CN103204123A - Vehicle-pedestrian detecting, tracking and early-warning device and method - Google Patents

Vehicle-pedestrian detecting, tracking and early-warning device and method Download PDF

Info

Publication number
CN103204123A
CN103204123A CN201310096452XA CN201310096452A CN103204123A CN 103204123 A CN103204123 A CN 103204123A CN 201310096452X A CN201310096452X A CN 201310096452XA CN 201310096452 A CN201310096452 A CN 201310096452A CN 103204123 A CN103204123 A CN 103204123A
Authority
CN
China
Prior art keywords
tracking
vehicle
early warning
collision time
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.)
Granted
Application number
CN201310096452XA
Other languages
Chinese (zh)
Other versions
CN103204123B (en
Inventor
谷永先
胡国俊
张加波
兰欣
夏登明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
ACADEMY OF PUBLIC SECURITY TECHNOLOGY HEFEI
CETC 38 Research Institute
Original Assignee
ACADEMY OF PUBLIC SECURITY TECHNOLOGY HEFEI
CETC 38 Research Institute
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by ACADEMY OF PUBLIC SECURITY TECHNOLOGY HEFEI, CETC 38 Research Institute filed Critical ACADEMY OF PUBLIC SECURITY TECHNOLOGY HEFEI
Priority to CN201310096452.XA priority Critical patent/CN103204123B/en
Publication of CN103204123A publication Critical patent/CN103204123A/en
Application granted granted Critical
Publication of CN103204123B publication Critical patent/CN103204123B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Traffic Control Systems (AREA)

Abstract

The invention discloses vehicle-pedestrian detecting, tracking and early-warning device and method. The method includes that the early-warning device preprocesses infrared videos obtained by an infrared camera through an image preprocessing module, detects vehicles and pedestrians through a detecting module, forecast-tracks the vehicles and pedestrians through a tracking module to eliminate interference influences of vehicle vibration and virtual targets, calculates the distance between each target and the infrared camera according to corresponding relationship between world coordinates and image coordinates through a distance measuring module, judges an early-warning standard through a judging module, and displays the infrared videos carrying target identifiers and distance information on a display. The vehicle-pedestrian detecting, tracking and early-warning device has the advantages that driving safety is improved, most traffic accidents are effectively avoided, and life and property loss is lowered. The invention further discloses the vehicle and pedestrian detecting, tracking and early-warning method using the early-warning device.

Description

A kind of traffic detects tracking and early warning device and method for early warning thereof
Technical field
The present invention relates to a kind of automobile auxiliary security control loop, relate in particular to a kind of traffic based on the monocular infrared video and detect tracking and early warning device and method for early warning thereof, can specifically be applied to target detect, tracking and the range finding in fields such as on-vehicle night vision, communications and transportation, video monitoring and public safety.
Background technology
Along with the fast development of automotive market and the reinforcement day by day of security protection consciousness, people are more and more higher to the requirement of automotive safety safeguards technique.Existing automobile lighting system descends in low situations of visbilitys such as night, snow day or dense fogs that sighting distance is not far, the disadvantage of poor effect becomes one of potential safety hazard of running car; in addition when driving a vehicle night; chaufeur can be disturbed by the light of the other side's vehicle usually and the blind area occur, also gets into an accident easily.The passive type infrared night vision system is carried out imaging according to the different principle of infrared light intensity that the object of different temperatures sends, the temperature of object is more high, the image that presents is more bright, so the passive type infrared night vision system can help the chaufeur navigation in the dark, make chaufeur can both see driving environment clearly having under light and dark two kinds of situations, can be brighter than road surface and trees by the traffic that the passive type infrared night vision system is seen, so the driver can notice vehicle and the pedestrian in the place ahead immediately.
Chaufeur takes place frequently owing to reasons such as fatigue driving or dispersion attention also can cause accident in addition.Studies show that chaufeur can be avoided 60% collision case as long as obtain 0.5 second pre-warning time before collision risk, if before 1.5 seconds, obtain pre-warning time, then can avoid 90% above traffic accident.Therefore, automobile is equipped with the incidence that a cover intelligent anticollision forewarn system can significantly reduce road accident, in the time of may bumping with front vehicles or pedestrian, automobile can carry out sound and light alarm, direction and the hazard level of prompting chaufeur dangerous article, chaufeur can take brake measure to avoid the generation of accident in case of necessity, also can pass through automobile CAN-bus, and forewarn system control automobile is implemented braking automatically.
At present, some high-end vehicles in dress market and the back dress market of small part before vehicle-mounted infrared viewing device has applied to, the infrared camera before the car directly shows the infrared image of catching at Liquid Crystal Display (LCD).During night running, the vehicle driver will watch road conditions attentively on one side, also need constantly watch infrared image, thereby comprehensively judge whether dangerous appearance, this mode has increased driver's burden, be easy to cause the erroneous judgement or fail to judge, can not play the effect of driver assistance effectively.For existing anti-collision early warning system, the product based on monocular visible image capturing head of Israel Mobileye company occupies most market at present, but it is when using night, owing to can only survey visible light, so observed range is nearer, limited its use at night.
Fpga chip in the market has powerful digital processing ability as data processing chip, the FPGA alerting ability is strong, parallel processing capability is powerful, the operational performance excellence because can programme, debug, programming and repetitive operation again, therefore can design and develop easily and verify, when circuit has a small amount of change, more can demonstrate the advantage of FPGA, satisfied the infrared video data volume big, handle the demanding demand of real-time, realized that data gather fast and handle.ARM chip in the market is as controller, and integrated a lot of functions have powerful transaction capabilities, peripherally just can provide diversified work, for example demonstration, runnable interface and application program etc. by means of simple.
On infrared imaging system is integrated, for further improving practicality and the ease for use of infrared imaging, the infrared image processing technology has become the research focus of infrared imaging field and image processing field, and corresponding operation platform also develops into embedded platform from upper computer, and becomes a kind of trend.The infrared image processing embedded platform structure of having reported mainly contains following two kinds: based on the infrared image processing device of ARM hardware structure, the collection of view data, processing and interface operation etc. are all finished at ARM (1); (2) based on the infrared image processing device of FPGA hardware structure, the collection of view data, processing and interface operation etc. are all finished at FPGA.Since the ARM data-handling capacity a little less than, and video processnig algorithms comprises lot of data and calculates, if using the ARM chip to finish video data separately handles, can't guarantee the real-time of video processing.Higher when video definition, when data volume is big, the ARM chip can't be finished the Processing tasks of data; Fpga chip can be realized the high speed processing task of mass data, but FPGA development difficulty height, algorithm is transplanted complicated, is difficult to host computer procedure is transplanted to functions such as realizing interface display among the FPGA.
Summary of the invention
In view of this, be necessary to provide a kind of traffic to detect tracking and early warning device and method for early warning thereof, its purpose is on the basis of infrared night vision, develop a kind of target detect that has, follow the tracks of, the vehicle-mounted infrared viewing device of range finding and anti-collision warning prompt facility, can improve the safety of driving, effectively avoid most traffic accident, thereby reduction life and property loss, the present invention is applied to be equipped with in the vehicle of passive type monocular noctovisor, other vehicles and the pedestrian outer to this vehicle detect and follow the tracks of range finding, the distance of calculating and other vehicles or pedestrians, and send early warning, thereby, have infrared image is carried out certain algorithm process, can detect risk object, and send alarm in time, then can alleviate driver's burden greatly.
The present invention realizes like this, a kind of traffic detects the tracking and early warning device, it is applied to be equipped with in the vehicle of passive type monocular noctovisor, other vehicles and the pedestrian outer to this vehicle detect and follow the tracks of range finding, calculate the distance with other vehicles or pedestrians, and send early warning, this traffic detects the tracking and early warning device and comprises:
The image pre-processing module, it is used for the infrared video that obtains from this noctovisor is carried out pretreatment: by the filtering method filtering noise, use the method for adaptive histogram equalization to strengthen picture contrast again;
Detection module, it detects for other vehicles or pedestrians to this video and locatees, and detects target vehicle or target pedestrian;
Tracking module, it is used for target vehicle or target pedestrian are carried out predicting tracing, further follows the tracks of and confirms;
Range finder module, it is used for calculating through the target vehicle of tracking affirmation or target pedestrian's distance, and this distance satisfies following formula: d = h tan ( α + arctan ( ( y 0 - y ) f ) )
Wherein, d is this vehicle-to-target vehicle or target pedestrian's distance; F is the effective focal length of this noctovisor; α is the pitch angle of this noctovisor; H is that the camera lens of this noctovisor is to the height on road surface; (x 0, y 0) be the optical axis of this camera lens and the intersection point on picture plane, be the initial point of photo coordinate system; (x y) is the projection coordinate of P point on the picture plane, and this P point is taken from through following the tracks of target vehicle or the target pedestrian of affirmation, as with the R point apart from d of this vehicle;
Judge module, it is used for judging whether this is scheduled to collision distance less than one apart from d;
Show and the early warning module that it is used for during less than this predetermined collision distance, starting audible alarm, and starting display alarm apart from d at this.
As the further improvement of such scheme, according to the characteristics of infrared video, namely vehicle is relative with pedestrian's temperature higher, and this detection module be used for to adopt the way of rim detection and feature identification, detects target vehicle and target pedestrian and locatees.
Further improvement as such scheme, this tracking module is used for adopting the Kalman filter method in conjunction with Mean Shift method, sets up vehicle, pedestrian's trace model, and upgrade the target model parameter in tracing process, the influence that this vehicle of filtering brings in vibration processes, and the empty target of filtration fraction.
Further improvement as such scheme, this demonstration and early warning module also are used for dividing section to adopt different corresponding sound and light alarm modes according to different apart from d, make the frequency of alarm sound and the icon of power and display alarm divide section to change along with the variation of distance d.
Further improvement as such scheme, this traffic detects the tracking and early warning device and also comprises: module during survey, it is used for going out instantaneous collision time according to target vehicle or pedestrian in the change calculations of video dimension scale, and this instantaneous collision time satisfies following formula:
T m = Δt S - 1
Wherein, T mBe instantaneous collision time; Δ t is instantaneous collision time T mAnd the interval between current time in two moment; S be two constantly in the videos ratio of target vehicle or pedestrian's size change, target vehicle or pedestrian near the time, S〉1;
This judge module, it is used for judging instantaneous collision time T mWhether less than a pre-warning time;
Show and the early warning module that it is used at instantaneous collision time T mDuring less than this pre-warning time, start audible alarm, and start display alarm.
Preferably, this demonstration and early warning module also are used for according to different instantaneous collision time T mDivide section to adopt different corresponding sound and light alarm modes, make the icon of the frequency of alarm sound and power and display alarm along with instantaneous collision time T mVariation and divide section to change.
Preferably, this traffic detects the tracking and early warning device and also comprises: correcting module, it is used for instantaneous collision time T mCarry out acceleration correction, obtain to satisfy the correction collision time of following formula:
T = T m 1 - 1 - 2 ( T . m + 1 ) T . m + 1
Wherein, T represents instantaneous collision time T mThe correction collision time that obtains through acceleration correction;
Figure DEST_PATH_GDA0000306141794
Represent instantaneous collision time T mTo the time differentiate;
This judge module, whether it is used for judging revises collision time T less than the anti-collision warning time;
Show and the early warning module that it is used for during the time, starting audible alarm less than this anti-collision warning at correction collision time T, and starts display alarm.
Again preferably, this demonstration and early warning module also are used for dividing section to adopt different corresponding sound and light alarm modes according to different correction collision time T, make the frequency of alarm sound and the icon of power and display alarm divide section to change along with the variation of revising collision time T.
Again preferably, this traffic detects the tracking and early warning device and also comprises: brake command forms module, it is used at distance d less than a predetermined minimum collision distance or revise collision time T less than a predetermined minimum anti-collision warning during time, form brake command, this brake command is used for by the CAN bus of this vehicle this vehicle being implemented braking.
The present invention also provides a kind of traffic to detect the tracking and early warning method, it is applied to be equipped with in the vehicle of passive type monocular noctovisor, other vehicles and the pedestrian outer to this vehicle detect and follow the tracks of range finding, calculate the distance with other vehicles or pedestrians, and send early warning, this traffic detects the tracking and early warning method and may further comprise the steps:
The infrared video that obtains from this noctovisor is carried out pretreatment: by the filtering method filtering noise, use the method for adaptive histogram equalization to strengthen picture contrast again;
Other vehicles or pedestrians in this video are detected and locate, detect target vehicle or target pedestrian: according to the characteristics of infrared video, be that vehicle is relative with pedestrian's temperature higher, adopt the way of rim detection and feature identification, detect target vehicle and target pedestrian and locate;
Target vehicle or target pedestrian are carried out predicting tracing, further follow the tracks of and confirm: adopt the Kalman filter method in conjunction with Mean Shift method, set up vehicle, pedestrian's trace model, and in tracing process, upgrade the target model parameter, the influence that this vehicle of filtering brings in vibration processes, and the empty target of filtration fraction;
Calculate through the target vehicle of tracking affirmation or target pedestrian's distance, this distance satisfies following formula: d = h tan ( α + arctan ( ( y 0 - y ) f ) )
Wherein, d is this vehicle-to-target vehicle or target pedestrian's distance; F is the effective focal length of this noctovisor; α is the pitch angle of this noctovisor; H is that the camera lens of this noctovisor is to the height on road surface; (x 0, y 0) be the optical axis of this camera lens and the intersection point on picture plane, be the initial point of photo coordinate system; (x y) is the projection coordinate of P point on the picture plane, and this P point is taken from through following the tracks of target vehicle or the target pedestrian of affirmation, as with the R point apart from d of this vehicle;
Judge whether this is scheduled to collision distance less than one apart from d;
During less than this predetermined collision distance, start audible alarm apart from d at this, and start display alarm.
As the further improvement of such scheme, it is further comprising the steps of that this traffic detects the tracking and early warning method:
The change calculations of dimension scale in video goes out instantaneous collision time according to target vehicle or pedestrian, and this instantaneous collision time satisfies following formula:
T m = Δt S - 1
Wherein, T mBe instantaneous collision time; Δ t is instantaneous collision time T mAnd the interval between current time in two moment; S be two constantly in the videos ratio of target vehicle or pedestrian's size change, target vehicle or pedestrian near the time, S〉1;
Judge instantaneous collision time T mWhether less than a pre-warning time;
At instantaneous collision time T mDuring less than this pre-warning time, start audible alarm, and start display alarm.
As the further improvement of such scheme, it is further comprising the steps of that this traffic detects the tracking and early warning method:
To instantaneous collision time T mCarry out acceleration correction, obtain to satisfy the correction collision time of following formula:
T = T m 1 - 1 - 2 ( T . m + 1 ) T . m + 1
Wherein, T represents instantaneous collision time T mThe correction collision time that obtains through acceleration correction;
Figure DEST_PATH_GDA0000306141798
Represent instantaneous collision time T mTo the time differentiate;
Judge and whether revise collision time T less than the anti-collision warning time;
T during the time, starts audible alarm less than this anti-collision warning in the correction collision time, and starts display alarm.
Preferably, it is further comprising the steps of that this traffic detects the tracking and early warning method: divide section to adopt different corresponding sound and light alarm modes according to different correction collision time T, make the frequency of alarm sound and the icon of power and display alarm divide section to change along with the variation of revising collision time T.
The invention has the advantages that: than visible light, infrared video can be observed longer-distance vehicle and pedestrian at night and greasy weather, target detect in conjunction with vehicle and pedestrian, follow the tracks of, range finding and early warning technology, thereby need not chaufeur constantly observes the infrared video in the telltale judge whether dangerous situation, but as the collision time of target during less than time of setting (perhaps the distance of target less than set apart from the time), device can send sound and light alarm, and the degree with car danger, the frequency of sound and power can change thereupon, avoid the generation of accident thereby chaufeur can take appropriate measures.In addition, in case of emergency, when less than certain distance or collision time, when chaufeur was not taken measures, device can be implemented braking to automobile by the CAN bus of automobile.
Description of drawings
The module that the traffic that Fig. 1 provides for preferred embodiments of the present invention detects the tracking and early warning system constitutes scheme drawing.
Fig. 2 is the structural representation that traffic detects the treatment circuit of tracking and early warning system among Fig. 1.
Fig. 3 is that the module that is applied to the traffic detection tracking and early warning device of traffic detection tracking and early warning system among Fig. 1 constitutes scheme drawing.
Fig. 4 is the range measurement principle scheme drawing that traffic detects the tracking and early warning device among Fig. 3.
Fig. 5 is the vehicle-mounted scheme drawing that traffic detects the tracking and early warning system among Fig. 1.
Fig. 6 is the birds-eye view of Fig. 5.
Fig. 7 is the target detect tracking range finding scheme drawing that traffic detects the tracking and early warning device among Fig. 3.
Fig. 8 is the contrast scheme drawing of instantaneous collision time and acceleration correction collision time.
The specific embodiment
In order to make purpose of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein only in order to explaining the present invention, and be not used in restriction the present invention.
Traffic of the present invention detects the tracking and early warning device, it is applied to be equipped with in the vehicle of passive type monocular noctovisor, other vehicles and the pedestrian outer to this vehicle detect and follow the tracks of range finding, the distance of calculating and other vehicles or pedestrians, and send early warning.
This vehicle must possess traffic and detect the tracking and early warning system, this traffic detects the tracking and early warning system and comprises passive type monocular noctovisor 11, telltale 12, analog-to-digital conversion module 13, power module 14 and the treatment circuit 15 that is installed in the vehicle, as shown in Figure 1.This treatment circuit 15 is undertaken being shown in this telltale 12 after data are handled by the video signal that this analog-to-digital conversion module 13 obtains this noctovisor 11.
In the present embodiment, this treatment circuit 15 adopts the main body hardware architecture of FPGA circuit module 16 and 17 combinations of ARM circuit module, receive the analog video image signals of noctovisor 11 outputs, through analog-to-digital conversion module 13(such as A/D decoding chip), carry out the video signal digitalisation; Utilize FPGA circuit module 16 to finish the collection of data, and in FPGA circuit module 16, realize image processing algorithm, the view data of gathering is handled, difference characteristic according to object and background infrared emanation, this algorithm accurately detects the object edge, draw out the object profile, real-time tracking is carried out in the movement of object to be shown, and by the distance measurement function in the algorithm, detected target is found range, for follow-up use provides reliable object and range information, thereby realization is to the detection of object in the vision signal, follow the tracks of and range finding the Infrared video image data after the processing, sending into ARM circuit module 17 shows and compresses storage, the realization realtime graphic shows that simultaneously for relevant departments provide the reference of tracing to the source, thereby this treatment circuit has been given full play to the advantage of FPGA and ARM.
In brief, it is analog-to-digital conversion module 13 that noctovisor 11 is imported the A/D processing module with analog video image signals, after the modulus transformation, send into FPGA circuit module 16 and finish the identification of object, tracking, detection range finding and warning function, the infrared video input after the processing is sent into ARM circuit module 17 and is finished video signal compression storage and demonstration.
As shown in Figure 2, this FPGA circuit module 16 comprises FPGR treater, Infrared video image signal BNG input circuit (BNG input), video decode circuit (video decode), SRAM(SRAM DDR2), warning circuit (audible alarm), I2C etc., this ARM circuit module 17 comprises arm processor, video compression coding circuit (video compression coding), SD card memory circuit (storage of SD card), debugging communicating circuit and video and shows mutual circuit; Wherein, Infrared video image signal BNG input circuit is electrically connected at the video decode circuit, and video decode circuit, SRAM and warning circuit all are electrically connected at the FPGR treater; SD card memory circuit is electrically connected at the video compression coding circuit, and video compression coding circuit, debugging communicating circuit (RJ45, UART USB, SPI), video shows that mutual circuit (show output user interactions) all is electrically connected at arm processor; FPGR treater and arm processor use the mode of bus to carry out the exchange of data, and the entire process circuit is unified coordinative command by arm processor.These power module 14 power supplies are carried out the power supply input to total system, as producing FPGA circuit module 16 and ARM circuit module 17 needed all types of power supplys.
Noctovisor 11 carries out imaging according to the infrared ray of target reflection or radiation, the output analog video image signals.The FPGA circuit module 16 for the treatment of circuit 15 receives the analog video signal of noctovisor 11 outputs, through the A/D decoding chip, carries out the video signal digitalisation.Utilize the big digital processing ability of the FPGA circuit module Final 16 to finish data acquisition, and in FPGA circuit module 16, realize image processing algorithm, difference characteristic according to object and background infrared emanation, object is detected, follows the tracks of and finds range, simultaneously detected risk object is carried out Realtime Alerts and handle.The fpga chip of FPGA circuit module 16 can be realized the high speed processing of mass data, can satisfy the hardware requirement that system handles in real time to the Infrared video image signal.Through the infrared video data that FPGA circuit module 16 is handled, send in the ARM circuit module 17 with the BT656 form, carry out real-time demonstration and the compression storage of video file, for relevant departments provide the reference of tracing to the source.
She Hui electronic system now, breaking away from software can't move substantially, on above-mentioned hardware system (being that traffic detects the tracking and early warning system), develop traffic and detected tracking and early warning method software, be that traffic detects the tracking and early warning device, the traffic that the present invention relates to detects the tracking and early warning device and is applied in the above-mentioned hardware system, and the subsequent function that the present invention is directed to above-mentioned hardware system realizes that part describes in detail.
Traffic detects the tracking and early warning device and is applied to be equipped with in the vehicle of passive type monocular noctovisor, namely be applied to be equipped with in the vehicle of traffic detection tracking and early warning system, other vehicles and the pedestrian outer to this vehicle detect and follow the tracks of range finding, the distance of calculating and other vehicles or pedestrians, and send early warning.
The system that the traffic that preferred embodiments of the present invention provides detects the tracking and early warning device constitutes as shown in Figure 3, and this traffic detects the tracking and early warning device and comprises that image pre-processing module 1, detection module 2, tracking module 3, range finder module 4, judge module 5, demonstration and early warning module 6, brake command form module 7, module 8 when surveying.
Traffic of the present invention detects the tracking and early warning device, adopt 1 pair of Infrared video image signal that obtains from noctovisor 11 of image pre-processing module to carry out pretreatment, pass through 2 pairs of vehicles of detection module then, the pedestrian detects, get rid of the obstacle of vibration influence of this vehicle through tracking module 3, detected target is carried out predicting tracing, through range finder module 4, according to the corresponding relation between world coordinates and the image coordinate, calculate the distance between each target and the noctovisor 11, afterwards, judge by judge module 5, show in telltale 12 by the Infrared video image signal that shows and early warning module 6 will have target identification and a range information at last, and set according to the user, can report to the police or report to the police according to the collision time that calculates according to safety distance, in case of emergency, can form module 7 by brake command and by the CAN bus of automobile automobile be implemented braking, namely by the CAN bus of this vehicle automobile be implemented braking.
Subsequently traffic of the present invention is detected the tracking and early warning device carry out detailed expansion explanation.
At first, image pre-processing module 1 is used for the Infrared video image signal that obtains from this noctovisor 11 is carried out pretreatment: by the filtering method filtering noise, use the method for adaptive histogram equalization to strengthen picture contrast again.For subsequent detection, tracking, range finding and early warning link lay the foundation.
Secondly, detection module 2 detects for other vehicles or pedestrians to this video signal and locatees, and detects target vehicle or target pedestrian.Detect 2 main detection and location of realizing target such as vehicle and pedestrian in the video signal of mould, characteristics according to infrared video, be that vehicle is relative higher with the temperature of targets such as pedestrian, adopt the way of rim detection and feature identification, can detect each target is target vehicle or target pedestrian.
Afterwards, tracking module 3 is used for target vehicle or target pedestrian are carried out predicting tracing, further follows the tracks of and confirms.Tracking module 3 mainly carries out predicting tracing to targets such as detected target vehicle or target pedestrians, further each target is confirmed.Adopt the Kalman filter method in conjunction with Mean Shift method, set up target tracking models such as vehicle, pedestrian, and in tracing process, upgrade the target model parameter, the influence that this vehicle of filtering brings in vibration processes, and the empty target of filtration fraction.
Then, range finder module 4 is used for calculating through the target vehicle of tracking affirmation or target pedestrian's distance, and as shown in Figure 4, this distance satisfies following formula:
Figure DEST_PATH_GDA0000306141799
Wherein, d is this vehicle-to-target vehicle or target pedestrian's distance; F is the effective focal length of this noctovisor 11; α be the pitch angle of this noctovisor 11 also be noctovisor 11 setting angle α; H is that the camera lens of this noctovisor 11 is to the height on road surface; (x 0, y 0) be the optical axis of this camera lens and the intersection point on picture plane, be the initial point of photo coordinate system; (x y) is the projection coordinate of P point on the picture plane, and this P point is taken from through following the tracks of target vehicle or the target pedestrian of affirmation, as with the R point apart from d of this vehicle.
Then, judge module 5 is used for judging whether this is scheduled to collision distance less than one apart from d.
At last, show and early warning module 6 is used for during less than this predetermined collision distance, starting audible alarm, and starting display alarm apart from d at this.This demonstration and early warning module 6 also can be used for dividing section to adopt different corresponding sound and light alarm modes according to different apart from d, make the frequency of alarm sound and the icon of power and display alarm divide section to change along with the variation of distance d.
Certainly, also can collision time shows and early warning by calculating.Module 8 is used for going out instantaneous collision time according to target vehicle or pedestrian in the change calculations of video dimension scale during survey, and this instantaneous collision time satisfies following formula:
T m = Δt S - 1
Wherein, T mBe instantaneous collision time; Δ t is instantaneous collision time T mAnd the interval between current time in two moment; S be two constantly in the videos ratio of target vehicle or pedestrian's size change, target vehicle or pedestrian near the time, S〉1.
Actual conditions may comprise accelerated movement or decelerated movement, so in order to obtain collision time more accurately, need be to instantaneous collision time T mCarry out acceleration correction, correcting module is used for instantaneous collision time T mCarry out acceleration correction, obtain to satisfy the correction collision time of following formula:
T = T m 1 - 1 - 2 ( T . m + 1 ) T . m + 1
Wherein, T represents instantaneous collision time T mThe correction collision time that obtains through acceleration correction;
Figure DEST_PATH_GDA00003061417912
Represent instantaneous collision time T mTo the time differentiate;
Whether this judge module 5 also is used for judging revises collision time T less than the anti-collision warning time;
Demonstration and early warning module 6 also are used for during the time, starting audible alarm less than this anti-collision warning at correction collision time T, and start display alarm.
Judge module 5 also is used for judging revises collision time T(when not having this function of design modification, adopts instantaneous collision time T m) whether less than a pre-warning time; Demonstration and early warning module 6 also are used for revising collision time T(or instantaneous collision time T m) during less than this pre-warning time, start audible alarm, and start display alarm.This demonstration and early warning module 6 also can be used for according to different correction collision time T(or instantaneous collision time T m) divide section to adopt different corresponding sound and light alarm modes, make the icon of the frequency of alarm sound and power and display alarm along with revising collision time T(or instantaneous collision time T m) variation and divide section to change.
In sum, the user can setpoint distance d early warning or correction collision time T(or instantaneous collision time T m) early warning.During setpoint distance d early warning, according to the early warning distance of setting, as target apart from d during less than early warning distance, the warning of then sounding, and show corresponding icon at telltale 12, and can set the different corresponding different sound and light alarm modes of distance, the icon that the frequency of sound and power and telltale show is along with distance d changes; Set and revise collision time T(or instantaneous collision time T m) during early warning, according to the pre-warning time of setting, as correction collision time T(or the instantaneous collision time T of target m) during less than pre-warning time, the warning of then sounding, and show corresponding icon at telltale 12, and can set different correction collision time T(or instantaneous collision time T m) corresponding different sound and light alarm modes, the icon that the frequency of sound and power and telltale 12 show is along with revising collision time T(or instantaneous collision time T m) change.In addition, when less than certain apart from d or revise collision time T(or instantaneous collision time T m) in emergency circumstances, brake command forms module 7 can implement braking to automobile by the CAN bus of automobile.
Than visible light, infrared video can be observed longer-distance vehicle and pedestrian at night and greasy weather, target detect in conjunction with vehicle and pedestrian, follow the tracks of, range finding and early warning technology, thereby need not chaufeur constantly observes the infrared video in the telltale judge whether dangerous situation, but as the correction collision time T of target during less than time of setting (perhaps the distance of target less than set apart from the time), system can send sound and light alarm, and the degree with car danger, the frequency of sound and power can change thereupon, avoid the generation of accident thereby chaufeur can take appropriate measures.In addition, in case of emergency, when less than certain apart from d or revise collision time T, when chaufeur was not taken measures, system can implement braking to automobile by the CAN bus of automobile.
Traffic detects the tracking and early warning system when mounted, as Fig. 5 and shown in Figure 6, noctovisor 11 is installed in this vehicle head, be hidden in grid after, the camera lens visual field that guarantees noctovisor 11 is not blocked, and keeps the installation site simultaneously near this left and right vehicle wheel center; The hardware architecture that analog-to-digital conversion module 13, power module 14 and treatment circuit 15 form is installed in the operating console below of this vehicle, by cable the video signal of noctovisor 11 is introduced this hardware architecture, power module 14 is received on the Cigarette lighter of this vehicle, and noctovisor 11, treatment circuit 15 and telltale 12 are powered.Telltale 12 is installed in the indoor correct position of this vehicular drive, as be installed in above the operating console, perhaps hang and be installed in the forward sight position of waiting on glass, the mistake cable is introduced this hardware architecture with the video signal of noctovisor 11, outputs to telltale 12 to show; Adjust the setting height(from bottom) h of noctovisor 11, according to setting height(from bottom) h, camera parameter and a position, demarcation position, calculate camera setting angle α.The setting height(from bottom) h of this noctovisor 11 makes the camera lens visual field can cover this vehicle front zone, is paved with between a half field-of-view to three/two visual fields with the road surface that obtains in the video.Start can be carried out infrared detection, tracking, range finding and the alarm of this vehicle front target, and result as shown in Figure 7.Subsequent, the present invention does more detailed application example.
Embodiment 1: the traffic of monocular infrared video detects the tracking and early warning system applies in truck
Noctovisor 11 is installed on the grid place of truck, and recording noctovisor 11 height h and pitch angle overhead is setting angle α.Noctovisor 11 is connected with the flush bonding module that comprises image processing function by bnc interface, flush bonding module is realized the frequency pretreatment of infrared view image signal, noise is carried out filtering and figure is strengthened, detect according to pedestrian and vehicle detection feature, and further confirm to obtain target pedestrian and target vehicle by track algorithm, get rid of empty target, height h and pitch angle α according to the noctovisor 11 that has recorded, vehicle and pedestrian are adopted location algorithm, draw the distance of each target, and calculate the collision time of each target according to the variation ratio of target size in two two field pictures.By the AV interface Infrared video image signal is outputed to Liquid Crystal Display (LCD), target in the infrared video that Liquid Crystal Display (LCD) shows adopts rectangle frame to mark, and mark the distance of each target in the rectangle frame bottom, as shown in Figure 7, automobile is that the target in track, this vehicle place, the track of both sides all mark with rectangle frame, and marks the distance of each target under rectangle frame.Report to the police if set safety distance, in case the distance that target is arranged less than safety distance, then the buzzer phone on the flush bonding module is reported to the police; Report to the police if set collision time, according to the concrete time of setting, such as 2.5 s, in case the collision time that target arranged during less than 2.5 s, then buzzer phone is reported to the police.Total system adopts the cigar lighter socket power supply of automobile.
Fig. 8 is instantaneous collision time T mWith the contrast of acceleration correction collision time T, suppose that the distance between two cars is 30 m, the relative rate of onset of two cars is 10 m/s, relative acceleration is 2 m/s 2(two cars accelerate close).When target is far away, instantaneous collision time T mObviously greater than acceleration correction collision time T; When target was nearer, two kinds of collision times trended towards unanimity.In addition, instantaneous collision time T mAlong with the variation of time presents non-linearly, instantaneous collision time T is described mCan not react real collision time exactly, then present the trend of good linear change through the correction collision time T of acceleration correction.
The above only is preferred embodiment of the present invention, not in order to limiting the present invention, all any modifications of doing within the spirit and principles in the present invention, is equal to and replaces and improvement etc., all should be included within protection scope of the present invention.

Claims (13)

1. a traffic detects the tracking and early warning device, it is applied to be equipped with in the vehicle of passive type monocular noctovisor, other vehicles and the pedestrian outer to this vehicle detect and follow the tracks of range finding, calculate the distance with other vehicles or pedestrians, and send early warning, it is characterized in that this traffic detects the tracking and early warning device and comprises:
The image pre-processing module, it is used for the infrared video that obtains from this noctovisor is carried out pretreatment: by the filtering method filtering noise, use the method for adaptive histogram equalization to strengthen picture contrast again;
Detection module, it detects for other vehicles or pedestrians to this video and locatees, and detects target vehicle or target pedestrian;
Tracking module, it is used for target vehicle or target pedestrian are carried out predicting tracing, further follows the tracks of and confirms;
Range finder module, it is used for calculating through the target vehicle of tracking affirmation or target pedestrian's distance, and this distance satisfies following formula:
Figure FDA0000295811701
Wherein, d is this vehicle-to-target vehicle or target pedestrian's distance; F is the effective focal length of this noctovisor; α is the pitch angle of this noctovisor; H is that the camera lens of this noctovisor is to the height on road surface; (x 0, y 0) be the optical axis of this camera lens and the intersection point on picture plane, be the initial point of photo coordinate system; (x y) is the projection coordinate of P point on the picture plane, and this P point is taken from through following the tracks of target vehicle or the target pedestrian of affirmation, as with the R point apart from d of this vehicle;
Judge module, it is used for judging whether this is scheduled to collision distance less than one apart from d;
Show and the early warning module that it is used for during less than this predetermined collision distance, starting audible alarm, and starting display alarm apart from d at this.
2. traffic as claimed in claim 1 detects the tracking and early warning device, it is characterized in that, characteristics according to infrared video, be that vehicle is relative with pedestrian's temperature higher, this detection module be used for to adopt the way of rim detection and feature identification, detects target vehicle and target pedestrian and locatees.
3. traffic as claimed in claim 1 detects the tracking and early warning device, it is characterized in that, this tracking module is used for adopting the Kalman filter method in conjunction with Mean Shift method, set up vehicle, pedestrian's trace model, and in tracing process, upgrade the target model parameter, the influence that this vehicle of filtering brings in vibration processes, and the empty target of filtration fraction.
4. traffic as claimed in claim 1 detects the tracking and early warning device, it is characterized in that, this demonstration and early warning module also are used for dividing section to adopt different corresponding sound and light alarm modes according to different apart from d, make the frequency of alarm sound and the icon of power and display alarm divide section to change along with the variation of distance d.
5. traffic as claimed in claim 1 detects the tracking and early warning device, it is characterized in that, this traffic detects the tracking and early warning device and also comprises: module during survey, it is used for going out instantaneous collision time according to target vehicle or pedestrian in the change calculations of video dimension scale, and this instantaneous collision time satisfies following formula:
T m = Δt S - 1
Wherein, T mBe instantaneous collision time; Δ t is instantaneous collision time T mAnd the interval between current time in two moment; S be two constantly in the videos ratio of target vehicle or pedestrian's size change, target vehicle or pedestrian near the time, S〉1;
This judge module, it is used for judging instantaneous collision time T mWhether less than a pre-warning time;
Show and the early warning module that it is used at instantaneous collision time T mDuring less than this pre-warning time, start audible alarm, and start display alarm.
6. traffic as claimed in claim 5 detects the tracking and early warning device, it is characterized in that, this demonstration and early warning module also are used for according to different instantaneous collision time T mDivide section to adopt different corresponding sound and light alarm modes, make the icon of the frequency of alarm sound and power and display alarm along with instantaneous collision time T mVariation and divide section to change.
7. traffic as claimed in claim 5 detects the tracking and early warning device, it is characterized in that, this traffic detects the tracking and early warning device and also comprises: correcting module, it is used for instantaneous collision time T mCarry out acceleration correction, obtain to satisfy the correction collision time of following formula:
T = T m 1 - 1 - 2 ( T · m + 1 ) T · m + 1
Wherein, T represents instantaneous collision time T mThe correction collision time that obtains through acceleration correction;
Figure FDA0000295811704
Represent instantaneous collision time T mTo the time differentiate;
This judge module, whether it is used for judging revises collision time T less than the anti-collision warning time;
Show and the early warning module that it is used for during the time, starting audible alarm less than this anti-collision warning at correction collision time T, and starts display alarm.
8. traffic as claimed in claim 7 detects the tracking and early warning device, it is characterized in that, this demonstration and early warning module also are used for dividing section to adopt different corresponding sound and light alarm modes according to different correction collision time T, make the frequency of alarm sound and the icon of power and display alarm divide section to change along with the variation of revising collision time T.
9. traffic as claimed in claim 7 detects the tracking and early warning device, it is characterized in that, this traffic detects the tracking and early warning device and also comprises: brake command forms module, it is used at distance d less than a predetermined minimum collision distance or revise collision time T less than a predetermined minimum anti-collision warning during time, form brake command, this brake command is used for by the CAN bus of this vehicle this vehicle being implemented braking.
10. a traffic detects the tracking and early warning method, it is applied to be equipped with in the vehicle of passive type monocular noctovisor, other vehicles and the pedestrian outer to this vehicle detect and follow the tracks of range finding, calculate the distance with other vehicles or pedestrians, and send early warning, it is characterized in that this traffic detects the tracking and early warning method and may further comprise the steps:
The infrared video that obtains from this noctovisor is carried out pretreatment: by the filtering method filtering noise, use the method for adaptive histogram equalization to strengthen picture contrast again;
Other vehicles or pedestrians in this video are detected and locate, detect target vehicle or target pedestrian: according to the characteristics of infrared video, be that vehicle is relative with pedestrian's temperature higher, adopt the way of rim detection and feature identification, detect target vehicle and target pedestrian and locate;
Target vehicle or target pedestrian are carried out predicting tracing, further follow the tracks of and confirm: adopt the Kalman filter method in conjunction with Mean Shift method, set up vehicle, pedestrian's trace model, and in tracing process, upgrade the target model parameter, the influence that this vehicle of filtering brings in vibration processes, and the empty target of filtration fraction;
Calculate through the target vehicle of tracking affirmation or target pedestrian's distance, this distance satisfies following formula: d = h tan ( α + arctan ( ( y 0 - y ) f ) )
Wherein, d is this vehicle-to-target vehicle or target pedestrian's distance; F is the effective focal length of this noctovisor; α is the pitch angle of this noctovisor; H is that the camera lens of this noctovisor is to the height on road surface; (x 0, y 0) be the optical axis of this camera lens and the intersection point on picture plane, be the initial point of photo coordinate system; (x y) is the projection coordinate of P point on the picture plane, and this P point is taken from through following the tracks of target vehicle or the target pedestrian of affirmation, as with the R point apart from d of this vehicle;
Judge whether this is scheduled to collision distance less than one apart from d;
During less than this predetermined collision distance, start audible alarm apart from d at this, and start display alarm.
11. traffic as claimed in claim 10 detects the tracking and early warning method, it is characterized in that, it is further comprising the steps of that this traffic detects the tracking and early warning method:
The change calculations of dimension scale in video goes out instantaneous collision time according to target vehicle or pedestrian, and this instantaneous collision time satisfies following formula:
T m = Δt S - 1
Wherein, T mBe instantaneous collision time; Δ t is instantaneous collision time T mAnd the interval between current time in two moment; S be two constantly in the videos ratio of target vehicle or pedestrian's size change, target vehicle or pedestrian near the time, S〉1;
Judge instantaneous collision time T mWhether less than a pre-warning time;
At instantaneous collision time T mDuring less than this pre-warning time, start audible alarm, and start display alarm.
12. traffic as claimed in claim 11 detects the tracking and early warning method, it is characterized in that, it is further comprising the steps of that this traffic detects the tracking and early warning method:
To instantaneous collision time T mCarry out acceleration correction, obtain to satisfy the correction collision time of following formula:
T = T m 1 - 1 - 2 ( T · m + 1 ) T · m + 1
Wherein, T represents instantaneous collision time T mThe correction collision time that obtains through acceleration correction;
Figure FDA0000295811708
Represent instantaneous collision time T mTo the time differentiate;
Judge and whether revise collision time T less than the anti-collision warning time;
T during the time, starts audible alarm less than this anti-collision warning in the correction collision time, and starts display alarm.
13. traffic as claimed in claim 12 detects the tracking and early warning method, it is characterized in that, it is further comprising the steps of that this traffic detects the tracking and early warning method: divide section to adopt different corresponding sound and light alarm modes according to different correction collision time T, make the frequency of alarm sound and the icon of power and display alarm divide section to change along with the variation of revising collision time T.
CN201310096452.XA 2013-03-25 2013-03-25 Vehicle-pedestrian detecting, tracking and early-warning device and method Active CN103204123B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310096452.XA CN103204123B (en) 2013-03-25 2013-03-25 Vehicle-pedestrian detecting, tracking and early-warning device and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310096452.XA CN103204123B (en) 2013-03-25 2013-03-25 Vehicle-pedestrian detecting, tracking and early-warning device and method

Publications (2)

Publication Number Publication Date
CN103204123A true CN103204123A (en) 2013-07-17
CN103204123B CN103204123B (en) 2015-07-08

Family

ID=48751597

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310096452.XA Active CN103204123B (en) 2013-03-25 2013-03-25 Vehicle-pedestrian detecting, tracking and early-warning device and method

Country Status (1)

Country Link
CN (1) CN103204123B (en)

Cited By (26)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103617747A (en) * 2013-11-07 2014-03-05 北京智谷睿拓技术服务有限公司 Information processing method, vehicle-mounted terminal and handheld equipment
CN104044503A (en) * 2014-07-03 2014-09-17 安庆市鸿裕工业产品设计有限公司 Trailing vehicle identifying and prompting device
CN104966064A (en) * 2015-06-18 2015-10-07 奇瑞汽车股份有限公司 Pedestrian ahead distance measurement method based on visual sense
CN105203034A (en) * 2015-07-29 2015-12-30 四川大学 Height and area measurement method based on monocular camera three-dimensional distance measurement model
CN105706145A (en) * 2016-01-31 2016-06-22 冯旋宇 Vehicle image distance measuring method and system
CN106156725A (en) * 2016-06-16 2016-11-23 江苏大学 A kind of method of work of the identification early warning system of pedestrian based on vehicle front and cyclist
CN104553983B (en) * 2013-10-24 2017-02-15 鸿富锦精密工业（深圳）有限公司 Vehicle pre-warning system and vehicle pre-warning method
CN106537479A (en) * 2014-07-22 2017-03-22 三菱电机株式会社 Driving assistance system, driving assistance method, and program
WO2017096821A1 (en) * 2015-12-08 2017-06-15 乐视控股（北京）有限公司 Driving safety detection method and apparatus
CN106909929A (en) * 2015-12-22 2017-06-30 比亚迪股份有限公司 Pedestrian's distance detection method and device
CN107226023A (en) * 2017-04-10 2017-10-03 江苏车视杰电子有限公司 Image procossing real-time early warning system and method
CN107226024A (en) * 2017-04-24 2017-10-03 惠州市凯越电子股份有限公司 A kind of high-precision vehicle sighting distance collection and processing system and method
CN107591026A (en) * 2017-09-11 2018-01-16 苏州莱孚斯特电子科技有限公司 A kind of pedestrian detection and the method for early warning
CN107921923A (en) * 2015-08-28 2018-04-17 德尔福技术有限公司 Pedestrian for automated vehicle is intended to detection
CN107959796A (en) * 2017-12-08 2018-04-24 朱明君 It is a kind of that there is the camera device of target detection
CN109039457A (en) * 2017-06-12 2018-12-18 意法半导体(R&D)有限公司 Use the vehicle communication of visible light communication
CN109583267A (en) * 2017-09-28 2019-04-05 京东方科技集团股份有限公司 Vehicle object detection method, vehicle object detecting device and vehicle
CN109747566A (en) * 2017-11-02 2019-05-14 郭宇铮 A kind of automatic night vision system
CN110001517A (en) * 2018-01-05 2019-07-12 聚晶半导体股份有限公司 Driving warning method and driving warning system
CN110264500A (en) * 2016-06-27 2019-09-20 御眼视觉技术有限公司 Based on the main vehicle of the Characteristics Control that parks cars detected
CN110622080A (en) * 2018-03-26 2019-12-27 深圳市大疆创新科技有限公司 Tracking processing method and control terminal of unmanned aerial vehicle
CN112348879A (en) * 2020-10-30 2021-02-09 深圳市优必选科技股份有限公司 Vehicle operation control method and device, electronic equipment and storage medium
CN112356815A (en) * 2020-12-01 2021-02-12 吉林大学 Pedestrian active collision avoidance system and method based on monocular camera
CN113016016A (en) * 2018-11-26 2021-06-22 三菱电机株式会社 Information presentation control device, information presentation control method, program, and recording medium
CN113401082A (en) * 2021-08-02 2021-09-17 姜春诗 Self-judging automobile safety automatic braking system and method
US11605298B2 (en) 2020-01-29 2023-03-14 Toyota Motor Engineering & Manufacturing North America, Inc. Pedestrian navigation based on vehicular collaborative computing

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH06270780A (en) * 1993-03-23 1994-09-27 Mazda Motor Corp Safety device for vehicle
DE102004046101A1 (en) * 2004-09-23 2006-09-21 Daimlerchrysler Ag Method for early detection of motor vehicle collision involves estimation of collision danger on the basis of determined time to collision and introducing collision reducing measures with exceeding of predetermined collision danger
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
CN201800639U (en) * 2010-08-20 2011-04-20 叶春林 Vehicle sight line monitoring and warning device
CN201901079U (en) * 2009-05-05 2011-07-20 杨斌 Automobile collision-prevention device
CN102963326A (en) * 2011-08-30 2013-03-13 通用汽车环球科技运作有限责任公司 Detection apparatus and method for detecting a carrier of a transceiver, motor vehicle

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH06270780A (en) * 1993-03-23 1994-09-27 Mazda Motor Corp Safety device for vehicle
DE102004046101A1 (en) * 2004-09-23 2006-09-21 Daimlerchrysler Ag Method for early detection of motor vehicle collision involves estimation of collision danger on the basis of determined time to collision and introducing collision reducing measures with exceeding of predetermined collision danger
CN201901079U (en) * 2009-05-05 2011-07-20 杨斌 Automobile collision-prevention device
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
CN201800639U (en) * 2010-08-20 2011-04-20 叶春林 Vehicle sight line monitoring and warning device
CN102963326A (en) * 2011-08-30 2013-03-13 通用汽车环球科技运作有限责任公司 Detection apparatus and method for detecting a carrier of a transceiver, motor vehicle

Cited By (37)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104553983B (en) * 2013-10-24 2017-02-15 鸿富锦精密工业（深圳）有限公司 Vehicle pre-warning system and vehicle pre-warning method
CN103617747B (en) * 2013-11-07 2016-03-23 北京智谷睿拓技术服务有限公司 Information processing method and car-mounted terminal, handheld device
CN103617747A (en) * 2013-11-07 2014-03-05 北京智谷睿拓技术服务有限公司 Information processing method, vehicle-mounted terminal and handheld equipment
CN104044503A (en) * 2014-07-03 2014-09-17 安庆市鸿裕工业产品设计有限公司 Trailing vehicle identifying and prompting device
CN106537479A (en) * 2014-07-22 2017-03-22 三菱电机株式会社 Driving assistance system, driving assistance method, and program
CN104966064A (en) * 2015-06-18 2015-10-07 奇瑞汽车股份有限公司 Pedestrian ahead distance measurement method based on visual sense
CN105203034A (en) * 2015-07-29 2015-12-30 四川大学 Height and area measurement method based on monocular camera three-dimensional distance measurement model
CN105203034B (en) * 2015-07-29 2018-07-17 四川大学 A kind of survey height survey area method based on monocular cam three-dimensional ranging model
CN107921923B (en) * 2015-08-28 2020-10-30 安波福技术有限公司 Pedestrian intent detection for automated vehicles
CN107921923A (en) * 2015-08-28 2018-04-17 德尔福技术有限公司 Pedestrian for automated vehicle is intended to detection
WO2017096821A1 (en) * 2015-12-08 2017-06-15 乐视控股（北京）有限公司 Driving safety detection method and apparatus
CN106909929A (en) * 2015-12-22 2017-06-30 比亚迪股份有限公司 Pedestrian's distance detection method and device
WO2017128441A1 (en) * 2016-01-31 2017-08-03 冯旋宇 Vehicle image distance measuring method and system
CN105706145A (en) * 2016-01-31 2016-06-22 冯旋宇 Vehicle image distance measuring method and system
CN106156725A (en) * 2016-06-16 2016-11-23 江苏大学 A kind of method of work of the identification early warning system of pedestrian based on vehicle front and cyclist
CN110264500A (en) * 2016-06-27 2019-09-20 御眼视觉技术有限公司 Based on the main vehicle of the Characteristics Control that parks cars detected
CN107226023A (en) * 2017-04-10 2017-10-03 江苏车视杰电子有限公司 Image procossing real-time early warning system and method
CN107226024A (en) * 2017-04-24 2017-10-03 惠州市凯越电子股份有限公司 A kind of high-precision vehicle sighting distance collection and processing system and method
CN107226024B (en) * 2017-04-24 2019-06-21 惠州市凯越电子股份有限公司 A kind of high-precision vehicle sighting distance acquisition and processing system and method
CN109039457A (en) * 2017-06-12 2018-12-18 意法半导体(R&D)有限公司 Use the vehicle communication of visible light communication
CN107591026B (en) * 2017-09-11 2021-04-02 苏州莱孚斯特电子科技有限公司 Pedestrian detection and early warning method
CN107591026A (en) * 2017-09-11 2018-01-16 苏州莱孚斯特电子科技有限公司 A kind of pedestrian detection and the method for early warning
CN109583267A (en) * 2017-09-28 2019-04-05 京东方科技集团股份有限公司 Vehicle object detection method, vehicle object detecting device and vehicle
US11482013B2 (en) 2017-09-28 2022-10-25 Beijing Boe Technology Development Co., Ltd. Object tracking method, object tracking apparatus, vehicle having the same, and computer-program product
CN109583267B (en) * 2017-09-28 2022-04-08 京东方科技集团股份有限公司 Vehicle target detection method, vehicle target detection device, and vehicle
CN109747566A (en) * 2017-11-02 2019-05-14 郭宇铮 A kind of automatic night vision system
CN107959796A (en) * 2017-12-08 2018-04-24 朱明君 It is a kind of that there is the camera device of target detection
CN110001517A (en) * 2018-01-05 2019-07-12 聚晶半导体股份有限公司 Driving warning method and driving warning system
CN110622080A (en) * 2018-03-26 2019-12-27 深圳市大疆创新科技有限公司 Tracking processing method and control terminal of unmanned aerial vehicle
CN110622080B (en) * 2018-03-26 2023-07-25 深圳市大疆创新科技有限公司 Unmanned aerial vehicle tracking processing method and control terminal
CN113016016A (en) * 2018-11-26 2021-06-22 三菱电机株式会社 Information presentation control device, information presentation control method, program, and recording medium
US11472432B2 (en) 2018-11-26 2022-10-18 Mitsubishi Electric Corporation Information presentation control device, information presentation device, information presentation control method, and non-transitory computer-readable recording medium
US11605298B2 (en) 2020-01-29 2023-03-14 Toyota Motor Engineering & Manufacturing North America, Inc. Pedestrian navigation based on vehicular collaborative computing
CN112348879A (en) * 2020-10-30 2021-02-09 深圳市优必选科技股份有限公司 Vehicle operation control method and device, electronic equipment and storage medium
CN112348879B (en) * 2020-10-30 2023-12-19 深圳市优必选科技股份有限公司 Vehicle operation control method and device, electronic equipment and storage medium
CN112356815A (en) * 2020-12-01 2021-02-12 吉林大学 Pedestrian active collision avoidance system and method based on monocular camera
CN113401082A (en) * 2021-08-02 2021-09-17 姜春诗 Self-judging automobile safety automatic braking system and method

Also Published As

Publication number Publication date
CN103204123B (en) 2015-07-08

Similar Documents

Publication Publication Date Title
CN103204123B (en) Vehicle-pedestrian detecting, tracking and early-warning device and method
CN103158620B (en) A kind of traffic detecting and tracking forewarn system
CN107031508B (en) Back-sight visual system and its application method for vehicle
CN105620489B (en) Driving assistance system and vehicle real-time early warning based reminding method
CN102556071B (en) Vehicle threat identification on full windshield head-up display
CN111775940B (en) Automatic channel changing method, device, equipment and storage medium
JP7499256B2 (en) System and method for classifying driver behavior - Patents.com
US10232772B2 (en) Driver assistance system
US9359009B2 (en) Object detection during vehicle parking
JP5712119B2 (en) Pedestrian notification device for vehicles
US20200225343A1 (en) Vehicle radar system for detecting dangerous goods
CN104786933A (en) Panoramic image driving auxiliary device and panoramic image driving auxiliary method
CN109572555A (en) A kind of block information display methods and system applied to unmanned vehicle
JP2017033542A (en) Information display
JP2003099899A (en) Device for operating degree of risk of driving behavior
CN203332106U (en) Automobile warning anti-collision system based on monocular vision
CN112896159A (en) Driving safety early warning method and system
US11770677B1 (en) Enhanced safety systems and method for transportation vehicles
CN109001743A (en) Tramcar anti-collision system
CN109466444A (en) Hazardous vehicles detect method for early warning and system
CN111137236A (en) Non-transparent liquid crystal display method and system based on automobile front windshield
KR20180007785A (en) Pedestrian Protection System for autonomous car
CN208847836U (en) Tramcar anti-collision system
CN111098864B (en) Prompt method, device, automatic driving vehicle and storage medium
CN109895694B (en) Lane departure early warning method and device and vehicle

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant