82 results about "Pedestrian crossing" patented technology

Smart car operations are detailed including capturing a point cloud from a vehicle street view and converting the point cloud to a 3D model; applying a trained neural network to detect street signs, cross walks, obstacles, or bike lanes; and generating driving recommendations based on driver behavior parameters by comparing the driver behavior parameters with one or more drivers with substantially similar behavior parameters.

In various examples, one or more deep neural networks (DNNs) are executed to regress on control points of a curve, and the control points may be used to perform a curve fitting operation—e.g., Bezier curve fitting—to identify landmark locations and geometries in an environment. The outputs of the DNN(s) may thus indicate the two-dimensional (2D) image-space and / or three-dimensional (3D) world-space control point locations, and post-processing techniques—such as clustering and temporal smoothing—may be executed to determine landmark locations and poses with precision and in real-time. As a result, reconstructed curves corresponding to the landmarks—e.g., lane line, road boundary line, crosswalk, pole, text, etc.—may be used by a vehicle to perform one or more operations for navigating an environment.

The present invention provides a driver assistance system and vehicle capable of predicting the likelihood of pedestrians or light vehicles crossing the road before a crosswalk in specific traffic conditions. [Solution] A driving assistance device according to one embodiment of the present disclosure is capable of predicting the time it will take for a target traffic participant to reach a crosswalk when, under predetermined conditions at a first time, the signal for pedestrians or light vehicles at a crosswalk begins to switch from indicating "proceed" to indicating "no proceed" at a second time. Furthermore, based on the predicted time, this driving assistance device can calculate the probability that the target traffic participant will cross the road on which the vehicle is traveling, and determine whether or not to provide driving assistance and the content of the driving assistance according to the calculated probability.

To provide an information providing device capable of surely notifying an automatic driving vehicle of an intention indication of a pedestrian.SOLUTION: An information providing device 10 is installed in a periphery of a pedestrian crossing PC. The information providing device 10 comprises a communication device 11 which receives an intention indication signal relating to crossing from a portable terminal 30 that a pedestrian PA carries, and a control device 12 which notifies an automatic driving vehicle VE of the reception of the intention indication signal via the communication device 11.SELECTED DRAWING: Figure 2

To control a vehicle such that a pedestrian can easily recognize that the vehicle has detected the presence of the pedestrian attempting to cross a road and decelerates, thereby preventing an increase in time required for the pedestrian to cross the road and for the vehicle to pass a crossing position.SOLUTION: A vehicle control device includes a camera (21) that images a front area of a vehicle (1), and a controller (10) configured to be capable of controlling a driving force source (31) and / or a brake (32) of the vehicle. The controller determines whether or not a pedestrian has an intention to cross a road at a crossing position on the basis of a position and a speed of the pedestrian, predicts a safety confirmation timing at which the pedestrian performs safety confirmation before crossing the road on the basis of the crossing position and the position and speed of the pedestrian when it is determined that the pedestrian has the intention to cross the road, and controls the driving force source and / or the brake so as to cause the vehicle to generate a yielding deceleration set such that the pedestrian can recognize that the vehicle prioritizes the pedestrian's crossing at the safety confirmation timing.SELECTED DRAWING: Figure 3

To suppress delay of detection of a predetermined target in front of a vehicle.SOLUTION: A driving assistance device 100 performs driving assistance of a vehicle when a predetermined target is present in a driving assistance area set in front of the vehicle. When setting change of area of a driving assistance area is possible and setting change of the area of the driving assistance area when a crosswalk is detected in front of the vehicle in an enlargement direction is possible, the driving assistance device 100 is configured to enlarge the area of the driving assistance area so as to spread outward of the vehicle so as to include the entire area of the driving assistance area when the crosswalk is detected.SELECTED DRAWING: Figure 1

The present invention relates to a crosswalk pedestrian protection system linked to traffic lights. The crosswalk pedestrian protection system linked to traffic lights, according to one aspect of the present invention, comprises: a camera unit provided to photograph a crosswalk and a pedestrian path or road adjacent to the crosswalk so as to acquire a crosswalk image by photographing the crosswalk and the pedestrian path or road; a control server which receives, from a plurality of traffic lights or a plurality of traffic light controllers, traffic light control signals for causing the traffic lights to display a blinking indication according to traffic signals including a red light, a yellow light, a green light, a U-turn signal, a left-turn signal, and a right-turn signal, and which generates and outputs a control signal for controlling road signs according to the traffic light control signals; and the road signs which are provided along the crosswalk and the pedestrian path or road adjacent to the crosswalk and blink according to the control signal output from the control server.

The application discloses a kind of identification methods of pedestrian on crosswalk, the method utilizes vehicle front camera to obtain the image corresponding to vehicle front scene, obtains the color block in image and carries out screening, and then obtains the regression straight line of color block, utilizes the characteristics of the longitudinal boundary line of white color block of crosswalk in the image of front camera compared to a point to the regression straight line in image is screened and numbered, and the regression straight line screened is the longitudinal boundary line of white color block of crosswalk.By the change of regression straight line number in detection process, the shielding condition of pedestrian to the white color block of crosswalk is reflected, and then the identification of pedestrian on crosswalk is realized.

To provide a drive support device and a vehicle, capable of notification or braking in an own vehicle before the own vehicle or another vehicle enters an intersection against presentation of a signal light, or a pedestrian or a bicyclist enters a crosswalk.SOLUTION: A drive support device according to an embodiment of the present disclosure can execute the following two steps: (1) determining a possibility that a vehicle starts to enter an intersection against presentation of a first signal light according to a change in lighting state of a second signal light different from a first signal light for a vehicle of a plurality of signal lights installed in the intersection in front of the stopped vehicle; and (2) controlling at least one of notification for a driver of the vehicle and braking of the vehicle according to a degree of the above possibility.SELECTED DRAWING: Figure 2

A driving assistance device performs driving assistance of a vehicle when a predetermined target exists in a driving assistance area set in front of the vehicle. The driving assistance device is configured so as to be able to change the setting of the area of the driving assistance area, and to change the setting of the area of the driving assistance area in the expansion direction when a pedestrian crosswalk is detected in front of the vehicle. The area of the driving assistance region is expanded so as to expand in the outside direction of the vehicle so as to include the entire driving assistance region when the pedestrian crosswalk is detected.

Embodiments of the disclosure are drawn to apparatuses, systems, and methods for radar object classification. A radar classification system may include a number of endpoint units and a base station. Each endpoint unit includes a camera and a radar. The camera may image a scene and the image may be used to establish spatial zones within the scene. The radar may collect point cloud data from one or more objects in the scene. A classifier may determine an identity of the object based on the point cloud data. The base station may collect information such as the identity and location of objects in the scene and relate this information to the spatial zones. For example, objects may be identified as a vehicle, pedestrian, or cycle, and related to zones such as roadway, sidewalk, and crosswalk for the purpose of traffic control.

The invention discloses an intelligent auxiliary driving control method and device and a computer program product, and the method comprises the steps: recognizing the traffic light information, road information, vehicle information and pedestrian information of an area where a vehicle is located; if the traffic signal lamp is recognized in front, performing pedestrian yielding control on the vehicle according to the indication of the traffic signal lamp and the pedestrian information; if it is recognized that there is no traffic signal lamp in front but there is a pedestrian crossing line, performing pedestrian yielding control on the vehicle according to the position relationship between the pedestrian and the pedestrian crossing line and whether the pedestrian has a gesture indicating that the vehicle is going ahead or not; and if no traffic signal lamp and no pedestrian crossing line are recognized in front, performing pedestrian commission control on the vehicle according to the position of the pedestrian, the expected trajectory of the pedestrian and the position relation of the vehicle. The braking comfort of intelligent auxiliary driving under the condition of guaranteeing pedestrian safety can be improved in the scene without traffic lights, the waiting time is shortened, the potential collision risk is avoided, and the pedestrian safety is guaranteed.

The present invention discloses a method and related device for traffic safety warning of a crosswalk, which relates to the technical field of intelligent transportation. The method includes: performing vehicle driving analysis using radar echo signals based on multi-dimensional Fourier transform to obtain vehicle driving information; performing face positioning and multi-layer filtering processing on a plurality of frames of target images based on occlusion analysis to obtain a set of target faces; performing two-way pedestrian flow analysis based on the set of target faces to obtain two-way pedestrian flow data; predicting the pedestrian passing time of the crosswalk based on the two-way pedestrian flow data and a plurality of frames of target images; analyzing the recommended driving information of the vehicle in the warning area based on the predicted pedestrian passing time data and the vehicle driving information; and generating voice using voice tokens and prosody analysis based on the recommended driving information to obtain target voice information for traffic warning. The present invention can accurately analyze the recommended driving information of the vehicle, so as to provide a more reliable traffic warning for vehicles and pedestrians.

The present invention relates to a sound and a floor walking signal control device and system that increase safety and efficiency by integrally controlling a sound signal device for a visually impaired person used for the purpose of crosswalk signal guidance and a floor walking signal device.

A method and apparatus for assisting a vehicle to stop at crosswalks and intersections by using a surround view monitor (SVM). In particular, the method includes: obtaining a front top-view image of the vehicle by using the SVM, performing a stop line detection in the front top-view image, and performing a crosswalk detection in the front top-view image in response to no detection of a stop line. The method further includes: generating a virtual stop line in response to a detection of a crosswalk, and controlling the vehicle to stop based on the detected stop line or the generated virtual stop line.

A method and apparatus for assisting a vehicle to stop at crosswalks and intersections by using a surround view monitor (SVM). In particular, the method includes: obtaining a front top-view image of the vehicle by using the SVM, performing a stop line detection in the front top-view image, and performing a crosswalk detection in the front top-view image in response to no detection of a stop line. The method further includes: generating a virtual stop line in response to a detection of a crosswalk, and controlling the vehicle to stop based on the detected stop line or the generated virtual stop line.

The present disclosure relates to a control device, a pedestrian assistance system, and a pedestrian assistance method. The control device includes a control unit that controls the display of a first crosswalk on a roadway toward a first side of the roadway and the display of a second crosswalk on the roadway toward a second side opposite to the first side of the roadway. The control unit, when a pedestrian crosses the roadway from the first side to the second side via the first and second crosswalks, disables the display of the first crosswalk from the first side toward the second side, and disables the display of the second crosswalk after the pedestrian has crossed.

The utility model provides an intelligent pedestrian crossing warning system which comprises a supporting metal frame, an extending plate, two projection curtains, three-dimensional projectors and a controller, a high-strength transverse frame is transversely fixed to the upper end of the supporting metal frame, the two three-dimensional projectors are installed on the front side and the rear side of the interior of the supporting metal frame in a staggered mode, the two projection curtains are installed on the upper end of the supporting metal frame in a staggered mode, and the controller is connected with the extending plate. The upper side of the front end of the supporting metal frame is provided with a convenient-to-disassemble plate through bolts, a controller and a language broadcasting device are installed in the convenient-to-disassemble plate, the right end of the high-strength transverse frame is horizontally and fixedly provided with an extension plate through two reinforcing inclined rods and a reinforcing strip plate, and the front side and the rear side of the lower end of the extension plate are each provided with a light barrier. The three-dimensional projection type warning structure designed by the utility model is matched with the buzzing warning device, can be used for warning the pedestrian crosswalk, is provided with the sunshade baffle, can prevent sunlight from influencing the three-dimensional projection effect, and also can shield light and rain for pedestrians, so that the practicability of the device is greatly improved, and the device is convenient to popularize and use.

Systems, devices, and methods are disclosed in which one or more light sources, detectors, processors, and controllers are configured such that light from the one or more light sources enhances the ability of a human or automated vehicle driver to identify and avoid pedestrians. The one or more light sources can provide spot illumination to a moving object or pedestrian on a road surface, with the spot illumination following the moving object or pedestrian along a portion of the road surface. The one or more light sources can project an image onto the ground or other surface. The light source can be carried by the pedestrian or on a personal vehicle used by the pedestrian. The light source can be stationary and provide illumination for a crosswalk.

A driving assistance device provided in a vehicle includes a communication device that receives crosswalk-related traffic information by performing V2X (Vehicle to Everything) communication with a signal controller, and a controller that identifies whether a pedestrian is present in a crosswalk based on the crosswalk-related traffic information, and when the pedestrian is present in the crosswalk, determines a time point at which to provide the crosswalk-related traffic information to a driver based on driving information of a vehicle and driver age information, and provides the crosswalk-related traffic information to the driver at the determined time point.

In various examples, one or more deep neural networks (DNNs) are executed to regress on control points of a curve, and the control points may be used to perform a curve fitting operation—e.g., Bezier curve fitting—to identify landmark locations and geometries in an environment. The outputs of the DNN(s) may thus indicate the two-dimensional (2D) image-space and / or three-dimensional (3D) world-space control point locations, and post-processing techniques—such as clustering and temporal smoothing—may be executed to determine landmark locations and poses with precision and in real-time. As a result, reconstructed curves corresponding to the landmarks—e.g., lane line, road boundary line, crosswalk, pole, text, etc.—may be used by a vehicle to perform one or more operations for navigating an environment.

To provide a driving assist system capable of preventing a vehicle from coming into contact with an obstacle when the vehicle makes a curving motion at an intersection.SOLUTION: A driving assist system that can communicate with a monitoring system which monitors each of crosswalks laid along the perimeter of an intersection and detects an obstacle in the crosswalk includes a motion prediction unit that predicts a curving motion at the intersection of the vehicle, a contact prediction unit that, when the curving motion at the intersection of the vehicle is predicted by the motion prediction unit, predicts a contact of the vehicle with an obstacle in the crosswalk in the curving direction of the vehicle, and a speed management unit that, when the contact of the vehicle with the obstacle in the crosswalk in the curving direction is predicted by the contact prediction unit, performs safety processing relevant to deceleration of the vehicle.SELECTED DRAWING: Figure 5

The lifting mechanism comprises a stand column, a lifting module and a driving module, the end, close to the ground, of the lifting module is provided with a hanging module used for hanging the bicycle, and the end, away from the ground, of the lifting module is hinged to the driving module; during use, the driving module is started to control the retraction or extension of the lifting module, so that the bicycles are lifted to a vertical parking state or a horizontal bicycle taking state from the lower part, an existing parking mode of placing the bicycles on the ground is replaced by a mode of vertically hanging the bicycles in the air, the occupation of a pedestrian crossing is reduced, and meanwhile, the effect of tidy placement can be realized.

In the present invention, when a vehicle (V1) is to turn right or left at an intersection (C) in which traffic lights (TL1, TL2) and a crosswalk (Z2) are provided, the vehicle (V1) stops before the intersection (C) in accordance with a stop signal displayed by the traffic lights (TL1, TL2). When there is no other vehicle that turning right or left in the same direction as the travel direction of the vehicle (V1) in front of the vehicle (V1), a detection area (A1) for detecting a pedestrian (H1) that can enter the crosswalk (Z2) in the travel direction is set. When the pedestrian (H1) is present in the detection area (A1) and the stop signal displayed by the traffic lights (TL1, TL2) is switched to a proceed signal, the stopped state of the vehicle (V1) is maintained for a predetermined time from the display of the proceed signal, or the vehicle (V1) is made to start and travel to a target stop position in front of the crosswalk (Z2) at a predetermined acceleration before the elapse of the predetermined time from the display of the proceed signal.

Disclosed is a smart traffic-light guidance system for a crosswalk. A smart traffic-light guidance system for a crosswalk, according to an embodiment of the present disclosure, includes: a post in the shape of a pillar; a light-emitting diode (LED) module provided at the lower end of the post to emit LED beams toward the ground in a direction parallel to a pedestrian stop line of the crosswalk and / or a direction perpendicular thereto; an LED display device provided on the back or front of the post; a plurality of types of sensors provided on one side of the exterior surface of the post to detect information related to the surrounding environment of the post; a voice output module provided on the other side of the exterior surface of the post to output messages to pedestrians and / or drivers; and at least one processor for controlling the LED module, the LED display device, the plurality of types of sensors, and the voice output module.

The invention discloses a YOLOv4-Tiny vehicle-to-person detection method based on an improved domain adaptive algorithm of class alignment. The method has general universality in a vehicle-to-pedestrian detection scene, and is applied to a scene that whether a vehicle on a pedestrian crosswalk delivers a pedestrian or not under a foggy weather condition. A conventional vehicle-to-person detection algorithm is low in efficiency and low in accuracy under a heavy fog condition, and the detection method is easily influenced by the installation angle of a camera. In order to solve the problem of a detection algorithm, an upper sampling layer is added in a CSPDarknet53 network in YOLOv4-Tiny, and a domain alignment module with a DANN network is added; in addition, a layered domain classifier is constructed in a plurality of middle layers of the backbone network, and the improved detection algorithm has certain universality and transportability for vehicle and pedestrian detection in a heavy fog environment. In order to solve the problem of misrecognition caused by the angle of a camera, lane information is divided, area IDs are named, the IDs are assigned to vehicles and pedestrians respectively, and then whether the IDs of the vehicles and the pedestrians are equal or not is judged to judge whether the vehicles give the pedestrians or not. According to the YOLOv4-Tiny vehicle-to-person detection method improved based on the domain adaptive algorithm of class alignment, the detection speed is improved to a certain extent, and the detection accuracy is also obvious.

The invention relates to the technical field of traffic, in particular to an intersection anti-collision early warning system and an intersection anti-collision early warning device based on intelligent traffic. The vehicle peak influence degree of the intersection in each preset second time period is determined, the comprehensive congestion performance degree of the intersection at the current moment is determined by combining the number of vehicles running on each lane, the average vehicle running speed and the total green light turn-on time, and the traffic congestion performance degree of the intersection at the current moment is determined by combining the difference of the number of people passing through the pedestrian crosswalk at different moments in the green light turn-on time period. And determining a collision risk index at the current moment according to the number difference of the motor vehicles and the number difference of the motor vehicles at the same moment of the adjacent lanes of the intersection, and performing intersection anti-collision early warning. According to the invention, the timeliness and accuracy of anti-collision early warning at the intersection are improved.

This radio wave sensor setting assistance device comprises: an acquisition unit that acquires a movement trajectory of one or more objects moving on a road including a crosswalk, the movement trajectory being detected by a radio wave sensor; an identification unit that identifies, from the movement trajectory of the one or more objects acquired by the acquisition unit, a target movement trajectory of a target object that moves continuously in a specific movement pattern; a first determination unit that determines, on the basis of the target movement trajectory in a coordinate space set in the radio wave sensor, a definition point that defines a detection area corresponding to the crosswalk in the coordinate space; and a second determination unit that determines the detection area in the coordinate space on the basis of the definition point determined by the first determination unit.