN103400499A (en) * | 2013-07-22 | 2013-11-20 | 青岛海信网络科技股份有限公司 | Ultra-high definition intelligent video electronic police system and vehicle violation judging method of ultra-high definition intelligent video electronic police system |
| CN104599530A (en) * | 2013-09-19 | 2015-05-06 | 罗伯特·博世有限公司 | Driver assistance system for a motor vehicle |
| CN105980880A (en) * | 2014-02-10 | 2016-09-28 | 株式会社电装 | Axis deviation detection device for beam sensor |
| CN105980880B (en) * | 2014-02-10 | 2018-10-26 | 株式会社电装 | The axle offset detection device of beam sensor |
| CN104899855A (en) * | 2014-03-06 | 2015-09-09 | 株式会社日立制作所 | Three-dimensional obstacle detection method and apparatus |
| CN106255997A (en) * | 2014-05-15 | 2016-12-21 | 本田技研工业株式会社 | Auxiliary device for moving |
| CN105204444A (en) * | 2014-06-08 | 2015-12-30 | 上海能感物联网有限公司 | Chinese text on-site automatic navigation and automobile driving controller device |
| CN105302799A (en) * | 2014-06-08 | 2016-02-03 | 上海能感物联网有限公司 | Controller apparatus of field automatic navigating and automobile driving by using foreign natural-language text |
| CN105302081A (en) * | 2014-06-08 | 2016-02-03 | 上海能感物联网有限公司 | Controller apparatus for remote automatic navigation and car driving by spoken foreign language text |
| CN105320648A (en) * | 2014-06-08 | 2016-02-10 | 苗码信息科技(上海)股份有限公司 | Method for remote automatic navigation and automobile driving by utilizing foreign language natural language text |
| CN105302082A (en) * | 2014-06-08 | 2016-02-03 | 上海能感物联网有限公司 | Controller apparatus for on-site automatic navigation and car driving by non-specific person foreign language speech |
| CN105280185A (en) * | 2014-06-08 | 2016-01-27 | 苗码信息科技(上海)股份有限公司 | Speaker-independent foreign language speech remote automatic navigation and automobile driving method |
| CN105242643A (en) * | 2014-06-08 | 2016-01-13 | 苗码信息科技(上海)股份有限公司 | Method for automatically navigating and driving automobile remotely through Chinese speech |
| CN105224523A (en) * | 2014-06-08 | 2016-01-06 | 上海能感物联网有限公司 | The sound remote self-navigation of unspecified person foreign language the control device driven a car |
| CN105161101A (en) * | 2014-06-08 | 2015-12-16 | 苗码信息科技(上海)股份有限公司 | Method of achieving automatic navigation and driving automobile through on-site speaker-independent foreign language voice |
| CN105159888A (en) * | 2014-06-08 | 2015-12-16 | 上海能感物联网有限公司 | Controller device for performing remote automatic navigation and driving automobile through Chinese speech |
| CN104200689A (en) * | 2014-08-28 | 2014-12-10 | 长城汽车股份有限公司 | Road early warning method and device |
| CN104200542A (en) * | 2014-09-24 | 2014-12-10 | 西安酷派软件科技有限公司 | Vehicle pre-warning method, vehicle pre-warning device, terminal and travelling data recorder |
| CN105466438B (en) * | 2014-09-25 | 2018-09-21 | 通用汽车环球科技运作有限责任公司 | Sensor instrument distance in anticollision vehicle and application |
| CN105466438A (en) * | 2014-09-25 | 2016-04-06 | 通用汽车环球科技运作有限责任公司 | Sensor odometry and application in crash avoidance vehicle |
| CN104574376B (en) * | 2014-12-24 | 2017-08-08 | 重庆大学 | Avoiding collision based on binocular vision and laser radar joint verification in hustle traffic |
| CN104574376A (en) * | 2014-12-24 | 2015-04-29 | 重庆大学 | Anti-collision method based on joint verification of binocular vision and laser radar in congested traffic |
| CN104908743A (en) * | 2015-06-03 | 2015-09-16 | 奇瑞汽车股份有限公司 | Vehicle collision prevention prewarning system and control method thereof |
| CN106291523A (en) * | 2015-06-24 | 2017-01-04 | 宏达国际电子股份有限公司 | Hand-held device, object localization method and computer-readable record medium |
| CN106291523B (en) * | 2015-06-24 | 2019-04-05 | 宏达国际电子股份有限公司 | Hand-held device, object localization method and computer-readable recording medium |
| CN105480227A (en) * | 2015-12-29 | 2016-04-13 | 大连楼兰科技股份有限公司 | Information fusion method based on infrared radar and video image in active driving technique |
| CN105480227B (en) * | 2015-12-29 | 2017-12-15 | 大连楼兰科技股份有限公司 | The method merged in active driving technology based on infrared radar with video image information |
| CN106408940A (en) * | 2016-11-02 | 2017-02-15 | 南京慧尔视智能科技有限公司 | Microwave and video data fusion-based traffic detection method and device |
| CN108263324A (en) * | 2016-12-30 | 2018-07-10 | 现代自动车株式会社 | Pedestrian detection and pedestrian impact preventing mean and method based on pose information |
| US11167736B2 (en) | 2016-12-30 | 2021-11-09 | Hyundai Motor Company | Posture information based pedestrian detection and pedestrian collision prevention apparatus and method |
| CN106816036A (en) * | 2017-04-01 | 2017-06-09 | 北京中鼎思宏科技有限公司 | The method for early warning and system of vehicle collision risk |
| CN110582803B (en) * | 2017-04-26 | 2022-02-08 | 三菱电机株式会社 | Processing apparatus |
| CN110582803A (en) * | 2017-04-26 | 2019-12-17 | 三菱电机株式会社 | Processing device and object identification information generation method |
| CN109521426A (en) * | 2017-09-18 | 2019-03-26 | 比亚迪股份有限公司 | The method and device thereof of the angle of target are obtained based on car radar |
| CN109727188A (en) * | 2017-10-31 | 2019-05-07 | 比亚迪股份有限公司 | Image processing method and its device, safe driving method and its device |
| WO2019085929A1 (en) * | 2017-10-31 | 2019-05-09 | 比亚迪股份有限公司 | Image processing method, device for same, and method for safe driving |
| CN107991677A (en) * | 2017-11-28 | 2018-05-04 | 广州汽车集团股份有限公司 | A kind of pedestrian detection method |
| CN108710828A (en) * | 2018-04-18 | 2018-10-26 | 北京汽车集团有限公司 | The method, apparatus and storage medium and vehicle of identification object |
| CN108846336A (en) * | 2018-05-31 | 2018-11-20 | 深圳市易成自动驾驶技术有限公司 | Object detection method, device and computer readable storage medium |
| US11066067B2 (en) * | 2018-06-29 | 2021-07-20 | Baidu Usa Llc | Planning parking trajectory for self-driving vehicles |
| CN110888135A (en) * | 2018-08-15 | 2020-03-17 | 比亚迪股份有限公司 | Target identification method and device, storage medium and vehicle |
| CN111031231A (en) * | 2018-10-10 | 2020-04-17 | 富泰华工业（深圳）有限公司 | Electronic device and method for judging three-dimensional object |
| CN111081061B (en) * | 2018-10-22 | 2021-09-21 | 杭州海康威视数字技术股份有限公司 | Collision early warning method and device |
| CN111081061A (en) * | 2018-10-22 | 2020-04-28 | 杭州海康威视数字技术股份有限公司 | Collision early warning method and device |
| CN109457654A (en) * | 2018-12-21 | 2019-03-12 | 吉林大学 | A kind of sprinkling truck preventing from mistake in jetting system based on pedestrian detection |
| CN109839634A (en) * | 2019-01-25 | 2019-06-04 | 中国汽车技术研究中心有限公司 | A kind of subject fusion method of vehicle-mounted camera and radar |
| CN109901156A (en) * | 2019-01-25 | 2019-06-18 | 中国汽车技术研究中心有限公司 | A kind of subject fusion method and apparatus of vehicle millimetre-wave radar and camera |
| CN109697861A (en) * | 2019-02-21 | 2019-04-30 | 武昌理工学院 | A kind of road barricade identification device and recognition methods |
| CN111762152B (en) * | 2019-03-30 | 2022-05-24 | 上海欧菲智能车联科技有限公司 | Parking method, parking device, parking equipment, vehicle and computer-readable storage medium |
| CN111762152A (en) * | 2019-03-30 | 2020-10-13 | 上海欧菲智能车联科技有限公司 | Parking method, parking device, parking equipment, vehicle and computer-readable storage medium |
| CN110046569B (en) * | 2019-04-12 | 2022-04-12 | 北京百度网讯科技有限公司 | Unmanned driving data processing method and device and electronic equipment |
| CN110046569A (en) * | 2019-04-12 | 2019-07-23 | 北京百度网讯科技有限公司 | A kind of data processing method, device and electronic equipment |
| CN111923898A (en) * | 2019-05-13 | 2020-11-13 | 广州汽车集团股份有限公司 | Obstacle detection method and device |
| CN110633625A (en) * | 2019-07-31 | 2019-12-31 | 北京木牛领航科技有限公司 | Identification method and system |
| CN110356325B (en) * | 2019-09-04 | 2020-02-14 | 魔视智能科技(上海)有限公司 | Urban traffic passenger vehicle blind area early warning system |
| CN110356325A (en) * | 2019-09-04 | 2019-10-22 | 魔视智能科技(上海)有限公司 | A kind of urban transportation passenger stock blind area early warning system |
| US11148663B2 (en) | 2019-10-02 | 2021-10-19 | Ford Global Technologies, Llc | Enhanced collision mitigation |
| CN110816527A (en) * | 2019-11-27 | 2020-02-21 | 奇瑞汽车股份有限公司 | Vehicle-mounted night vision safety method and system |
| CN111137283A (en) * | 2019-12-27 | 2020-05-12 | 奇瑞汽车股份有限公司 | Sensor data fusion method and device, advanced driving assistance system and vehicle |
| CN111137283B (en) * | 2019-12-27 | 2022-02-01 | 芜湖雄狮汽车科技有限公司 | Sensor data fusion method and device, advanced driving assistance system and vehicle |
| CN111409584A (en) * | 2020-02-27 | 2020-07-14 | 广汽蔚来新能源汽车科技有限公司 | Pedestrian protection method, device, computer equipment and storage medium |
| CN111599216A (en) * | 2020-05-18 | 2020-08-28 | 合肥杰代机电科技有限公司 | Auxiliary driving method, device and system based on image recognition and UWB (ultra-wideband) tag |
| CN112349142A (en) * | 2020-10-29 | 2021-02-09 | 深圳市元征科技股份有限公司 | Vehicle rear-end collision early warning method and related equipment thereof |
| CN112101316B (en) * | 2020-11-17 | 2022-03-25 | 北京中科原动力科技有限公司 | Target detection method and system |
| CN112101316A (en) * | 2020-11-17 | 2020-12-18 | 北京中科原动力科技有限公司 | Target detection method and system |
| CN114550475A (en) * | 2020-11-24 | 2022-05-27 | 通用汽车环球科技运作有限责任公司 | Method and system for interactive hypothesis estimation for multi-vehicle traffic for autonomous driving |
| 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 |
| CN112489496A (en) * | 2020-12-25 | 2021-03-12 | 深圳市爱培科技术股份有限公司 | Vehicle safety early warning method and device based on video identification |
| 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 |
| CN113077520A (en) * | 2021-03-19 | 2021-07-06 | 中移智行网络科技有限公司 | Collision prediction method and device and edge calculation server |
| CN113701642A (en) * | 2021-07-30 | 2021-11-26 | 的卢技术有限公司 | Method and system for calculating appearance size of vehicle body |
| CN114407845A (en) * | 2021-12-24 | 2022-04-29 | 阿波罗智能技术(北京)有限公司 | Brake control method, brake control device, vehicle, electronic device, and storage medium |
| CN114604239A (en) * | 2022-03-15 | 2022-06-10 | 安徽科技学院 | Vehicle backing anti-collision system based on Internet of things |
| CN115421113A (en) * | 2022-09-29 | 2022-12-02 | 成都环泰睿诚科技有限公司 | A testing arrangement for millimeter wave radar |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102542843A (en) | Early warning method for preventing vehicle collision and device | |
| CN102481931B (en) | Vehicle Controller | |
| CN111932901B (en) | Road vehicle tracking detection apparatus, method and storage medium | |
| JP4420011B2 (en) | Object detection device | |
| CN106611512B (en) | Method, device and system for processing starting of front vehicle | |
| CN112349144B (en) | Monocular vision-based vehicle collision early warning method and system | |
| CN102806913B (en) | Novel lane line deviation detection method and device | |
| CN112562405A (en) | Radar video intelligent fusion and early warning method and system | |
| CN103630122B (en) | Monocular vision lane line detection method and distance measurement method thereof | |
| CN111727437A (en) | Multispectral system providing pre-crash warning | |
| US10369995B2 (en) | Information processing device, information processing method, control device for vehicle, and control method for vehicle | |
| CN103176185A (en) | Method and system for detecting road barrier | |
| Ruder et al. | Highway lane change assistant | |
| CN106585670B (en) | To train detection systems and method before a kind of urban track traffic based on video | |
| JP2019207653A (en) | Detection device and detection system | |
| CN106164930A (en) | Method for lane detection | |
| EP3364336B1 (en) | A method and apparatus for estimating a range of a moving object | |
| US11753002B2 (en) | Vehicular control system | |
| CN106570487A (en) | Method and device for predicting collision between objects | |
| CN112835030A (en) | Data fusion method and device for obstacle target and intelligent automobile | |
| CN103673977B (en) | The method and apparatus of rear dead zone of vehicle detection | |
| KR20100066952A (en) | Apparatus for tracking obstacle using stereo vision and method thereof | |
| JP5997962B2 (en) | In-vehicle lane marker recognition device | |
| Fakhfakh et al. | Weighted v-disparity approach for obstacles localization in highway environments | |
| CN111612818A (en) | Novel binocular vision multi-target tracking method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20120704 |