158 results about "Pedestrian road crossing" patented technology

The invention relates to the technical field of intelligent traffic control, in particular to a single-intersection signal lamp dynamic timing method and system based on holographic perception, and the method comprises the steps: collecting the information of a single intersection and surrounding traffic participants in real time through a multi-source holographic perception device, and carrying out the preprocessing, thereby obtaining a standardized traffic data set; based on the data set, combining vehicle, pedestrian and non-motor vehicle demand weights, constructing a traffic demand evaluation model, and calculating a demand priority coefficient of each entrance lane; constructing a signal lamp dynamic timing optimization objective function by taking minimization of intersection total vehicle waiting time, minimization of pedestrian crossing waiting time and maximization of intersection traffic volume per unit time as objectives according to the priority coefficient in combination with intersection traffic capacity constraint conditions, solving to obtain an optimal signal lamp timing parameter, and issuing the optimal signal lamp timing parameter to a control terminal; and traffic state feedback data of the intersection are collected in real time, and timing optimization is carried out again if the change exceeds a preset threshold value. The system can wait for a long time, improves the intersection passing efficiency, and relieves traffic congestion.

The invention is suitable for the technical field of traffic control, and provides a road section pedestrian crossing signal control method and system based on human and vehicle postures. The method comprises the following steps: acquiring instantaneous speed and position data of a head vehicle on each lane in front of a pedestrian crossing in real time, and calculating the maximum crossing time by combining the length of the pedestrian crossing and the type of a pedestrian; determining the length of the upstream and downstream judgment area of the pedestrian crossing based on the road design speed and the street crossing time; monitoring the number of pedestrians and the longest waiting time in the waiting area, and judging whether a first triggering condition is met or not by combining a reasonable waiting time threshold value and a capacity threshold value; judging whether a second triggering condition is met or not by comparing the theoretical driving time of the vehicle with the pedestrian crossing time in the judgment area; and when the first and second trigger conditions are met simultaneously, starting a pedestrian green light phase, otherwise, maintaining the current signal state. According to the invention, the waiting time of pedestrians and vehicles can be effectively reduced, and the intersection passing efficiency and safety are improved.

The invention provides a pedestrian intention reasoning method fusing scene interaction features and hierarchical temporal modeling, relates to the technical field of automatic driving, and solves the technical problems of low pedestrian intention prediction accuracy and generalization ability in the prior art. The method comprises the following steps: acquiring man-vehicle distance data, self-vehicle speed data and scene picture data; semantic segmentation is carried out on the scene picture data, and the object attribute of each pixel is identified and identified to obtain a segmented image, bounding box coordinates and pedestrian posture key points; the bounding box coordinate is the position of the pedestrian in the segmented image; extracting scene time sequence features in the segmented image; based on the bounding box coordinates, the pedestrian posture key points, the pedestrian-vehicle distance data and the self-vehicle speed data, pedestrian motion intention features in space-time correlation are extracted; and performing feature fusion on the scene time sequence features and the time-space associated pedestrian motion intention features by adopting a hierarchical temporal strategy, and predicting a pedestrian crossing intention result. The method is used in the pedestrian intention reasoning process.

The invention belongs to the technical field of traffic safety pre-warning, and provides a pedestrian zebra crossing pre-warning system device which comprises a mounting stand column, a monitoring assembly and a pre-warning assembly, a connecting base is arranged at the top of the front side of the mounting stand column, the monitoring assembly is arranged on the connecting base, and the monitoring assembly comprises an AI camera, a laser radar and a far infrared sensor. The early warning assembly comprises an electronic warning board, a laser transmitter and a laser spotlight; by comprehensively using various sensors such as the AI camera, the infrared sensor and the laser radar, pedestrians can be monitored and recognized from different angles and different modes, the accuracy of pedestrian recognition is improved, and the method is particularly suitable for pedestrian detection under complex weather and illumination conditions and has a wide application prospect. Through the synergistic effect of the laser spotlight, the laser curtain wall, the electronic warning board and the warning sound, early warning is performed on drivers and pedestrians from multiple aspects of visual sense and auditory sense, the early warning effect is enhanced, and the safety of the pedestrians crossing the road is improved.

The invention records a visual space-time pedestrian passing intention prediction method for automatic driving, and the method comprises the following steps: S1, extracting pedestrian motion time features, inputting the features into a bidirectional LSTM network, and outputting a time context coding vector; s2, constructing a spatial pyramid model and a time pyramid model; s4, weighting each level feature of the space-time pyramid model, splicing the weighted space features and time features to form spliced space-time feature vectors, summing the spliced space-time feature vectors according to levels, and outputting fused space-time feature vectors; and S5, establishing a classification network of a depth separable convolution and outputting a pedestrian passing intention probability value. Through joint modeling of the space-time pyramid model, the problem of space-time feature splitting is solved. The spatial features and the time features are respectively processed through a double-path attention module, a spatial attention weight and a time attention weight are output, and the feature discrimination capability of automatic driving in a complex scene is improved by adopting space-time attention weight fusion.

The invention relates to the technical field of traffic lights, and particularly discloses a traffic light signal real-time dynamic adjustment processing method based on electronic police data, which comprises the following steps: acquiring traffic monitoring data of a target traffic light intersection, analyzing and processing the data, generating period-level basic flow data, and dynamically adjusting a traffic light signal scheme according to the flow data. Algorithm data only needs traffic flow collected by an electronic police, a front-end sensing device does not need to be additionally installed, data processing and calculation are directly carried out in an existing traffic light signal machine, a rear-end big data calculation server is omitted, and therefore zero investment of technology application is basically achieved. According to the technology, all traffic signals connected to a signal machine are dynamically adjusted in real time by changing the whole signal control scheme mode, and the technology comprises green light duration adjustment E1, release mode adjustment E2, variable lamp panel adjustment E3, variable lane adjustment E4, intersection induction screen adjustment E5, green wave scheme adjustment E6 and pedestrian crossing control adjustment E7, so that the maximum application scene is achieved.

The invention discloses a traffic safety early warning method for a pedestrian crossing and a related device, and relates to the technical field of intelligent traffic, and the method comprises the steps: carrying out the vehicle driving analysis through a radar echo signal based on multi-dimensional Fourier transform, and obtaining the vehicle driving information; performing face positioning and multi-layer filtering processing by using the plurality of frames of target images based on shielding analysis to obtain a target face set; based on the target face set, carrying out two-way people flow analysis to obtain two-way people flow data; performing pedestrian passing time prediction on the pedestrian crosswalk based on the two-way pedestrian flow data and the plurality of frames of target images; analyzing recommended driving information of the vehicle in the early warning area based on the pedestrian passing time prediction data and the vehicle driving information; and based on the recommended driving information, performing voice generation by using the voice token and rhythm analysis, and obtaining target voice information to perform passage early warning. According to the method, the recommended driving information of the vehicle can be accurately analyzed, so that more reliable passing early warning is provided for the vehicle and the pedestrian.

The present application relates to the technical field of intelligent traffic control, and more particularly to a single intersection signal lamp dynamic timing method and system based on holographic perception, comprising: real-time collection of single intersection and surrounding traffic participant information through multi-source holographic perception equipment, preprocessing to obtain standardized traffic data set; based on the data set, combining vehicle, pedestrian and non-motor vehicle demand weight, constructing a traffic demand evaluation model, calculating the demand priority coefficient of each entrance; according to the priority coefficient, combining the intersection traffic capacity constraint condition, taking the minimization of the total vehicle waiting time at the intersection, the minimization of the pedestrian crossing waiting time and the maximization of the intersection unit time traffic volume as the target, constructing a signal lamp dynamic timing optimization objective function, solving to obtain the optimal signal lamp timing parameters and issuing to the control terminal; real-time collection of intersection traffic state feedback data, and if the change exceeds the preset threshold, re-timing optimization. It can reduce waiting time, improve intersection traffic efficiency and relieve traffic congestion.

The invention discloses an intelligent traffic safety warning device and a method thereof, and belongs to the technical field of road traffic safety. The device takes curbs as carriers, and the curbs are divided into two types of intelligent curbs, namely pedestrian crossings and roadways, which are both provided with laser radar sensors and LED early warning modules. Dynamic parameters of pedestrians and vehicles are detected in real time, a central processing unit predicts data such as pedestrian and vehicle conflict time difference and carries out six-level danger division, corresponding early warning schemes are triggered, and two-way warning of the pedestrians and the vehicles is achieved through light color change, voice prompt and projection light. The device adopts a three-level energy supply system, can be suitable for complex scenes such as single-person single-vehicle and single-person multi-vehicle, and selects an optimal early warning strategy based on a maximum risk principle. Through dynamic perception, track prediction and graded bidirectional early warning, road section traffic safety can be improved, accidents are reduced, urban traffic intelligent development is expected to be promoted, innovative technical support is provided for smart city construction, and the method has important social value and application prospects.

The present application relates to the technical field of vehicle violation monitoring, and discloses a vehicle violation monitoring method and system based on a city monitoring pole, which comprises the following steps: a mapping relationship between image coordinates and world coordinates is established by a stop line and a feature point of a pedestrian crossing, a polar coordinate system with an entry corner point of the pedestrian crossing as a pole point is constructed, and an angular sector area is divided, and a detection zone is formed by limiting a height range. A time sequence of the first appearance of a pedestrian in the detection zone is extracted, a time difference value of adjacent angular sectors is calculated to obtain an angular gradient peak index and a maximum peak angular sector position. When the index exceeds a threshold value, a forensic judgment time window is generated according to the maximum peak angular sector; otherwise, a backup time window is used. The position of the front end of a vehicle relative to the stop line and the pedestrian occupancy rate of the entry area of the pedestrian crossing are detected in the time window and the angular neighborhood, and if the pedestrian occupancy rate reaches a threshold value and the vehicle position crosses the line, a violation is output, otherwise, no violation is output.

The invention provides a pedestrian passing intention prediction method based on cross-modal attention interaction, and the method comprises the steps: obtaining the speed information of a vehicle and the coordinate information of a human body bounding box, and obtaining the speed modal features of the vehicle and the coordinate modal features of the human body bounding box through a cross-modal attention interaction module; fusing the self-vehicle speed modal feature and the human body bounding box coordinate modal feature through a feature fusion module to obtain a fused feature; processing the fusion feature by using a Transform model to obtain a pedestrian passing intention score; and predicting the pedestrian passing intention based on at least the pedestrian passing intention score. According to the method, a cross-modal attention interaction module and a feature fusion module are adopted, complementarity and difference between different modal features are fully utilized to be fused into fusion features, after the fusion features are coded and decoded based on a Transform model, whether pedestrians pass through a predicted time node or not is judged through an output pedestrian pass-through intention score, and the pedestrian pass-through intention prediction accuracy is improved. And the prediction performance is improved.

The utility model relates to the technical field of road construction, in particular to a spraying mechanism of a line drawing robot, which comprises a frame, a running device, a main spraying device and a side spraying device, the running device comprises running wheel sets arranged on two sides of the frame, the main spraying device is arranged on the frame, and the side spraying device is positioned on the outer side of the running wheel sets. In practical application, spraying operation of road edges, narrow sidewalk boundaries or parking space lines in parking lots is often difficult to efficiently complete in a traditional mode due to space limitation. The side edge spraying device can be tightly attached to the road edge, so that the spraying range is flexible, and the spraying precision is precise. The side edge spraying device improves the operation efficiency and the spraying quality. And the time and cost consumption caused by manual adjustment or repeated spraying for covering the narrow edge area is reduced. According to the utility model, the limitation of the traditional spraying mode in narrow space operation is solved, and the spraying device has efficient and accurate spraying capability.

The invention relates to the technical field of behavior prediction, and discloses a pedestrian crossing prediction method and system based on multi-modal feature fusion, and the method comprises the steps: obtaining multi-modal input data in a current observation time window; obtaining a currently observed main modal time sequence feature based on the multi-modal input data, and constructing a condition vector; extracting future observation features of the main mode; inputting the condition vector and the future observation features of the main mode into a teacher network to obtain first potential distribution; inputting the condition vector and the prior potential vector into a student network, enabling second potential distribution output by the student network to approach the first potential distribution through KL divergence alignment loss, and refining the prior potential vector to obtain a refined potential vector; inputting the condition vector and the refined potential vector into a decoder, and outputting a pedestrian crossing prediction probability and a corresponding uncertainty measure; according to the invention, the problems of low prediction precision and poor robustness of an existing pedestrian crossing prediction mode are solved.

The disclosure provides a vehicle control method and device based on a high-precision map and electronic equipment, relates to the technical field of artificial intelligence, and particularly relates to the technical field of automatic driving, intelligent traffic and the like. The specific implementation scheme is: in a case where it is determined based on the high-precision map that a to-be-passed lane of a vehicle is bound with a safety island, a plurality of access areas bound with the safety island and a pedestrian crossing bound with each access area are acquired from the high-precision map, a target pedestrian crossing having an overlapping area with the to-be-passed lane is acquired from the plurality of pedestrian crossings, a target access area corresponding to the target pedestrian crossing is acquired from the plurality of access areas, and in a case where it is detected that a road surface distance between the vehicle and the safety island is less than a preset distance threshold, position information corresponding to the target access area is provided to the vehicle, so that the vehicle can perceive the target access area of the safety island based on the position information, and drive safely on the safety island based on a perception result, which is beneficial to safe driving of the vehicle.

The application discloses a kind of no signal pedestrian crossing human-vehicle game behavior perception utility function quantitative evaluation method, belong to traffic safety and management field;Including analysis and determination of the game subject at no signal pedestrian crossing and setting the perception utility of game subject;Adopt Monte Carlo simulation and human ear perception similarity respectively quantify the perception utility of each game subject;Determine the acceptable perception level of each game subject;The perception utility function of each game subject is established using logistic regression model;The application can quantitatively analyze the problem that pedestrian crossing and motor vehicle yielding behavior at no signal pedestrian crossing mutually confront, mutually game each other, establish the basis for constructing Jacobian matrix and replicator dynamic equation in human-vehicle game model.

The present disclosure provides a trajectory determination method, device, equipment, storage medium, program product and an autonomous vehicle, relates to the technical field of computers, and particularly relates to the technical field of autonomous driving and intelligent traffic. The specific implementation scheme is as follows: according to perception data of a target vehicle, a target obstacle satisfying a target interaction condition with the target vehicle is determined. The target interaction condition includes at least one of a first interaction condition and a second interaction condition, the first interaction condition represents an obstacle crossing a pedestrian crossing scene, and the second interaction condition represents an obstacle turning towards an exit lane scene. According to obstacle state data of the target obstacle and vehicle state data of the target vehicle, a motion trajectory of the obstacle in a future target time period is determined. According to the trajectory determination method of the present disclosure, the motion trajectory of the obstacle affecting the driving safety of the target vehicle can be determined in advance and in a timely manner.

The utility model provides a vehicle-to-person auxiliary signal lamp control system, and relates to the technical field of traffic signal control. The system comprises at least one ground induction coil speed measuring device, a first microprocessor, a first communication module, at least one pedestrian signal lamp, a second microprocessor, a second communication module, a weighing sensor and at least one vehicle signal lamp. Wherein the number of the ground induction coil speed measuring devices corresponds to the number of the lanes; each ground induction coil speed measuring device is connected with the first microprocessor, the first microprocessor is connected with the first communication module, and the first communication module is connected with each pedestrian signal lamp; the weighing sensor is connected with the second microprocessor, the second microprocessor is connected with the second communication module, and the second communication module is connected with each vehicle signal lamp. The vehicle-to-person auxiliary signal lamp control system disclosed by the utility model can be installed on a pedestrian crossing which is not suitable for a traditional traffic lamp so as to play roles in protecting and guiding pedestrians and vehicles and improving the traffic efficiency.

The invention belongs to the technical field of artificial intelligence, and discloses a multi-purpose teaching and training intelligent vehicle based on machine vision. The specific use steps of the multipurpose teaching and training intelligent vehicle in a training field given by a user are as follows: S1, initialization and starting, S2, track tracking operation, S3, detection of sidewalks or upslopes, S4, operation in a deceleration zone, S5, acceleration to pass through roundabout, S6, detection of a yellow square frame and traffic light identification, and S7, arrival at a destination: a run6 is started for acceleration in a green light, and the vehicle continuously drives to a terminal point to complete a driving task. Through theoretical pushing and field verification, the rotating speed of the motor of the intelligent vehicle is successfully optimized to 300 revolutions per minute, perfect matching of the speed and the torque is achieved, the running stability of the intelligent vehicle is remarkably improved through the adjustment, the intelligent vehicle can steadily turn at different curves, stable and smooth racing track performance is ensured, and the running safety of the intelligent vehicle is improved. The innovation not only overcomes the centrifugal force problem of the original motor at a high speed, but also enhances the controllability of the vehicle, and establishes a new benchmark for the technical development of the intelligent vehicle.

To provide a pedestrian traverse prediction method and pedestrian traverse prediction device capable of accurately predicting whether pedestrians are to cross a road when the pedestrians exist on both sides of the road.SOLUTION: A pedestrian traverse prediction device includes an object detection device and controller mounted on an own vehicle 50. The object detection device detects a pedestrian 60 within a predetermined distance in front of the own vehicle 50. The object detection device detects a pedestrian 61 on the opposite side of a road with a position of the pedestrian 60 as reference. When a behavior change of the pedestrian 61 is detected within a predetermined time after the object detection device detects a behavior change of the pedestrian 60, the controller allows at least one likelihood between a first likelihood when the pedestrian 60 crosses the road and a second likelihood when the pedestrian 61 crosses the road to be higher than that when the behavior change of the pedestrian 61 is not detected within the predetermined time.SELECTED DRAWING: Figure 2

The utility model provides a crossing auxiliary device for visually impaired people, which relates to the technical field of traffic auxiliary devices and comprises a shell, a camera, an auxiliary monitoring sensor, a voice broadcast module and a trigger switch are arranged on the shell, and a power supply and a control mainboard are arranged in the shell. The camera, the auxiliary monitoring sensor, the voice broadcast module and the trigger switch are respectively in signal connection with the control mainboard, the power supply is used for supplying power to the camera, the voice broadcast module and the control mainboard, the camera is used for shooting intersection traffic light images, and the auxiliary monitoring sensor is used for monitoring pedestrian crossing traffic flow. According to the utility model, through combination of traffic light state identification and traffic flow detection, street-crossing auxiliary guidance is provided for visually impaired people, so that the safety risk of street crossing of the visually impaired people is further reduced.

The present invention provides a vehicle control device and a computer program capable of suppressing erroneous recognition as a pedestrian crosswalk when a road sign is detected. A vehicle control device is provided with a control unit that executes driving assistance control of a vehicle, and the control unit performs: analysis of imaging data obtained by imaging an environment around the vehicle; identifying a road present in the environment in a direction in which the vehicle travels; calculating a first distance in the width direction of the road; identifying a road surface identifier existing on the road; calculating a second distance in the width direction of a predetermined region including the road surface mark when it is recognized that the road surface mark is the predetermined pattern representing the pedestrian crosswalk; calculating a ratio of the second distance to the first distance; when the ratio is equal to or greater than a predetermined value, the driving assistance control unit recognizes a road surface mark as a pedestrian crosswalk and executes driving assistance control. And when the ratio is less than the predetermined value, recognizing the road surface mark as being not the pedestrian crosswalk, and not executing the driving assistance control.

The invention relates to the technical field of traffic safety, and discloses a traffic monitoring and early warning device for a pedestrian crossing, which comprises a cleaning ring, the cleaning ring is movably sleeved on a stand column, the inner wall of the stand column is provided with a clamping groove, the stand column is movably clamped with the outer side of a cleaning piece through the clamping groove, the inner side of the cleaning piece is not in contact with the wall surface of the stand column, and the cleaning ring is movably sleeved on the cleaning ring. An outer hole is formed in the outer wall of the cleaning ring, the outer wall of the cleaning piece is fixedly connected with one end of a cleaning handle, the other end of the cleaning handle penetrates through the outer hole of the stand column, and the cleaning ring is connected with the stand column through a power assembly. During cleaning work, the power assembly can control the cleaning ring to move up and down, so that the cleaning part can move to the front ends of the laser assembly and the camera assembly, full cleaning of the laser assembly and the camera assembly is achieved, impurities are prevented from affecting image collection of the camera assembly and laser emission of the laser assembly, and the monitoring and early warning quality is improved.

The invention relates to a pedestrian crossing signal control method based on radar detection, and the method comprises the steps: S1, a first radar determines the number of effective waiting pedestrians according to the waiting time of the pedestrians in a roadside waiting region, and then determines the maximum waiting time, and the maximum waiting time is configured to be that the larger the number of the effective waiting pedestrians detected by the first radar in the roadside waiting region is, the smaller the number of the effective waiting pedestrians is; the maximum waiting time is shorter; s2, determining the turn-on time of the passing phase signal lamp according to the maximum waiting time; and S3, determining the traffic capacity Ci of the pedestrian crossing area, and adjusting the traffic duration t of the traffic phase signal lamp according to the number P of the effective waiting pedestrians and the traffic capacity Ci. According to the invention, pedestrian state detection is carried out on pedestrian crossing key areas such as a roadside waiting area and a crossing channel area, pedestrian crossing demands, behavior characteristics and characteristics of a pedestrian crossing area are comprehensively considered, pedestrian waiting duration and pedestrian crossing duration are intelligently and dynamically adjusted, pedestrian crossing passage delay is reduced, and pedestrian crossing efficiency is improved. And the overall passing efficiency and quality are effectively improved.

To enable appropriate driving assistance in accordance with a surrounding environment when passing through a pedestrian crossing.SOLUTION: A driving assistance control device 5 for a vehicle that includes a surrounding sensor 1 that acquires surrounding data representing at least the situation in front of a vehicle, is configured to restrict driving assistance executed before or upon entering a pedestrian crossing when the time during which at least a portion of a pedestrian crossing area ahead on an adjacent lane of the own lane on which the vehicle is traveling continuously remains the blind spot of the surrounding sensor 1 is less than a predetermined time.SELECTED DRAWING: Figure 1

The application provides a kind of pedestrian traffic intention multimodal prediction method and prediction device, applied to access control monitoring technical field, based on the image information obtained, extract pedestrian multimodal feature, and whether the current pedestrian is allowed to pass through by decision logic judgment, including the following steps: S1, obtain the image sequence of inbound pedestrian, execute multi-target detection and tracking, identify each pedestrian ID, form boundary box sequence;S2, for each pedestrian, multimodal feature extraction is carried out, the multimodal feature includes card swiping action, gaze direction, running behavior and pedestrian category;S3, after processing multimodal feature, input into decision model to judge, to control gate state.The pedestrian traffic intention multimodal prediction method and prediction device, by fusing the gaze direction of pedestrian, action behavior, hand card swiping action and human body feature information, etc. Comprehensive judgment of the traffic intention of current traffic personnel, improve the accuracy and timeliness of abnormal behavior detection.

This invention discloses a design method, a crack-resistant maintenance system, and a construction method for a tunnel crack-resistant maintenance system, comprising the following steps: design preparation, obtaining tunnel parameters and indicators, including tunnel length, construction progress, maintenance time requirements, pedestrian crossing spacing, ventilation facility installation, water supply facility installation, and temperature and humidity inside and outside the tunnel, and determining the location of sub-maintenance systems; designing the ventilation device of the maintenance system based on the installation of ventilation facilities inside the tunnel, including the design of ventilation duct routes; designing the circulation device of the maintenance system based on the installation of water supply facilities inside the tunnel, including the layout design of water circulation pipes and greywater recycling devices, and drawing a layout diagram; calculating the turnover cycle and turnover distance; designing a humidification device, which includes a humidification material sheet made of wet film, the humidification device being supplied with water by the circulation device, and the ventilation device being used to humidify external air by passing through the humidification device; and calculating the optimal wind speed and circulating water temperature.

To detect and evaluate drivers who prioritize safe driving near pedestrian crossings. [Solution] The computing device according to the embodiment includes a controller. When the controller detects a marking indicating the presence of a pedestrian crossing from an image captured by an in-vehicle camera, it determines whether the driver performed safe driving actions based on sensor data from the in-vehicle sensor. The controller also performs a driving evaluation of the driver based on the determination result of whether the driver performed safe driving actions.

The present disclosure provides a trajectory determination method, device, equipment, storage medium, program product and an autonomous vehicle, relates to the technical field of computers, and particularly relates to the technical field of autonomous driving and intelligent traffic. The specific implementation scheme is as follows: according to perception data of a target vehicle, a target obstacle satisfying a target interaction condition with the target vehicle is determined. The target interaction condition includes at least one of a first interaction condition and a second interaction condition, the first interaction condition represents an obstacle crossing a pedestrian crossing scene, and the second interaction condition represents an obstacle turning towards an exit lane scene. According to obstacle state data of the target obstacle and vehicle state data of the target vehicle, a motion trajectory of the obstacle in a future target time period is determined. According to the trajectory determination method of the present disclosure, the motion trajectory of the obstacle affecting the driving safety of the target vehicle can be determined in advance and in a timely manner.

The application provides an automatic shunting method and system for a traffic weak participant group in automatic driving game, comprising the following steps: S1, acquiring all traffic weak participant group information of a current frame through sensing information; S2, judging a lane or a pedestrian crossing where the traffic weak participant group is located, and preliminarily classifying obstacles; S3, shunting the traffic weak participant group by using rules; and S4, constructing attributes of a new flow after shunting. The application is obviously clustered in behavior of the traffic weak participant group, can save a large amount of calculation resources such as collision judgment and trajectory prediction, reasonably avoids driving risks, and enhances stability, safety and comfort of automatic driving.

The utility model discloses an intelligent pedestrian crosswalk line safety prompt system, which comprises an information projection module, a display module and a control module which are arranged at a road pedestrian crosswalk line, and a detection module which is arranged in an upstream motor vehicle lane of the road pedestrian crosswalk line, the detection module, the information projection module and the display module are all in communication connection with the control module; the detection module is used for detecting whether a vehicle passes and generating a vehicle detection signal; and the control module is used for generating a control signal according to the vehicle detection signal so as to control the information projection module to project information to the ground and control the display module to display the information. The system is suitable for pedestrian crossing places without signal lamp control, has a good reminding effect on pedestrians, can effectively improve the pedestrian traffic safety at pedestrian crossing lines, and can solve the problem that in the prior art, pedestrian crossing lines of road sections are insufficient in reminding for pedestrians, so that the occurrence rate of pedestrian-vehicle conflicts and traffic accidents is remarkably reduced.