CN104512329A - Reversing safety auxiliary method, reversing safety auxiliary device and automobile - Google Patents
Reversing safety auxiliary method, reversing safety auxiliary device and automobile Download PDFInfo
- Publication number
- CN104512329A CN104512329A CN201310451913.0A CN201310451913A CN104512329A CN 104512329 A CN104512329 A CN 104512329A CN 201310451913 A CN201310451913 A CN 201310451913A CN 104512329 A CN104512329 A CN 104512329A
- Authority
- CN
- China
- Prior art keywords
- moving objects
- module
- image
- recorded
- moving
- 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.)
- Granted
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R1/00—Optical viewing arrangements; Real-time viewing arrangements for drivers or passengers using optical image capturing systems, e.g. cameras or video systems specially adapted for use in or on vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R2300/00—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle
- B60R2300/80—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement
- B60R2300/806—Details of viewing arrangements using cameras and displays, specially adapted for use in a vehicle characterised by the intended use of the viewing arrangement for aiding parking
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a reversing safety auxiliary method, a reversing safety auxiliary device and an automobile. The reversing safety auxiliary method comprises the following steps: collecting real-time videos about a reversing route through a camera arranged at the tail of the automobile; detecting a moving object in the real-time videos, and obtaining the shape size and the current position of the moving object; tracking the detected moving object, and obtaining the moving direction and the moving velocity of the moving object; carrying out early warning logic judgment according to the shape size, the current position, the moving direction and the moving velocity of the moving object; and warning or not according to the result of the early warning logic judgment. The method can be used for fast detecting the moving object which suddenly appears on the reversing route and warning in time, so that the safety during the reversing is improved.
Description
Technical field
The invention belongs to vehicle electric field and visual processes field, be specifically related to the safe householder method of a kind of reversing, reversing safety aid and automobile.
Background technology
Along with being on the increase of automobile, the wiping accident such as to touch produced because of reversing is also on the increase, particularly at crowded parking area and cross roads place, because back mirror exists very large blind area, suddenly the Moving Objects entering reversing route is difficult to make timely reaction, easily causes collision case.Therefore, detect the Moving Objects on reversing route in time, give warning in advance, user's time enough can to take measures to avoid accident.
Current reversing safety assisting system mainly contains two kinds: Reverse Sensor ancillary system and reverse image accessory system, and they can improve the safety of reversing to a certain extent, but still have significant limitation.The maximum detectable range of Reverse Sensor ancillary system is only about 2m, and this detection range cannot make timely early warning for Moving Objects close fast; In addition, Reverse Sensor accurately cannot detect the obstacle lower than probe installation location; And Reverse Sensor investigative range is limited, the obstacle of back mirror part blind area cannot be detected.Reverse image is only chaufeur and provides image reference, does not have warning function, and user cannot pay close attention to reverse image always.
Summary of the invention
The present invention one of is intended to solve the problems of the technologies described above at least to a certain extent or at least provides a kind of useful business to select.For this reason, first object of the present invention is to propose the safe householder method of reversing that a kind of monitoring range is comprehensive, disturbance rejection is strong, prediction accuracy is high.
According to the safe householder method of the reversing of the embodiment of the present invention, comprise the following steps: A. is by being placed in the real-time video on the camera collection vehicle backing route of the tailstock; B. in described real-time video, detect Moving Objects, obtain geomery and the current location of described Moving Objects; C. the described Moving Objects detected is followed the tracks of, obtain sense of motion and the movement rate of described Moving Objects; D. according to the described geomery of described Moving Objects, described current location, described sense of motion and described movement rate, early warning Logic judgment is carried out; And E. is according to the result of early warning Logic judgment, carry out reporting to the police or not reporting to the police.
According to the safe householder method of the reversing of the embodiment of the present invention, at least tool has the following advantages:
(1) adopt camera to monitor, can detect the object within the scope of 10m, and the maximum detectable range of Reverse Sensor is only about 2m, the present invention has the wider more fully advantage of monitoring range.
(2) detect in conjunction with inter-frame difference and background differential pair Moving Objects, can avoid the interference of the external factors such as illumination variation, target shadow, turbulent noise, can adapt to various scene changes, disturbance rejection is strong, prediction accuracy is high.
(3) adopt distribution projection algorithm to detect the current location of described Moving Objects, the image of two-dimensional space is transformed into the one-dimensional space by the mode of projection, and calculated amount reduces greatly, and data-handling efficiency is high, is applicable to Real-Time Monitoring.
(4) consider the characteristic information of the geomery of Moving Objects, current location, movement rate, sense of motion, judge whether to there is traffic safety hidden danger, and determine potential safety hazard grade, there is truly comprehensive, intelligentized advantage.
In addition, the safe householder method of reversing according to the above embodiment of the present invention can also have following additional technical characteristic:
In one embodiment of the invention, also to comprise: after described steps A, before described step B, Image semantic classification is carried out to described real-time video.
In one embodiment of the invention, described step B specifically comprises: B1. judges whether present frame is the first frame; If B2. present frame is the first frame, then using the source images of present frame as the background image of present frame, enter step B4; If B3. present frame is not the first frame, then adopts inter-frame difference and background subtraction phase-splitting associated methods to obtain the background image of present frame, enter step B4; B4. deduct the background image of present frame with the source images of present frame, obtain background subtraction partial image; B5. described background subtraction partial image is carried out to the image binaryzation of adaptive threshold, tell moving region and non-moving areas; B6. the background of described moving region is remained unchanged, replacement is carried out to the background of described non-moving areas and upgrades; And B7. adopts the Moving Objects in distribution projection algorithm acquisition moving region, and obtain geomery and the current location of described Moving Objects.
In one embodiment of the invention, the computing formula of the image binaryzation process of adaptive threshold described in described step B5 is:
Wherein α is adaptation coefficient and 0 < α < 1, and (i, j) represents the pixel of the i-th row jth row, b
tthe value of (i, j) in the background image that (i, j) is t present frame, b
t-1the value of (i, j) in the background image that (i, j) is former frame, f
tthe value of (i, j) in the source images that (i, j) is present frame, D
tthe binaryzation result of the background subtraction partial image that (i, j) is t.
In one embodiment of the invention, described step C specifically comprises: C1. provides current kinetic object set and recorded Moving Objects set, element in described current kinetic object set is by described Moving Objects that described step B detects in present frame, the described element having recorded Moving Objects set is initialized as sky in 0 moment, upgrades in following instant by performing step C3 and step C4; C2. recorded each element in Moving Objects set mated described with each element in described current kinetic object set one by one, if the match is successful, then the described geomery of described Moving Objects and described current location are upgraded, and mark these two elements for mate at described current kinetic object set and described record in Moving Objects set respectively; C3. Moving Objects set has been recorded described in scanning, if there is certain element not to be labeled and to mate, think that the described Moving Objects of haveing been friends in the past leaves the visual field, then by described element from described recorded Moving Objects set delete to upgrade described in recorded Moving Objects set; C4. described current kinetic object set is scanned, if there is certain element not to be labeled and to mate, then think and have new described Moving Objects to come into view, then recorded in Moving Objects set described in described element being added to and recorded Moving Objects set described in upgrading; And C5. repeats step C1 to C4, obtain the described of each moment and record Moving Objects set, the described current location in adjacent two moment of the described described Moving Objects recorded in Moving Objects set is compared, obtains the described sense of motion of described Moving Objects and described movement rate.
In one embodiment of the invention, while performing described step C, also comprise: the confidence level recording described Moving Objects, described confidence level is used for having recorded Moving Objects set described in auxiliary renewal, wherein, when continuous multiple frames image detection is to described Moving Objects, the described confidence level of described Moving Objects adds up gradually; When continuous multiple frames image detection is less than described Moving Objects, the described confidence level of described Moving Objects is successively decreased gradually.
For this reason, second object of the present invention is to propose the reversing safety aid that a kind of monitoring range is comprehensive, disturbance rejection is strong, prediction accuracy is high.
According to the reversing safety aid of the embodiment of the present invention, comprising: video acquisition module, described video acquisition module comprises the camera being placed in the tailstock, the real-time video on collection vehicle reversing route; Moving Objects detection module, described Moving Objects detection module is connected with described video acquisition module, for detecting Moving Objects in described real-time video, obtains geomery and the current location of described Moving Objects; Moving object tracking module, described moving object tracking module is connected with described Moving Objects detection module, for following the tracks of the described Moving Objects detected, obtains sense of motion and the movement rate of described Moving Objects; Early warning logic judgment module, described early warning logic judgment module is connected with described moving object tracking module, for the described geomery according to described Moving Objects, described current location, described sense of motion and described movement rate, carries out early warning Logic judgment; And annunciator, described annunciator is connected with described early warning logic judgment module, carries out reporting to the police or not reporting to the police according to the judged result of described early warning logic judgment module.
According to the reversing safety aid of the embodiment of the present invention, at least tool has the following advantages:
(1) video acquisition module adopts camera to monitor, can detect the object within the scope of 10m, and the maximum detectable range of Reverse Sensor is only about 2m, and the present invention has the wider more fully advantage of monitoring range.
(2) in Moving Objects detection module, detect in conjunction with inter-frame difference and background differential pair Moving Objects, can avoid the interference of the external factors such as illumination variation, target shadow, turbulent noise, can adapt to various scene changes, disturbance rejection is strong, prediction accuracy is high.
(3), in moving object tracking module, adopt distribution projection algorithm to detect the current location of described Moving Objects, the image of two-dimensional space is transformed into the one-dimensional space by the mode of projection, and calculated amount reduces greatly, and data-handling efficiency is high, is applicable to Real-Time Monitoring.
(4) consider the characteristic information of the geomery of Moving Objects, current location, movement rate, sense of motion, judge whether to there is traffic safety hidden danger, and determine potential safety hazard grade, there is truly comprehensive, intelligentized advantage.
In addition, the safe householder method of reversing according to the above embodiment of the present invention can also have following additional technical characteristic:
In one embodiment of the invention, also comprise: image pre-processing module, described image pre-processing module between described video acquisition module and the described Moving Objects detection module, for carrying out Image semantic classification to described real-time video.
In one embodiment of the invention, described Moving Objects detection module specifically comprises: background image acquisition module, wherein, if present frame is the first frame, described background image acquisition module is using the source images of present frame as the background image of present frame, if present frame is not the first frame, described background image acquisition module adopts inter-frame difference and background subtraction phase-splitting associated methods to obtain the background image of present frame; Background subtraction partial image acquisition module, described background subtraction partial image acquisition module is connected with described background image acquisition module, obtains background subtraction partial image for the background image source images of present frame being deducted present frame; Image binaryzation module, described image binaryzation module is connected with described background subtraction partial image acquisition module, for carrying out the image binaryzation of adaptive threshold to described background subtraction partial image, tells moving region and non-moving areas; Context update module, described context update module is connected with described image binaryzation module, for remaining unchanged to the background of described moving region, carrying out replacement upgrade the background of described non-moving areas; And size positions acquisition module, size positions acquisition module is connected with described image binaryzation module, for adopting the Moving Objects in distribution projection algorithm acquisition moving region, and obtains geomery and the current location of described Moving Objects.
In one embodiment of the invention, described in described image binaryzation module, the computing formula of the image binaryzation process of adaptive threshold is:
Wherein α is adaptation coefficient and 0 < α < 1, and (i, j) represents the pixel of the i-th row jth row, b
tthe value of (i, j) in the background image that (i, j) is t present frame, b
t-1the value of (i, j) in the background image that (i, j) is former frame, f
tthe value of (i, j) in the source images that (i, j) is present frame, D
tthe binaryzation result of the background subtraction partial image that (i, j) is t.
In one embodiment of the invention, described moving object tracking module specifically comprises: current kinetic object set internal memory, for storing current kinetic object set, the element in described current kinetic object set is by described Moving Objects that described Moving Objects detection module detects in present frame; Recorded Moving Objects set internal memory, recorded Moving Objects set for storing, the described element having recorded Moving Objects set is initialized as sky in 0 moment, constantly updates in following instant; Matching module, described matching module respectively with described current kinetic object set internal memory with record Moving Objects set internal memory and be connected, for having recorded each element in Moving Objects set mated described with each element in described current kinetic object set one by one, if the match is successful, then the described geomery of described Moving Objects and described current location are upgraded, and mark these two elements for mate at described current kinetic object set and described record in Moving Objects set respectively; Scan more new module, described scanning more new module respectively with described current kinetic object set internal memory with record Moving Objects set internal memory and be connected, for having recorded Moving Objects set upgraded described, wherein, described scanning upgrades described in module scans has recorded Moving Objects set, if there is certain element not to be labeled and to mate, think that the described Moving Objects of haveing been friends in the past leaves the visual field, then described scanning more new module by described element from described recorded Moving Objects set delete to upgrade described in recorded Moving Objects set; Current kinetic object set described in module scans is upgraded with described scanning, if there is certain element not to be labeled and to mate, then think and have new described Moving Objects to come into view, then described scanning the more just described element of new module add to described in recorded in Moving Objects set recorded Moving Objects set described in upgrading; And kinematic parameter acquisition module, be connected with the described Moving Objects set internal memory that recorded, described current location for adjacent two moment by the described described Moving Objects recorded in Moving Objects set compares, and obtains the described sense of motion of described Moving Objects and described movement rate.
In one embodiment of the invention, also comprise in described moving object tracking module: confidence level internal memory, described confidence level internal memory is for recording the confidence level of described Moving Objects, described confidence level is used for having recorded Moving Objects set described in auxiliary renewal, wherein, when continuous multiple frames image detection is to described Moving Objects, the described confidence level of described Moving Objects adds up gradually; When continuous multiple frames image detection is less than described Moving Objects, the described confidence level of described Moving Objects is successively decreased gradually.
For this reason, the 3rd object of the present invention is to propose the automobile that a kind of monitoring range is comprehensive, disturbance rejection is strong, prediction accuracy is high.
According to the automobile of the embodiment of the present invention, comprise above-mentioned any one the reversing safety aid disclosed of the present invention.
Automobile due to the embodiment of the present invention has the similar structure to the reversing safety aid of the embodiment of the present invention, therefore also has similar advantage.
Additional aspect of the present invention and advantage will part provide in the following description, and part will become obvious from the following description, or be recognized by practice of the present invention.
Accompanying drawing explanation
Above-mentioned and/or additional aspect of the present invention and advantage will become obvious and easy understand from accompanying drawing below combining to the description of embodiment, wherein:
Fig. 1 is the schematic flow sheet of the safe householder method of reversing of the embodiment of the present invention;
Fig. 2 is the Moving Objects testing process schematic flow sheet of the safe householder method of reversing of the embodiment of the present invention;
Fig. 3 is the moving object tracking process flow schematic diagram of the safe householder method of reversing of the embodiment of the present invention; With
Fig. 4 is the structured flowchart of the reversing safety aid of the embodiment of the present invention.
Detailed description of the invention
Be described below in detail embodiments of the invention, the example of described embodiment is shown in the drawings, and wherein same or similar label represents same or similar element or has element that is identical or similar functions from start to finish.Be exemplary below by the embodiment be described with reference to the drawings, be intended to for explaining the present invention, and can not limitation of the present invention be interpreted as.
As shown in Figure 1, the safe householder method of reversing of the embodiment of the present invention, specifically can comprise the steps:
A. by being placed in the real-time video on the camera collection vehicle backing route of the tailstock.
Particularly: taken the situation on vehicle backing route by the camera being placed in tail of body, the effective resolution of camera is 640 × 480, and frame per second is 30 frames/second.Because camera installation site and angle directly can affect shooting area, misoperation then likely produces blind area, and therefore this installation process is rather important.Concrete installation site and angle different according to different vehicles and vehicle body size, preferably, camera installation direction adopt obliquely tilt install, real time status on vehicle backing route can be obtained preferably like this.
Preferably, after completing above-mentioned steps A, need real-time video and carry out Image semantic classification.Particularly: after having gathered real-time video, by Video Decoder, the analog signal that camera inputs need be decoded as the digital video of YUV, complete A/D and change and input dsp chip, DSP passes through PPI interface by Image Saving.DSP gathers and after preserving image, utilizes the Gaussian filter of 3 × 3 to carry out image denoising and level and smooth pretreatment, improve picture quality.
B. in real-time video, detect Moving Objects, obtain geomery and the current location of Moving Objects.
Moving Objects detection technique is exactly the region of motion change in sequence of video images is on a frame-by-frame basis detected separate, and removes the impact of background image thus finds interested target prospect part.In actual environment, the interference due to external factors such as illumination variation, target shadow, turbulent noises makes the accurate detection of Moving Objects become quite difficulty.The testing process composition graphs 2 of the Moving Objects of the present embodiment, specifically can comprise the steps:
B1. judge whether present frame is the first frame.
If B2. present frame is the first frame, then using the source images of present frame as the background image of present frame, enter step B4.
Particularly, remember then there be Back (t)=SourceImage (t), t=0 by the moment t=0 that the first frame is corresponding.Wherein Back (t) represents the background image of t present frame (i.e. t+1 frame), and SourceImage (t) represents the source images of t present frame.
If B3. present frame is not the first frame, then adopts inter-frame difference and background subtraction phase-splitting associated methods to obtain the background image of present frame, enter step B4.
Traditional background difference algorithm detects the initial model of the aviation value image as a setting choosing the first frame or former frame at the beginning at Moving Objects, but contain Moving Objects in initial frame, this is obviously inaccurate, can cause having a strong impact on when context update speed is very slow in subsequent treatment to detection.Therefore the present embodiment adopts inter-frame difference and background subtraction to divide to combine, and to improve accuracy, specific formula for calculation is as follows:
As can be seen from the above equation, when SourceImage (t)-Back (t-1) difference is less, Back(t) almost with Back(t+1) equal.This means that the method has the characteristic of low pass, Moving Objects is regarded as random noise, carried out the acquisition of background image, algorithm complex is low.It can also be seen that from above formula, when t becomes large, 1/t reduce gradually latter half is negligible with the formula, computation speed is fast, operand reduces, thus can meet the real-time of object detection.
B4. deduct the background image of present frame with the source images of present frame, obtain background subtraction partial image.
Particularly, in t, in the source images of note present frame, (i, j) picture element point chromatic value is f
t(i, j), in the background image of present frame, (i, j) picture element point chromatic value is b
t(i, j), then in the background subtraction partial image of present frame, (i, j) picture element point chromatic value is d
t(i, j)=f
t(i, j)-b
t(i, j).
B5. background subtraction partial image is carried out to the image binaryzation of adaptive threshold, tell moving region and non-moving areas.
Particularly, the computing formula of image binaryzation is:
after binaryzation value be 1 region mean that the source images of present frame and background image differ greatly, belong to moving region; After binaryzation value be 0 region mean the source images of present frame and background image difference less, belong to non-moving areas.
It should be noted that, in non-moving areas, the fine difference of source images and background image causes due to camera visual angle change in reversing process, and position motion slowly also can occur such as one tree in back-up video, and it belongs to non-moving areas.In moving region, differing greatly in source images and background image, this difference is the relative motion that in reversing process, camera visual angle change causes on the one hand, the absolute motion due to Moving Objects itself on the other hand, such as there is visibility point motion in a doggie darted in back-up video, and it belongs to moving region.
It should be noted that, T is the binary-state threshold after current source picture and current background calculus of differences.After difference, the noise distribution of image is very large and have the identical characteristics of Gaussian distribution, and Moving Objects region does not possess this characteristic, the average, the standard deviation that therefore pass through calculating difference image can obtain the average of corresponding noise distribution, the estimated valve of standard deviation.According to probability statistics principle, the change variable of Gaussian distribution meets 3 δ principles, therefore the threshold value T utilizing 3 δ principles to try to achieve carries out binary conversion treatment and can realize at utmost suppressing the noise of difference image, thus greatly reduces the interference of noise, determines moving region.
B6. the background of moving region is remained unchanged, replacement is carried out to the background of non-moving areas and upgrades.
The computing formula of this step can be:
Wherein α is adaptation coefficient and 0 < α < 1.Other symbols are existing lexical or textual analysis hereinbefore, and wherein (i, j) represents the pixel of the i-th row jth row, b
tthe value of (i, j) in the background image that (i, j) is t present frame, b
t-1the value of (i, j) in the background image that (i, j) is former frame, f
tthe value of (i, j) in the source images that (i, j) is present frame, D
tthe binaryzation result of the background subtraction partial image that (i, j) is t.
Step B6 does further context update on the basis of step B3 to context update.If only rely on the background update method that step B3 describes, along with the increase of t, background model tends towards stability.And in practical application, be engraved in during movement background along with vehicle and change, need to upgrade non-moving areas background.By the method that step B6 describes, the background of non-moving areas can be upgraded the moment, and do not affect the detection of Moving Objects.
B7. adopt the Moving Objects in distribution projection algorithm acquisition moving region, and obtain geomery and the current location of Moving Objects.
Substep projection algorithm refers to, first vertical projection is done to image, each Moving Objects can produce corresponding crest in projection result, therefore can detect the number of Moving Objects and the horizontal boundary of each Moving Objects in image of interest region by vertical projection.Then in its horizontal boundary, do horizontal projection to each Moving Objects respectively, its projection result can the vertical border of each Moving Objects of accurate response, thus detects the boundary position of each Moving Objects, determines geomery and the current location of Moving Objects.The image of two-dimensional space is transformed into the one-dimensional space by the mode of distribution projection, and data volume greatly reduces, and is applicable to the real-time detection of embedded system.
C. the Moving Objects detected is followed the tracks of, obtain sense of motion and the movement rate of Moving Objects.
Carry out tracking to Moving Objects to refer to: between continuous print picture frame, create the features relevant such as position-based, size, speed, direction Corresponding matching and record Moving Objects path of motion in the video sequence.As shown in Figure 3, step C specifically can comprise the steps:
C1., current kinetic object set is provided and has recorded Moving Objects set, element in current kinetic object set is by Moving Objects that step B detects in present frame, the element having recorded Moving Objects set is initialized as sky in 0 moment, upgrades in following instant by performing step C3 and step C4.
C2. mate recording each element in Moving Objects set with each element in current kinetic object set one by one, if the match is successful, then the geomery of Moving Objects and current location are upgraded, and respectively at current kinetic object set with recorded in Moving Objects set and mark these two elements for mate.
C3. scan and recorded Moving Objects set, be not labeled mate if there is certain element, think that the Moving Objects of haveing been friends in the past leaves the visual field, then element has been recorded Moving Objects set from recording Moving Objects set to delete to upgrade.
C4. scan current kinetic object set, be not labeled mate if there is certain element, then think and have new Moving Objects to come into view, then element is added to record in Moving Objects set and recorded Moving Objects set to upgrade.
It should be noted that, step C3 and step C4 can with successively, rear first or order carries out simultaneously.
C5. repeat C1 to C4, obtain the Moving Objects of the record set in each moment, the current location in adjacent two moment of the Moving Objects recorded in Moving Objects set is compared, obtain sense of motion and the movement rate of Moving Objects.
Above-mentioned moving object tracking method it be the moving object tracking method of feature based, accuracy is higher, has certain noise immunity.
According to an example of the present invention, while performing step C, also comprise: the confidence level of record Moving Objects, confidence level is used for auxiliary renewal and has recorded Moving Objects set.Wherein, when continuous multiple frames image detection is to Moving Objects, the confidence level of Moving Objects adds up gradually; When continuous multiple frames image detection is less than Moving Objects, the confidence level of Moving Objects is successively decreased gradually.After Moving Objects has confidence level parameter, just can with reference to this confidence level when performing step C3.Such as, Moving Objects set has been recorded in scanning, there is certain element and not being labeled and mating (a certain element unmarked coupling first recorded in Moving Objects set namely being detected) in Late Cambrian, means and follow the tracks of first with losing Moving Objects corresponding to this element.Now actual conditions may not be that this Moving Objects thoroughly disappears in the visual field, are also likely errors.Therefore should not deleting this element at once, but reduce the confidence level of this element, until when confidence level is less than believability threshold, just think that Moving Objects really leaves, just element being deleted from recording Moving Objects set.Assisting by means of confidence level, makes the tracking results of the present embodiment truer more accurate.
D. according to the geomery of Moving Objects, current location, sense of motion and movement rate, early warning Logic judgment is carried out.
First, the information such as the geomery of the Moving Objects obtained according to above-mentioned steps B and step C, current location, sense of motion and movement rate, the path of motion of the following Moving Objects in a short time of prediction.Then, whether comprehensive descision exists traffic safety hidden danger, and determines potential safety hazard grade.Such as, predict that certain Moving Objects volume is comparatively large, its with the relative velocity of vehicle is comparatively large and it is less than secure threshold with the relative distance of vehicle, then mean and in the future acutely collision occur possibly, now judge that this situation is severe compromise.Again such as, predict certain Moving Objects small volume, the relative velocity of itself and vehicle is less, and the relative distance of itself and vehicle is slightly larger than secure threshold, then mean and likely slight collision can occur in the future, now judge that this situation is common potential safety hazard.Those skilled in the art can realize step D neatly according to actual conditions.
E. carry out reporting to the police or not reporting to the police according to the result of early warning Logic judgment.
Warning can adopt the combination of both audible alarm, photoelectric alarm, audible alarm and photoelectric alarm, or other forms, warns user.
According to the safe householder method of the reversing of the embodiment of the present invention, at least tool has the following advantages:
(1) adopt camera to monitor, can detect the object within the scope of 10m, and the maximum detectable range of Reverse Sensor is only about 2m, the present invention has the wider more fully advantage of monitoring range.
(2) detect in conjunction with inter-frame difference and background differential pair Moving Objects, can avoid the interference of the external factors such as illumination variation, target shadow, turbulent noise, can adapt to various scene changes, disturbance rejection is strong, prediction accuracy is high.
(3) adopt distribution projection algorithm to detect current location and the position of Moving Objects, the image of two-dimensional space is transformed into the one-dimensional space by the mode of projection, and calculated amount reduces greatly, and data-handling efficiency is high, is applicable to Real-Time Monitoring.
(4) between continuous print picture frame, Corresponding matching and the record Moving Objects path of motion in the video sequence of the features relevant such as position-based, size, speed, direction is created by moving object tracking algorithm, accuracy is high, has certain noise immunity.
(5) consider the characteristic information of the geomery of Moving Objects, current location, movement rate, sense of motion, judge whether to there is traffic safety hidden danger, and determine potential safety hazard grade, there is truly comprehensive, intelligentized advantage.
The present invention proposes a kind of reversing safety aid, as shown in Figure 4, can comprise: video acquisition module 100, Moving Objects detection module 200, moving object tracking module 300 and early warning logic judgment module 400.Video acquisition module 100 comprises the camera being placed in the tailstock, for obtaining the real-time video on vehicle backing route.Moving Objects detection module 200 is connected with video acquisition module 100, for detecting Moving Objects in real-time video, obtains geomery and the current location of Moving Objects.Moving object tracking module 300 is connected with Moving Objects detection module 200, for following the tracks of the Moving Objects detected, obtains sense of motion and the movement rate of Moving Objects.Early warning logic judgment module 400 is connected with moving object tracking module 300, for the geomery according to Moving Objects, current location, sense of motion and movement rate, carries out early warning Logic judgment.Annunciator 500 is connected with early warning logic judgment module 400, carries out reporting to the police or not reporting to the police according to the judged result of early warning logic judgment module 400.
According to an example of the present invention, reversing safety aid can also comprise: image pre-processing module 600.This image pre-processing module 600 between video acquisition module 100 and Moving Objects detection module 200, for carrying out Image semantic classification to the real-time video collected.
According to an example of the present invention, Moving Objects detection module 200 specifically can comprise background image acquisition module, background subtraction partial image acquisition module, image binaryzation module, context update module and size positions acquisition module.In background image acquisition module, if present frame is the first frame, background image acquisition module is using the source images of present frame as the background image of present frame, if present frame is not the first frame, background image acquisition module adopts inter-frame difference and background subtraction phase-splitting associated methods to obtain the background image of present frame.Background subtraction partial image acquisition module is connected with background image acquisition module, obtains background subtraction partial image for the background image source images of present frame being deducted present frame.Image binaryzation module is connected with background subtraction partial image acquisition module, for carrying out the image binaryzation of adaptive threshold to background subtraction partial image, tells moving region and non-moving areas.Context update module is connected with image binaryzation module, for remaining unchanged to the background of moving region, carrying out replacement upgrade the background of non-moving areas.Size positions acquisition module is connected with image binaryzation module, for adopting the Moving Objects in distribution projection algorithm acquisition moving region, and obtains geomery and the current location of Moving Objects.
According to an example of the present invention, in image binaryzation module, the computing formula of the image binaryzation process of adaptive threshold can be:
Wherein α is adaptation coefficient and 0 < α < 1, and (i, j) represents the pixel of the i-th row jth row, b
tthe value of (i, j) in the background image that (i, j) is t present frame, b
t-1the value of (i, j) in the background image that (i, j) is former frame, f
tthe value of (i, j) in the source images that (i, j) is present frame, D
tthe binaryzation result of the background subtraction partial image that (i, j) is t.
According to an example of the present invention, moving object tracking module 300 specifically can comprise: current kinetic object set internal memory, record Moving Objects set internal memory, matching module, scan more new module and kinematic parameter acquisition module.Current kinetic object set internal memory is for storing current kinetic object set.Element in current kinetic object set is by Moving Objects that Moving Objects detection module detects in present frame.Record Moving Objects set internal memory and record Moving Objects set for storing.The element having recorded Moving Objects set is initialized as sky in 0 moment, constantly updates in following instant.Matching module respectively with current kinetic object set internal memory with record Moving Objects set internal memory and be connected, for mating recording each element in Moving Objects set with each element in current kinetic object set one by one.If the match is successful, then the geomery of Moving Objects and current location are upgraded, and respectively at current kinetic object set with recorded in Moving Objects set and mark these two elements for mate.Scan more new module respectively with current kinetic object set internal memory with record Moving Objects set internal memory and be connected, for upgrading recording Moving Objects set.This renewal process in two kinds of situation, the first situation, scanning upgrades module scans and has recorded Moving Objects set, if there is certain element not to be labeled and to mate, think that the Moving Objects of haveing been friends in the past leaves the visual field, then scan more new module and element has been recorded Moving Objects set from recording Moving Objects set to delete to upgrade.The second situation, scanning upgrades module scans current kinetic object set, if there is certain element not to be labeled and to mate, then think and have new Moving Objects to come into view, then scan more new module just element add to record in Moving Objects set and recorded Moving Objects set to upgrade.Kinematic parameter acquisition module with record Moving Objects set internal memory and be connected, the current location for adjacent two moment by the Moving Objects recorded in Moving Objects set compares, and obtains sense of motion and the movement rate of Moving Objects.
According to an example of the present invention, can also comprise in moving object tracking module 300: confidence level internal memory.This confidence level internal memory is for recording the confidence level of Moving Objects, and confidence level is used for auxiliary renewal and has recorded Moving Objects set.When continuous multiple frames image detection is to Moving Objects, the confidence level of Moving Objects adds up gradually; When continuous multiple frames image detection is less than Moving Objects, the confidence level of Moving Objects is successively decreased gradually.When scan more new module to record Moving Objects set carry out the renewal of the first situation time, can with reference to confidence level.Such as, scan more new module and a certain element unmarked coupling first recorded in Moving Objects set detected, namely mean and follow the tracks of first with losing Moving Objects corresponding to this element.Now actual conditions may not be that this Moving Objects thoroughly disappears in the visual field, are also likely errors.Therefore should not deleting this element at once, but reduce the confidence level of this element, until when confidence level is less than believability threshold, just think that Moving Objects really leaves, just element being deleted from recording Moving Objects set.Assisting by means of confidence level, makes tracking results of the present invention truer more accurate.
The reversing safety aid of the embodiment of the present invention, the Moving Objects appeared at suddenly in reversing process on reversing route detects, and give warning in advance guarantee safety.
According to the reversing safety aid of the embodiment of the present invention, at least tool has the following advantages:
(1) adopt camera to monitor, can detect the object within the scope of 10m, and the maximum detectable range of Reverse Sensor is only about 2m, the present invention has the wider more fully advantage of monitoring range.
(2) detect in conjunction with inter-frame difference and background differential pair Moving Objects, can avoid the interference of the external factors such as illumination variation, target shadow, turbulent noise, can adapt to various scene changes, disturbance rejection is strong, prediction accuracy is high.
(3) adopt distribution projection algorithm to detect current location and the position of Moving Objects, the image of two-dimensional space is transformed into the one-dimensional space by the mode of projection, and calculated amount reduces greatly, and data-handling efficiency is high, is applicable to Real-Time Monitoring.
(4) between continuous print picture frame, Corresponding matching and the record Moving Objects path of motion in the video sequence of the features relevant such as position-based, size, speed, direction is created by moving object tracking algorithm, accuracy is high, has certain noise immunity.
(5) consider the characteristic information of the geomery of Moving Objects, current location, movement rate, sense of motion, judge whether to there is traffic safety hidden danger, and determine potential safety hazard grade, there is truly comprehensive, intelligentized advantage.
The present invention also proposes the automobile that a kind of monitoring range is comprehensive, disturbance rejection is strong, prediction accuracy is high.According to the automobile of the embodiment of the present invention, comprise above-mentioned any one the reversing safety aid disclosed of the present invention.
Automobile due to the embodiment of the present invention has the similar structure to the reversing safety aid of the embodiment of the present invention, therefore also has similar advantage.
Describe and can be understood in diagram of circuit or in this any process otherwise described or method, represent and comprise one or more for realizing the module of the code of the executable instruction of the step of specific logical function or process, fragment or part, and the scope of the preferred embodiment of the present invention comprises other realization, wherein can not according to order that is shown or that discuss, comprise according to involved function by the mode while of basic or by contrary order, carry out n-back test, this should understand by embodiments of the invention person of ordinary skill in the field.
In the description of this specification sheets, specific features, structure, material or feature that the description of reference term " embodiment ", " some embodiments ", " example ", " concrete example " or " some examples " etc. means to describe in conjunction with this embodiment or example are contained at least one embodiment of the present invention or example.In this manual, identical embodiment or example are not necessarily referred to the schematic representation of above-mentioned term.And the specific features of description, structure, material or feature can combine in an appropriate manner in any one or more embodiment or example.
Although illustrate and describe embodiments of the invention above, be understandable that, above-described embodiment is exemplary, can not be interpreted as limitation of the present invention, those of ordinary skill in the art can change above-described embodiment within the scope of the invention when not departing from principle of the present invention and aim, revising, replacing and modification.
Claims (13)
1. the safe householder method of reversing, is characterized in that, comprise the following steps:
A. by being placed in the real-time video on the camera collection vehicle backing route of the tailstock;
B. in described real-time video, detect Moving Objects, obtain geomery and the current location of described Moving Objects;
C. the described Moving Objects detected is followed the tracks of, obtain sense of motion and the movement rate of described Moving Objects;
D. according to the described geomery of described Moving Objects, described current location, described sense of motion and described movement rate, early warning Logic judgment is carried out; And
E. according to the result of described early warning Logic judgment, carry out reporting to the police or not reporting to the police.
2. the safe householder method of reversing according to claim 1, is characterized in that, also comprise: after described steps A, before described step B, carries out Image semantic classification to described real-time video.
3. the safe householder method of reversing according to claim 1 and 2, is characterized in that, described step B specifically comprises:
B1. judge whether present frame is the first frame;
If B2. present frame is the first frame, then using the source images of present frame as the background image of present frame, enter step B4;
If B3. present frame is not the first frame, then adopts inter-frame difference and background subtraction phase-splitting associated methods to obtain the background image of present frame, enter step B4;
B4. deduct the background image of present frame with the source images of present frame, obtain background subtraction partial image;
B5. described background subtraction partial image is carried out to the image binaryzation of adaptive threshold, tell moving region and non-moving areas;
B6. the background of described moving region is remained unchanged, replacement is carried out to the background of described non-moving areas and upgrades; And
B7. adopt the Moving Objects in distribution projection algorithm acquisition moving region, and obtain geomery and the current location of described Moving Objects.
4. the safe householder method of reversing according to claim 3, is characterized in that, the computing formula of the image binaryzation process of adaptive threshold described in described step B5 is:
Wherein α is adaptation coefficient and 0 < α < 1, and (i, j) represents the pixel of the i-th row jth row, b
tthe value of (i, j) in the background image that (i, j) is t present frame, b
t-1 (i, j) be the value of (i, j) in the background image of former frame, f
tthe value of (i, j) in the source images that (i, j) is present frame, D
tthe binaryzation result of the background subtraction partial image that (i, j) is t.
5. the safe householder method of reversing according to claim 1, is characterized in that, described step C specifically comprises:
C1., current kinetic object set is provided and has recorded Moving Objects set, element in described current kinetic object set is by described Moving Objects that described step B detects in present frame, the described element having recorded Moving Objects set is initialized as sky in 0 moment, upgrades in following instant by performing step C3 and step C4;
C2. recorded each element in Moving Objects set mated described with each element in described current kinetic object set one by one, if the match is successful, then the described geomery of described Moving Objects and described current location are upgraded, and mark these two elements for mate at described current kinetic object set and described record in Moving Objects set respectively;
C3. Moving Objects set has been recorded described in scanning, if there is certain element not to be labeled and to mate, think that the described Moving Objects of haveing been friends in the past leaves the visual field, then by described element from described recorded Moving Objects set delete to upgrade described in recorded Moving Objects set;
C4. described current kinetic object set is scanned, if there is certain element not to be labeled and to mate, then think and have new described Moving Objects to come into view, then recorded in Moving Objects set described in described element being added to and recorded Moving Objects set described in upgrading; And
C5. step C1 to C4 is repeated, obtain the described of each moment and record Moving Objects set, the described current location in adjacent two moment of the described described Moving Objects recorded in Moving Objects set is compared, obtains the described sense of motion of described Moving Objects and described movement rate.
6. the safe householder method of reversing according to claim 1, is characterized in that, while performing described step C, also comprises: the confidence level recording described Moving Objects, and described confidence level is used for having recorded Moving Objects set described in auxiliary renewal, wherein,
When continuous multiple frames image detection is to described Moving Objects, the described confidence level of described Moving Objects adds up gradually;
When continuous multiple frames image detection is less than described Moving Objects, the described confidence level of described Moving Objects is successively decreased gradually.
7. a reversing safety aid, is characterized in that, comprising:
Video acquisition module, described video acquisition module comprises the camera being placed in the tailstock, the real-time video of described video acquisition module on collection vehicle reversing route;
Moving Objects detection module, described Moving Objects detection module is connected with described video acquisition module, for detecting Moving Objects in described real-time video, obtains geomery and the current location of described Moving Objects;
Moving object tracking module, described moving object tracking module is connected with described Moving Objects detection module, for following the tracks of the described Moving Objects detected, obtains sense of motion and the movement rate of described Moving Objects;
Early warning logic judgment module, described early warning logic judgment module is connected with described moving object tracking module, for the described geomery according to described Moving Objects, described current location, described sense of motion and described movement rate, carries out early warning Logic judgment; And
Annunciator, described annunciator is connected with described early warning logic judgment module, carries out reporting to the police or not reporting to the police according to the judged result of described early warning logic judgment module.
8. reversing safety aid according to claim 7, it is characterized in that, also comprise: image pre-processing module, described image pre-processing module between described video acquisition module and the described Moving Objects detection module, for carrying out Image semantic classification to described real-time video.
9. the reversing safety aid according to claim 7 or 8, is characterized in that, described Moving Objects detection module specifically comprises:
Background image acquisition module, wherein, if present frame is the first frame, described background image acquisition module is using the source images of present frame as the background image of present frame, if present frame is not the first frame, described background image acquisition module adopts inter-frame difference and background subtraction phase-splitting associated methods to obtain the background image of present frame;
Background subtraction partial image acquisition module, described background subtraction partial image acquisition module is connected with described background image acquisition module, obtains background subtraction partial image for the background image source images of present frame being deducted present frame;
Image binaryzation module, described image binaryzation module is connected with described background subtraction partial image acquisition module, for carrying out the image binaryzation of adaptive threshold to described background subtraction partial image, tells moving region and non-moving areas;
Context update module, described context update module is connected with described image binaryzation module, for remaining unchanged to the background of described moving region, carrying out replacement upgrade the background of described non-moving areas; And
Size positions acquisition module, size positions acquisition module is connected with described image binaryzation module, for adopting the Moving Objects in distribution projection algorithm acquisition moving region, and obtains geomery and the current location of described Moving Objects.
10. reversing safety aid according to claim 9, is characterized in that, described in described image binaryzation module, the computing formula of the image binaryzation process of adaptive threshold is:
Wherein α is adaptation coefficient and 0 < α < 1, and (i, j) represents the pixel of the i-th row jth row, b
tthe value of (i, j) in the background image that (i, j) is t present frame, b
t-1the value of (i, j) in the background image that (i, j) is former frame, f
tthe value of (i, j) in the source images that (i, j) is present frame, D
tthe binaryzation result of the background subtraction partial image that (i, j) is t.
11. reversing safety aids according to claim 7, is characterized in that, described moving object tracking module specifically comprises:
Current kinetic object set internal memory, for storing current kinetic object set, the element in described current kinetic object set is by described Moving Objects that described Moving Objects detection module detects in present frame;
Recorded Moving Objects set internal memory, recorded Moving Objects set for storing, the described element having recorded Moving Objects set is initialized as sky in 0 moment, constantly updates in following instant;
Matching module, described matching module respectively with described current kinetic object set internal memory with record Moving Objects set internal memory and be connected, for having recorded each element in Moving Objects set mated described with each element in described current kinetic object set one by one, if the match is successful, then the described geomery of described Moving Objects and described current location are upgraded, and mark these two elements for mate at described current kinetic object set and described record in Moving Objects set respectively;
Scan more new module, described scanning more new module respectively with described current kinetic object set internal memory with record Moving Objects set internal memory and be connected, for having recorded Moving Objects set upgrade described, wherein,
Described scanning upgrades described in module scans has recorded Moving Objects set, if there is certain element not to be labeled and to mate, think that the described Moving Objects of haveing been friends in the past leaves the visual field, then described scanning more new module by described element from described recorded Moving Objects set delete to upgrade described in recorded Moving Objects set; With
Described scanning upgrades current kinetic object set described in module scans, if there is certain element not to be labeled and to mate, then think and have new described Moving Objects to come into view, then described scanning the more just described element of new module add to described in recorded in Moving Objects set recorded Moving Objects set described in upgrading; And
Kinematic parameter acquisition module, be connected with the described Moving Objects set internal memory that recorded, described current location for adjacent two moment by the described described Moving Objects recorded in Moving Objects set compares, and obtains the described sense of motion of described Moving Objects and described movement rate.
12. reversing safety aids according to claim 7, it is characterized in that, also comprise in described moving object tracking module: confidence level internal memory, described confidence level internal memory is for recording the confidence level of described Moving Objects, described confidence level is used for having recorded Moving Objects set described in auxiliary renewal, wherein
When continuous multiple frames image detection is to described Moving Objects, the described confidence level of described Moving Objects adds up gradually;
When continuous multiple frames image detection is less than described Moving Objects, the described confidence level of described Moving Objects is successively decreased gradually.
13. 1 kinds of automobiles, is characterized in that, comprise the reversing safety aid according to any one of claim 7-9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310451913.0A CN104512329B (en) | 2013-09-27 | 2013-09-27 | Move backward safe householder methods, device and automobile |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201310451913.0A CN104512329B (en) | 2013-09-27 | 2013-09-27 | Move backward safe householder methods, device and automobile |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104512329A true CN104512329A (en) | 2015-04-15 |
CN104512329B CN104512329B (en) | 2017-04-05 |
Family
ID=52788373
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201310451913.0A Active CN104512329B (en) | 2013-09-27 | 2013-09-27 | Move backward safe householder methods, device and automobile |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104512329B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105946718A (en) * | 2016-06-08 | 2016-09-21 | 深圳芯智汇科技有限公司 | Vehicle-mounted terminal and reversing image toggle display method thereof |
CN106608221A (en) * | 2015-10-26 | 2017-05-03 | 比亚迪股份有限公司 | Vehicle blind area detecting system and method |
CN107644528A (en) * | 2017-08-02 | 2018-01-30 | 浙江工业大学 | A kind of vehicle queue length detection method based on vehicle tracking |
CN108297794A (en) * | 2018-01-11 | 2018-07-20 | 阿尔派株式会社 | Parking assistance system and traveling line of prediction display methods |
CN109145805A (en) * | 2018-08-15 | 2019-01-04 | 深圳市豪恩汽车电子装备股份有限公司 | Moving target detection method and system under vehicle-mounted environment |
CN109243150A (en) * | 2018-09-30 | 2019-01-18 | 深圳市金豪泰科技有限公司 | A kind of vehicle early warning method and terminal |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004114879A (en) * | 2002-09-27 | 2004-04-15 | Clarion Co Ltd | Parking assisting device, and image display device |
CN101175972A (en) * | 2005-05-19 | 2008-05-07 | 罗伯特·博世有限公司 | Driver assistance method |
CN101256073A (en) * | 2007-02-28 | 2008-09-03 | 三洋电机株式会社 | Apparatus and method for monitoring a vehicle's surroundings |
CN101303735A (en) * | 2007-05-03 | 2008-11-12 | 索尼德国有限责任公司 | Method for detecting moving objects in a blind spot region of a vehicle and blind spot detection device |
CN102442311A (en) * | 2010-10-06 | 2012-05-09 | 罗伯特·博世有限公司 | Method and device for determining processed image data about a sourround field of a vehicle |
CN102774325A (en) * | 2012-07-31 | 2012-11-14 | 西安交通大学 | Rearview reversing auxiliary system and method for forming rearview obstacle images |
CN103150748A (en) * | 2013-03-18 | 2013-06-12 | 大连慈航电子有限公司 | Reversing image three-dimensional (3D) scene reconstruction method and system |
-
2013
- 2013-09-27 CN CN201310451913.0A patent/CN104512329B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004114879A (en) * | 2002-09-27 | 2004-04-15 | Clarion Co Ltd | Parking assisting device, and image display device |
CN101175972A (en) * | 2005-05-19 | 2008-05-07 | 罗伯特·博世有限公司 | Driver assistance method |
CN101256073A (en) * | 2007-02-28 | 2008-09-03 | 三洋电机株式会社 | Apparatus and method for monitoring a vehicle's surroundings |
CN101303735A (en) * | 2007-05-03 | 2008-11-12 | 索尼德国有限责任公司 | Method for detecting moving objects in a blind spot region of a vehicle and blind spot detection device |
CN102442311A (en) * | 2010-10-06 | 2012-05-09 | 罗伯特·博世有限公司 | Method and device for determining processed image data about a sourround field of a vehicle |
CN102774325A (en) * | 2012-07-31 | 2012-11-14 | 西安交通大学 | Rearview reversing auxiliary system and method for forming rearview obstacle images |
CN103150748A (en) * | 2013-03-18 | 2013-06-12 | 大连慈航电子有限公司 | Reversing image three-dimensional (3D) scene reconstruction method and system |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106608221A (en) * | 2015-10-26 | 2017-05-03 | 比亚迪股份有限公司 | Vehicle blind area detecting system and method |
CN106608221B (en) * | 2015-10-26 | 2019-06-25 | 比亚迪股份有限公司 | The detection system and method for vehicle blind zone |
CN105946718A (en) * | 2016-06-08 | 2016-09-21 | 深圳芯智汇科技有限公司 | Vehicle-mounted terminal and reversing image toggle display method thereof |
CN107644528A (en) * | 2017-08-02 | 2018-01-30 | 浙江工业大学 | A kind of vehicle queue length detection method based on vehicle tracking |
CN108297794A (en) * | 2018-01-11 | 2018-07-20 | 阿尔派株式会社 | Parking assistance system and traveling line of prediction display methods |
CN109145805A (en) * | 2018-08-15 | 2019-01-04 | 深圳市豪恩汽车电子装备股份有限公司 | Moving target detection method and system under vehicle-mounted environment |
CN109243150A (en) * | 2018-09-30 | 2019-01-18 | 深圳市金豪泰科技有限公司 | A kind of vehicle early warning method and terminal |
Also Published As
Publication number | Publication date |
---|---|
CN104512329B (en) | 2017-04-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Chen et al. | Lane departure warning systems and lane line detection methods based on image processing and semantic segmentation: A review | |
CN100440269C (en) | Intelligent detecting prewarning method for expressway automobile running and prewaring system thereof | |
CN104512329A (en) | Reversing safety auxiliary method, reversing safety auxiliary device and automobile | |
EP2118818B1 (en) | Video-based road departure warning | |
CN106647776B (en) | Method and device for judging lane changing trend of vehicle and computer storage medium | |
WO2019026785A1 (en) | Attached object detection device, and vehicle system provided with same | |
US10814815B1 (en) | System for determining occurrence of an automobile accident and characterizing the accident | |
US20140348390A1 (en) | Method and apparatus for detecting traffic monitoring video | |
CN106096525A (en) | A kind of compound lane recognition system and method | |
CN102982304B (en) | Utilize polarized light image to detect the method and system of vehicle location | |
CN101576952B (en) | Method and device for detecting static targets | |
Aytekin et al. | Increasing driving safety with a multiple vehicle detection and tracking system using ongoing vehicle shadow information | |
CN104657735A (en) | Lane line detection method and system, as well as lane departure early warning method and system | |
Liu et al. | Development of a vision-based driver assistance system with lane departure warning and forward collision warning functions | |
CN110544211A (en) | method, system, terminal and storage medium for detecting lens attachment | |
CN201402413Y (en) | Vehicle control assistant device | |
CN104463903A (en) | Pedestrian image real-time detection method based on target behavior analysis | |
CN104881645A (en) | Vehicle front target detection method based on characteristic-point mutual information content and optical flow method | |
CN105809715A (en) | Inter-frame cumulative variation matrix-based visual moving object detection method | |
CN112101316B (en) | Target detection method and system | |
CN105574502A (en) | Automatic detection method for violation behaviors of self-service card sender | |
CN105069441A (en) | Moving vehicle detection method based on background updating and particle swarm optimization algorithm | |
Yahiaoui et al. | Let the sunshine in: Sun glare detection on automotive surround-view cameras | |
CN106570487A (en) | Method and device for predicting collision between objects | |
CN118038386B (en) | Dynamic target detection system under high-density complex traffic scene |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |