610 results about "Zebra crossing" patented technology

The invention provides a road marking line extracting method based on a forward camera head in automatic driving. The method comprises steps of obtaining a normal incidence view of a road marking line in front of a current vehicle via reverse perspective transformation; restraining an initial threshold value of current solving road segmentation according to parts of prior knowledge formed based on normal running modes of vehicles; by using the initial threshold value, segmenting the normal incidence view; judging the parallel property presented by edge pixel points and the equidistant property presented by a projection histogram; and extracting road marking lines including lane lines, road traffic signs, vehicle stop markings and zebra marking lines. According to the invention, execution speed is fast; by operating the projection histogram, effects on detection and extraction imposed by incomplete image details can be reduced; robustness of the extracting method is improved; constraints on few prior knowledge are increased; and by adopting the approximate, divide-and-conquer and dimension reduction technological means, the range of the extraction precision is further reduced and processing of sub-regions of parts of road scenes is inhibited.

The invention discloses a navigation mobile phone for the blind. The navigation mobile phone is characterized in that: a user inputs destination reaching information by a voice module or a keyboard for the blind, a global positioning system (GPS)/GPSONE chip acquires the current position information of the user, and the destination reaching information and the current position information of the user are transmitted to a navigation server by a mobile phone radio frequency module; a travel scheme provided by the navigation server and a regional map are downloaded by the mobile phone radio frequency module, and navigation information general situations are broadcast to the blind by voices; simultaneously image information acquired by a dual-camera module is processed, traffic light, blind sidewalk or zebra crossing information is extracted and broadcast to the blind by the voices, and obstacle information is acquired and broadcast to the blind in a voice way by an ultrasonic ranging module and a microwave speed measurement module; and the falling or collision information of the user is monitored and recorded by a three-axis gyroscope and an accelerometer. The mobile phone is highly integrated, simply operated, convenient to produce, low in cost and suitable for wide popularization.

The invention provides a road zebra crossing automatic extraction method based on vehicle-mounted laser scanning point cloud, and relates to public traffic road zebra crossings. According to the method, global positioning system data for recording vehicle positions and tracks in real time is used for extracting a plurality of cross sections from the vehicle-mounted laser scanning point cloud data, and the road and non-road classification is realized through detecting the elevation mutation of road shoulders of the roads in the scanning line data; then, the three-dimension road data is converted into an intensity characteristic image with space distribution characteristics, the laser scanning point normal distribution characteristics are utilized for dynamically cutting the road zebra crossings, the GPS (global positioning system) track data is used again for calculating the linear morphology closed operation direction and size, and the extraction of the road zebra crossings is realized. Through the cross section subdivision on the vehicle-mounted moving scanning data, and the three-dimension road surface data detection is converted into the detection of the elevation mutation of the road shoulders of the roads in the two-dimension profile for realizing the road and non-road classification. Compared with a method of directly processing mass three-dimension data, the method has the advantages that the calculation quantity is small, and the efficiency is high.

The invention provides a vision detection system for vehicles not yielding to pedestrians at zebra crossing, comprising a monitoring camera covering the whole zebra crossing area, a HD (high definition) snapshot camera for taking snapshots of vehicles, a traffic cloud server, and a vision detection subsystem. The vision detection subsystem comprises a zebra crossing area detection module, a not-yielding-to-pedestrians behavior detection module, a not-yielding-to-pedestrians behavior vehicle image snapshot module, a vehicle type identification module, a license plate positioning and identifyingmodule, and a violation detection report generating module. The traffic cloud server is used for receiving video data of the whole zebra crossing area obtained by the monitoring camera, and submitting the video data to the vision detection subsystem to conduct not-yielding-to-pedestrians behavior detection and personal identity verification of violation vehicles. A violation detection report canbe automatically generated and stored with the detection and identification result, three snapshots of not-yielding-to-pedestrians vehicle images, and the process video images. The invention is quitehigh in detection precision and robustness.

The invention provides an intersection precise parking device and method used for automatic driving. The device comprises an image acquisition device, an electronic control unit, millimeter-wave radar and a speedometer. A camera is used for acquiring images of zebra crossing and a stop line in a road and traffic lights above the road. The millimeter-wave radar is used for detecting front vehicle information. The electronic control unit can detect the zebra crossing, the stop line and the traffic lights and can estimate the distance between a vehicle and the stop line according to pulse number fed back by the speedometer when the stop line enters a camera view dead zone, and the automatically driven vehicle can be precisely parked at the stop line of an intersection. When a vehicle is in front of the current vehicle, the electronic control unit can achieve precise parking according to data detected by the millimeter-wave radar, the position of the front vehicle and the states of the traffic lights. The device and method solve the problem about how to precisely park the automatically driven vehicle at the stop line at the intersection.

The invention relates to a traffic light adjustment method and device, and the method comprises the steps: obtaining the flow information of a traffic intersection, wherein the flow information comprises at least one of the number of pedestrians waiting to pass at a zebra crossing, the waiting time of the pedestrians, the number of vehicles waiting to pass on lanes, and the waiting time of the vehicles; and adjusting the display of the red and green lights of the traffic intersection according to the flow information. Through the technical scheme of the invention, the method and device adjust the red and green lights according to the number of pedestrians and the number of vehicles, can reduce the waiting time of the pedestrians and vehicles, improve the passing rate of the pedestrians and vehicles, and improve the user experience.

The invention relates to a zebra crossing pedestrian monitoring and warning device based on laser inspection. The current devices have bad using effects. The device of the invention comprises a pedestrian monitoring device, a control box and signal lamps, wherein the pedestrian monitoring device comprises two trigger gates respectively arranged at the start and end of a zebra crossing; each trigger gate comprises a laser emission column and a laser pick-off column arranged on a sidewalk respectively at two ends of the zebra crossing; the laser emission column of each trigger gate emits laser beam and the laser pick-off column of each trigger gate picks off the laser beam; when a pedestrian passes through the trigger gates, the laser beam is cut off; two rows of signal lamps are respectively arranged at two sides of the zebra crossing; and the control box is arranged on a telegraph pole of the sidewalk. The device of the invention adopts the pedestrian monitoring systems arranged at two ends of the zebra crossing, and each pedestrian monitoring system is additionally provided with a passing in and out direction judging function, thereby improving the efficiency of system operation. The device of the invention is more conductive to remind drivers to avoid collision to reduce hidden danger of traffic accidents.

The invention discloses an intelligent video analyzing method for pedestrians crossing zebra stripes. The intelligent video analyzing method comprises the following steps that (1) a video analyzing system is arranged near the zebra stripes and is started regularly at preset time points, and cameras collect video information data in real time and transmit the video information data to a video analyzer; (2) the video analyzer analyzes the video information data and judges states of traffic lights, the intruder alarming function of an intelligent alarming module is started if the red light is turned on, and the prompt information playing function of the intelligent alarming module is started if the green light or the yellow light is turned on; (3) the video analyzing system is closed at preset time points, and the video information data of the day are stored before the video analyzing system is closed. By means of the scheme, the unique intelligent video analyzing method for the urban zebra stripe traffic lights and the moving pedestrians is achieved, the intrusion on the pedestrians crossing the zebra stripes is detected when the red light is turned on, and intelligent audio and video alarming is conducted according to detecting results.

The invention discloses a solar intelligent zebra crossing device. The solar intelligent zebra crossing device comprises a solar power supply system, a pedestrian sensing and detecting system, a PLC (programmable logic controller) control system, a zebra crossing LED indicator light system and a voice warning system. When pedestrians go into a zebra crossing area, pressure sensors transmit sensing signals to the control system, the control system judges that the pedestrians walk out of the zebra crossing or to the opposition direction of the zebra crossing. When the pedestrians walk to the counter road via the zebra crossing, LED lamps embedded on the zebra crossing emit conspicuous red light to prompt passing vehicles of no entry so as to avoid the pedestrians in advance. When the vehicles pass and the pedestrians are detected at a starting line of the zebra crossing, the voice warning system can prompt the pedestrians of no entry. The solar intelligent zebra crossing device is powered by solar energy, energy source is saved, cables are not needed to be paved, mounting of the device is convenient, avoiding of the vehicles and safety passing of the pedestrians are facilitated, and traffic potential hazards are reduced.

The invention relates to a pedestrian crossing traffic light control method and a traffic light control system for achieving the method. Pedestrian crossing signal lights are arranged at the two ends of a zebra crossing, and a motor vehicle traffic signal light is fixedly arranged above the zebra crossing. The method comprises the steps that according to the initial state, the pedestrian crossing signal lights are red, and the motor vehicle traffic signal light is green; the total weight of pedestrians in waiting areas at the two ends of the pedestrian crossing is detected; according to the detected weight of the pedestrians, the time for switching the red pedestrian crossing signal lights into the green pedestrian crossing signal lights and the time for switching the green motor vehicle traffic signal light into the red motor vehicle traffic signal light are controlled. According to the method and system, the weight of the pedestrians waiting for crossing the road in the waiting areas is detected, the time for switching the green motor vehicle traffic signal light into the red motor vehicle traffic signal light is controlled, it is detected that the larger the weight of the pedestrians is, the shorter the time for switching the green motor vehicle traffic signal light into the red motor vehicle traffic signal light is, and therefore the time of the pedestrians for waiting for passage is reasonably controlled, and the efficiency of communication and transportation is improved.

The invention provides a control device for preventing cars from running a red light, which belongs to the technical field of cars and solves the problem that control devices for preventing cars from running the red light are low in intelligentization and automation degrees in the prior art. The control device for preventing the cars from running the red light comprises an image pick-up device, a car speed sensor, a brake actuating mechanism, a car controller and a video identification unit, wherein the video identification unit is connected with the car controller, the image pick-up device is connected with the video identification unit, the car speed sensor and the brake actuating mechanism are both connected with the car controller, the video identification unit is used for picking up video image information in the image pick-up device and identifying the video image information, and the car controller is used for comprehensively judging whether to control the brake actuating mechanism to brake or not. The control device for preventing the cars from running the red light can automatically brake when the red light is on and stop in front of the zebra crossing, thereby improving the running safety and running intelligentization.

The invention relates to RMB counterfeit identifying technologies, and provides a counterfeit identifying method and a counterfeit identifying system based on zebra crossing infrared image characteristics. The counterfeit identifying method comprises the steps of A, acquiring an infrared image of RMB and carrying out preprocessing on the acquired infrared image; B, extracting HOG characteristics of the preprocessed infrared image and selecting HOG characteristics which satisfy preset conditions from the extracted HOG characteristics; and C, carrying out counterfeit identifying according to the selected HOG characteristics. The counterfeit identifying method based on the zero crossing infrared image characteristics acquires a zebra crossing anti-counterfeit image of the RMB by adopting infrared light, and carries out processing and identifying on the zebra crossing anti-counterfeit image by using an improved HOG and a support vector machine, thereby being capable of effectively eliminating noise effects and improving the performance of infrared image counterfeit identifying, and being capable of improving the accuracy in counterfeit identification for authentic and counterfeit banknotes.

The invention relates to an unmanned vehicle environment itemized performance testing system and testing method, and aims to provide a method for testing common obstacles of an unmanned vehicle under an outdoor driving condition, thereby planning a driving path of a vehicle conveniently and improving the independent capability of driving the unmanned vehicle outdoors. Whether the vehicle is completely in conformity with the hardware condition of an unmanned vehicle by virtue of the patrol run test, track change test in encountering obstacles, turning left (right) test, curve track running test in patrolling obstacles, test for recognizing a stop line in encountering red lights, test for accelerating and slowing down urgently, test for recognizing road signboards, test for recognizing ground mark lines, test for recognizing zebra crossings, curve road running test in patrolling lane lines by the unmanned vehicle.

The invention relates to an automatic capture system and a recognition method for vehicles not giving way to passengers on a zebra crossing. The automatic capture system comprises subsystems, including a system management subsystem, an image collection subsystem, a violation capture subsystem, a data storage subsystem and a network transmission subsystem. The system management subsystem is used for configuring and managing automatic capturing of a vehicle not giving way to passengers on the zebra crossing; the image collection subsystem is used for collecting image data of the zebra crossing and image data of a vehicle road area; the violation capture subsystem is used for capturing and discovering the vehicles not giving way to the passengers in the zebra crossing area; the data storage subsystem is used for storing original images, captured violation images and captured videos; the network transmission subsystem is used for uploading the captured images and the captured videos to a traffic police station or a server. The recognition method allows the vehicles running straight and not giving way to the passengers to be captured and also allows the vehicles cornering and not giving way to the passengers; since a way of capturing the fronts of the vehicles is adopted, positional relation of the vehicles and passengers in the captured images is clear, and no blocking occurs.

The invention discloses a multi-surface mark fusion-based lane level locating method. The method comprises the steps of 1, obtaining a vehicle road image; 2, performing grayscale processing and filtering processing on the road image; 3, performing lane line detection on the processed road image in the step 2; 4, performing stop line detection on the road image; 5, performing zebra crossing detection on the road image; and 6, locating the position of a vehicle in a lane in real time according to a lane line, a zebra crossing and a stop line. According to the method, information of multiple mark lines of a road is fused for performing accurate road lane line locating; and the method not only can be suitable for a driving safety pre-warning function of the vehicle but also can be fused in a pure vision system in unmanned driving to perform lane line patrol and turning at the intersection.

The invention provides a mobile robot track plotting correcting system based on straight-running intersection and a mobile robot track plotting correcting method. The method is simple and the accuracy rate is high. The system comprises a mobile robot track plotting unit and a track plotting correcting unit, wherein the mobile robot track plotting unit comprises a speedometer, an inertial navigation sensor and a track plotting module installed on the robot; the track plotting correcting unit comprises a camera, an intersection detection module and a correcting module installed on the robot. Firstly, the mobile robot is subjected to track plotting by the speedometer and inertial data to obtain an initial positioning position, and then the track plotting position is corrected through the combination of data acquired based on the zebra crossing detection of the intersection and the data of an electronic map, so that the relatively accurate positioning position of the mobile robot can be acquired.

The invention belongs to the technical field of road traffic information detection, and relates to a fusion method for detecting road traffic information based on double cameras. Key road traffic information such as lane lines, zebra crossings, vehicles, traffic lights and the like in front of an intelligent vehicle are acquired via double cameras, the lane lines and the zebra crossings are detected by adopting an improved detection algorithm, and the functions of single cameras are promoted by adopting five-frame cyclic detection; features which need to be acquired by the system in different states are determined according to the set logic rule, and the corresponding features are recognized by logic detection, so that the response speed of the system is improved, key information is provided for transverse and longitudinal control of the intelligent vehicle, and a foundation is laid for normal running of the intelligent vehicle in urban roads; and more information is acquired for analysis and decision under emergency, so that the defect that the single camera acquires data is overcome.

The invention discloses a zebra-crossing 'blind zone' vehicle-and-pedestrian mutual recognition and early warning method, and belongs to a vehicle-and-pedestrian mutual recognition and early warning method. The method includes the steps that lanes and vehicles which are capable of generating 'blind zone' phenomena and pedestrians are monitored, whether accident damages are generated or not is judged, an early warning is simultaneously raised to the pedestrians and drivers through a detector, messages are sent to mobile phones of the drivers and the pedestrians or other multimedia terminals toconduct warning, and road-junction real-time monitoring videos are sent to the mobile phones of the drivers or the other multimedia terminals as occasion requires to assist the drivers in comprehensively mastering current road-junction conditions. The detector comprises a camera and a radar sensor, and is used for detecting distance relationships between the lanes and the vehicles which are capable of generating the 'blind zone' phenomena and the pedestrians and raising related early warnings. The zebra-crossing 'blind zone' vehicle-and-pedestrian mutual recognition and early warning method has the advantages that the zebra-crossing vehicles capable of generating 'blind zone' phenomena and zebra-crossing pedestrians are monitored, collected information is processed, warnings are raised tovehicle owners and the pedestrians, and accident damages caused by the 'blind zone' phenomena are prevented.

The invention discloses a traffic light time control method for a two-way multi-lane zebra crossing intersection. A video monitoring device arranged at a zebra crossing intersection identifies and collects the number of vehicles waiting at the intersection and the number of pedestrians waiting at the two sides of the zebra crossing and identifies and determines a traffic flow situation; accordingto the vehicle number and pedestrian number as well as the traffic flow situation, processing is carried out based on different conditions; and a traffic light control system calculates green light lasting time and red light lasting time respectively based on the waiting vehicle number and waiting pedestrian number according to a lane traffic light lasting time calculation formula. Therefore, a problem of traffic resource wasting caused by fixed setting of the traffic light lasting time of the two-way multi-lane zebra crossing intersection is solved.

The invention discloses a zebra crossing real-time detection method based in intelligent driving, and belongs to the field of traffic information detection in the intelligent traffic industry. The zebra crossing real-time detection method includes the steps of firstly, obtaining an image Src_Image of the road in front of an intelligent vehicle in real time at a frame rate of 25 frames per second to 50 frames per second, and conducting inverse perspective transformation on the obtained original image Src_Image to obtain a bird view image Bird_View of a road image; then, cutting a lane area image ROI_Image out of the bird view image Bird_View according to two lane lines of a lane, conducting graying, self-adaption binaryzation, canny edge extraction and morphology corrosion expansion on the image ROI_Image to obtain a binaryzation image Dst_Bw; finally, conducting transverse pixel statistics on the image Dst_Bw to obtain the black-white skip time number Sum, the black strip average width Wb, the white strip average width Ww and the strip average height H. If the conditions that Sum is larger than S1 and smaller than S2, the absolute value of the difference between Wb and Ww is smaller than W, Wb is larger than Wb1 and smaller than Wb2, Ww is larger than Ww1 and smaller than Ww2, and H is larger than H1 and smaller than H2 are all satisfied, the zebra crossing is confirmed to appear in front of the intelligent vehicle, and if not, the zebra crossing is confirmed not to appear.

The invention provides a street-crossing pedestrian trajectory prediction method and system based on a social force model, and a medium. The method comprises the following steps: a basic data acquisition step: selecting a pedestrian-vehicle mixed zebra crossing area for early investigation, shooting a pedestrian walking video of the area, and performing video processing and image processing on thepedestrian walking video to obtain pedestrian walking feature data and pedestrian-vehicle interaction scene data; and a model parameter calibration step: preprocessing the obtained pedestrian walkingcharacteristic data and the obtained pedestrian-vehicle interaction scene data, and calibrating parameters of a logistic regression model and a social force model. According to the method, the improved social force model is utilized, the individual difference of pedestrians is fully considered, the pedestrian track prediction of the crossing street is applied to the field of automatic driving vehicle decision making, the driving safety of the automatic driving vehicle in the pedestrian-vehicle mixed zebra crossing area can be improved, the delay rate of the vehicle is reduced, and the road traffic capacity is improved.

The invention discloses a zebra crossing scribing device for municipal roads. The device comprises a bottom plate and a transverse plate, wherein a first hanging bracket and a second hanging bracket are respectively arranged at the two sides of the lower end face of the transverse plate; the lower end of the first hanging bracket is provided with a screw rod shaft, and the two ends of the screw rod shaft are rotatablely connected with the first hanging bracket; the screw rod shaft is provided with a sliding sleeve in screw-thread fit connection with the screw rod shaft; a cleaning brush is arranged at the lower end of the sliding sleeve; the transverse plate is provided with a transmission shaft and a drive shaft which are arranged in parallel; two rotary racks are respectively hinged to the two sides of the lower end of the second hanging bracket; the two rotary racks are connected with each other by means of a regulating spring, and the rotary rack positioned at the left side is provided with a hollow coating roller; one end of a support guide pipe is separately communicated with the left end and the right end of a cylinder body, arranged on the transverse plate, by means of twodischarge hose pipes; one-way valves are respectively arranged on the two discharge hose pipes and two feed hose pipes. The zebra crossing scribing device has the advantages of simple structure, continuous and uniform road surface scribing, higher scribing efficiency, unified driving, convenient control, simple and convenient operation and higher practicality.

The invention provides an intersection intelligent light-controlled indication camcorder which comprises a ground crosswalk signal light, a ground vehicle signal light and a vehicle red light camera. The ground crosswalk signal light is arranged on a zebra crossing of a road intersection. The display color of the ground crosswalk signal light and the display color of a crosswalk light in the direction are synchronous. The ground vehicle signal light is arranged on a stop line at the road intersection. The display color of the ground vehicle signal light and the display color of a vehicle signal light in the driving direction are synchronous. According to the invention, the intersection intelligent light-controlled indication camcorder is capable of directing pedestrians to consciously abide by traffic rules; the camera is arranged on a traffic light pole in front of the intersection; cost is saved; the stop line, the license plate number of an illegal vehicle, the color of a signal light and the facial image of a driver appear in a picture at the same time; and the enforcement pertinence of traffic police is improved.

The invention provides a method for identifying a vehicle type identification method, a device, and a computer readable storage medium. The vehicle type identification method comprises steps: obtaining vehicle type identification information of a corresponding vehicle in an image to be identified by constructing a vehicle type identification model and performing vehicle type identification on a zebra crossing area captured by a camera and an image to be identified around the zebra crossing area by using the vehicle type identification model, wherein the vehicle type identification informationincludes vehicle class information, vehicle coordinates, vehicle vertical pixels, and vehicle horizontal pixels; calculating the size and proportion of the corresponding vehicle in the image to be recognized according to the scale of the vehicle vertical pixel, the vehicle horizontal pixel and the zebra crossing in the image to be recognized; searching information of the first vehicle type according to the size and proportion from the website; converting the image to be identified into an HSV image and searching out second vehicle information corresponding to a hue value of the vehicle in theHSV image from the first vehicle type information. The method can effectively reduce the judgment range of the vehicle type and improve the accuracy of the vehicle type recognition.