A kind of panorama parking assisting system and its implementation
Technical field
The present invention relates to vehicle electric field, relate in particular to a kind of panorama parking assisting system and its implementation.
Background technology
Early stage parking assisting system adopts radar or single camera usually; Adopt the mode of audible alarm or demonstration rear view of vehicle camera video image; Help the vehicle driver to judge blind angle place's vehicle and obstacle distance, but adopt the radar type of alarm, the demonstration of distance is not directly perceived; Adopt rearmounted camera mode, then still can exist blind angle and distance to judge inaccurate problem, technology is risen gradually so panorama is parked.
In the panorama parking assisting system, a plurality of cameras of operated by rotary motion obtain the image of motor vehicle environment; Thereby make things convenient for chaufeur to judge environment surrounding automobile, but existing panorama parking assisting system, the anamorphose that it absorbed is serious; And be that the image of proofreading and correct or do not have to proofread and correct is simply spliced the confession driver's observation, find out probably through human eye whether vehicle periphery has obstacle, this mode poor stability; Stability is not high, has brought certain hidden danger to safe driving.
Therefore, prior art awaits to improve and development.
Summary of the invention
Deficiency in view of above-mentioned prior art the object of the present invention is to provide a kind of panorama parking assisting system and its implementation, is intended to solve safety and the stable problem that existing automobile parking process exists.
Technical scheme of the present invention is following:
A kind of panorama parking assisting system; Wherein, Comprise the image that is arranged on all around the wide-angle imaging head that is used to gather the peripheral vehicle image of car body, is used to proofread and correct and splices the collection of wide-angle imaging head with the panoramic picture generation module that generates panoramic picture, be used for said panoramic picture is carried out the detection module of obstacle identification and is used for the reminding module according to the testing result output detection information of detection module, said wide-angle imaging head, panoramic picture generation module, detection module and reminding module electrically connect successively.
Described panorama parking assisting system wherein, is provided with the image pattern storehouse in the said detection module, the negative sample image that stores the positive sample image that comprises obstacle information in the panoramic picture in the said image pattern storehouse and do not contain obstacle information.
Described panorama parking assisting system wherein, also is provided with the target classification device in the said detection module, positive sample image and negative sample image that said target classification device is used for the image pattern storehouse is stored carry out the obstacle target detect, and then the cognitive disorders thing.
Described panorama parking assisting system, wherein, said detection information is exported with image, literal or speech form.
Described panorama parking assisting system, wherein, said reminding module comprises the display device for mounting on vehicle that is used to show detection information.
Described panorama parking assisting system is characterized in that, said display device for mounting on vehicle is one or more combinations in vehicle-mounted LCD display, OLED screen, LED screen, the video input display equipment.
Described panorama parking assisting system, wherein, said reminding module also comprises the speech play module that is used to play detection information.
Described panorama parking assisting system, wherein, said obstacle comprises people, animal or Rigid Bodies.
A kind of implementation method of described panorama parking assisting system wherein, may further comprise the steps:
A, said wide-angle imaging head are gathered the image of peripheral vehicle;
The generation panoramic picture is proofreaied and correct, spliced to B, said panoramic picture generation module to said image;
C, said detection module carry out obstacle identification to said panoramic picture and obtain testing result;
D, said reminding module are according to testing result output detection information.
Beneficial effect: panorama parking assisting system of the present invention and its implementation, through the image of wide-angle imaging head collection peripheral vehicle; The generation panoramic picture is proofreaied and correct, spliced to the panoramic picture generation module to said image; Detection module carries out obstacle identification to said panoramic picture and obtains testing result; Reminding module is according to testing result output detection information; The detection information accurate and effective that the present invention adopts multiple technologies to obtain; Can effectively judge the obstacle information of peripheral vehicle, make things convenient for the driving of parking of chaufeur to wait operation, improve the safety of driving; Cost of the present invention is low, device is simple, practical.
Description of drawings
Fig. 1 is the structured flowchart of panorama parking assisting system of the present invention.
Fig. 2 is the diagram of circuit of panorama parking assisting system implementation method of the present invention.
The specific embodiment
The present invention provides a kind of panorama parking assisting system and its implementation, and is clearer, clear and definite for making the object of the invention, technical scheme and effect, below to further explain of the present invention.Should be appreciated that specific embodiment described herein only in order to explanation the present invention, and be not used in qualification the present invention.
Panorama parking assisting system of the present invention; Of Fig. 1; Comprise be arranged on all around the wide-angle imaging head 100 that is used to gather the peripheral vehicle image of car body, be used to proofread and correct and splice image that wide-angle imaging head 100 gathers with the panoramic picture generation module 200 that generates panoramic picture, be used for said panoramic picture is carried out the detection module 300 of obstacle identification and is used for the reminding module 400 according to the testing result output detection information of detection module, said wide-angle imaging head 100, panoramic picture generation module 200, detection module 300 and reminding module 400 electrically connect successively.Carry out detailed description in the face of each module among the present invention down.
Wide-angle imaging head 100 is arranged on car body all around in the present invention; Thereby promptly use the image that four wide-angle imaging heads 100 obtain the whole orientation of peripheral vehicle 360 degree; Specifically can be separately positioned on wide-angle imaging head 100 in grid position and the left and right side outside rear-view mirror of Vehicular body front be on the back door, to obtain best shooting effect, certainly if necessary; Some wide-angle imaging heads also can be set more; In case run into shooting blind angle amount, 8 wide-angle imaging heads for example are set, cover the image of all field ranges of peripheral vehicle; Let the clear vehicle-surroundings of checking of chaufeur whether have obstacle and understand the relative azimuth and the distance of obstacle, help the light parked vehicle of chaufeur.
Said panoramic picture generation module 200 is used for the image that wide-angle imaging head 100 is gathered is proofreaied and correct and spliced so that generate the panoramic picture of peripheral vehicle; Specifically; The vision signal that this wide-angle imaging head 100 can will comprise image is input in the panoramic picture generation module 200; 200 pairs of images of panoramic picture generation module carry out visual angle conversion and synthetic fusion treatment then; 4 road images are synthesized a birds-eye view directly over the complete car body, as for specifically how image being proofreaied and correct, spliced and can repeat no more with reference to prior art.
Core part of the present invention is that panoramic picture is carried out obstacle identification; Thereby judge whether vehicle-surroundings has obstacle, and will detect information indicating and give chaufeur, make things convenient for chaufeur directly to obtain detection information; Need not to carry out unnecessary work, alleviated the burden of chaufeur.Specifically describe below and how panoramic picture is carried out obstacle identification and output detection information.
In detection module 300, be provided with the image pattern storehouse, in this image pattern storehouse, store positive sample image that contains obstacle information and the negative sample image that does not contain obstacle information.In detection module, also be provided with the target classification device; This target classification device is to have utilized obstacle characteristic in the image pattern storehouse to train to obtain; After training is accomplished; The target classification device can to interesting areas in the panoramic picture for example obstacle discern detection, the target classification device is output as 1 when detecting obstacle, otherwise is output as 0; In order to detect the view picture panoramic picture, can be in panoramic picture the mobile search window, in order to detect the obstacles of different sizes, can carry out size to the target classification device and change, testing result will be truer like this.
Target classification device among the present invention is based on the embedded platform training and generates the target classification device, and the sorter model that draws through this training method can reach the purpose that reduces calculated amount.
In the present invention, said detection information is exported with image, literal or speech form.Obstacle can be people, animal or the Rigid Bodies of vehicle for example.
Said reminding module 400 comprises the display device for mounting on vehicle that is used to show detection information; When this detection information is presented at display device for mounting on vehicle with graphicform; Can obstacle be identified, utilize the sign frame that obstacle is identified, thus user friendly checking.Said display device for mounting on vehicle can make things convenient for the user to carry out freely selecting according to use habit and needs for one or more combinations in vehicle-mounted LCD display, OLED screen, LED screen, the video input display equipment.
Said reminding module 400 also comprises the speech play module that is used to play detection information; When this detection information is when exporting with speech form; Can in detection information, add the azimuth information of obstacle; Note the where is it obstacle thereby through the speech play module detection information is play the prompting driver again, this prompting mode has alleviated driver's burden, and is also convenient for users to use.Certainly, also can above-mentioned detection information be exported with one or more modes that combine of image, literal or voice, to reach the purpose of hommization more.
Based on said system, the present invention also provides a kind of implementation method of described panorama parking assisting system, and is as shown in Figure 2, may further comprise the steps:
S101, said wide-angle imaging head are gathered the image of peripheral vehicle;
The generation panoramic picture is proofreaied and correct, spliced to S102, said panoramic picture generation module to said image;
S103, said detection module carry out obstacle identification to said panoramic picture and obtain testing result;
S104, said reminding module are according to testing result output detection information.
In sum, panorama parking assisting system of the present invention and its implementation are through the image of wide-angle imaging head collection peripheral vehicle; The generation panoramic picture is proofreaied and correct, spliced to the panoramic picture generation module to said image; Detection module carries out obstacle identification to said panoramic picture and obtains testing result; Reminding module is according to testing result output detection information; The detection information accurate and effective that the present invention adopts multiple technologies to obtain; Can effectively judge the obstacle information of peripheral vehicle, make things convenient for the driving of parking of chaufeur to wait operation, improve the safety of driving; Cost of the present invention is low, device is simple, practical.
Should be understood that application of the present invention is not limited to above-mentioned giving an example, concerning those of ordinary skills, can improve or conversion that all these improvement and conversion all should belong to the protection domain of accompanying claims of the present invention according to above-mentioned explanation.