The disclosure provides a parking space detection method and device, a vehicle, and a storage medium. The method includes: separately inputting an obtained current frame image into a pre-trained parking space detection model, a pre-trained obstacle detection model, and a pre-trained scenario detection model, to obtain a parking space prediction result, an obstacle prediction result, and a scenario prediction result; determining, based on a detected positional relationship between any target parking space and a vehicle-mounted camera, whether the target parking space is a parking space where the vehicle-mounted camera is located; performing, if yes, verification on a parking space prediction result of the target parking space by using an obstacle prediction result and a scenario prediction result, to obtain a single-frame prediction result of the target parking space; and performing, if no, verification on a parking space prediction result of the target parking space by using a scenario prediction result, to obtain a single-frame prediction result of the target parking space. In this way, after the verification based on the plurality of verification mechanisms, a highly precise parking space detection result is given in a complex scenario, and a precise prediction result is given while the vehicle does not need to pass the target parking space completely, which improves a parking space release rate.

A vehicle safety system and technique are described. In one example, a vehicle safety system communicably coupled to a vehicle, comprises processing circuitry coupled to a camera unit and a LiDAR sensor, the processing circuitry to execute logic operative to analyze an image captured by one or more cameras to identify predicted regions of road damage, correlate LiDAR sensor data with the predicted regions of road damage, analyze the LiDAR sensor data correlated with the predicted regions of road damage to identify regions of road damage in three-dimensional space; and output one or more indications of the identified regions of road damage, wherein the processing circuitry is coupled to an interface to the vehicle, the processing circuitry to output an identification of road damage.

An in-vehicle detection device is mounted on a vehicle. The in-vehicle detection device includes a camera configured to capture a first range around the vehicle as the capturing range, a sensor different in type from the camera and configured to measure a second range as the measurement range with the second range overlapping with at least a part of the first range, and a processor configured to perform detection processing on an image captured by the camera. The processor is configured to identify a first area that is included in the image and is excluded from the target of the detection processing based on the measurement result of the sensor and is configured to perform the detection processing on a second area that is included in the image and is not included in the first area.

A vehicular vision system includes a camera and a radar sensor disposed at the equipped vehicle. The system includes an electronic control unit (ECU) and, as the equipped vehicle travels along a road, the ECU, via processing of image data and processing of sensor data, determines other vehicles present on the road ahead of the equipped vehicle. The ECU, responsive to determining the presence of a plurality of other vehicles present on the road, fuses the image data captured by the camera and the sensor data captured by the radar sensor. The ECU, based on the fused data, determines a threat level for each vehicle of the plurality of other vehicles and, when the threat level for one or more vehicles of the plurality of other vehicles exceeds a threshold value, generates a braking command. The ECU transmits the braking command to a braking system of the equipped vehicle.

A vehicular control system includes a camera and an electronic control unit (ECU) that processes image data captured by the camera. The ECU, via processing of the image data, determines lane information of a traffic lane. The lane information includes lane boundaries. The ECU also determines presence of other vehicles on the road ahead of the equipped vehicle. The ECU, responsive to determining presence of a target vehicle ahead of the equipped vehicle, and at least in part via processing by the image data, predicts a change in velocity of the target vehicle relative to the equipped vehicle. The ECU, responsive to determining the lane information and responsive to predicting the change in velocity of the target vehicle, generates longitudinal and lateral commands for centering the vehicle within the traffic lane and maintaining a threshold distance between the equipped vehicle and the target vehicle.

A method for tracking an at least partially occluded object. The method includes recognizing a non-occluded portion of the at least partially occluded object in an input image; generating a simulated image of the at least partially occluded object based on features of the non-occluded portion extracted from the input image; determining first coordinates of the at least partially occluded object in a first coordinate system; and converting the first coordinates of the at least partially occluded object in the first coordinate system into second coordinates in a second coordinate system defined in a display apparatus.

An apparatus for providing an around view comprises: first and second cameras for acquiring first and second image information; and a processor. The processor can generate an around view image including a first area including a subject overlapping area and a second area excluding the subject overlapping area, on the basis of first and second images. The subject overlapping area is disposed between first and second boundary lines in the first and second images. The first boundary line is located in the first area, and the second boundary line adjoins the second area. If it is predicted that a first object will pass through the second boundary line due to the first object approaching within a predetermined distance thereto, the processor can generate an around view image in which the second area is changed so that the second area includes the subject overlapping area.

Systems and methods are disclosed herein for tracking a vulnerable road user (VRU) regardless of occlusion. In an embodiment, the system captures a series of images including the VRU, and inputs each of the images into a detection model. The system receives a bounding box for each of the series of images of the VRU as output from the detection model. The system inputs each bounding box into a multi-task model, and receives as output from the multi-task model an embedding for each bounding box. The system determines, using the embeddings for each bounding box across the series of images, an indication of which of the embeddings correspond to the VRU.

A vehicular driving assist system includes a rearward viewing camera, a driver-side camera, a passenger-side camera and at least one radar sensor. Image data captured by the cameras is provided to a control and radar data captured by the radar sensor is provided to the control. The control processes the provided captured data to determine a potential hazard presented by rear-approaching traffic. The control outputs video image data for display by a display device of the equipped vehicle. The display device includes a video display screen that displays video images for viewing by a driver of the equipped vehicle during operation of the equipped vehicle. The control processes provided captured image data and provided captured radar data to alert the driver to the determined potential hazard presented by the rear-approaching traffic in the side traffic lane adjacent to the traffic lane being traveled by the equipped vehicle.

An image processing apparatus (12) has a processing device (122) for executing, on a first image (111w) captured by a first imaging device (11w) imaging a first imaging area and a second image (111t) captured by a second imaging device (11t) imaging a second imaging area, an image recognition processing for recognizing a target in the first image and the second image, the processing device executes the image recognition processing on a non-overlapped image part (113w) of the first image without executing it on a overlapped image part (112w) of the first image when the processing device executes the image recognition processing on the first image, the non-overlapped image part includes a non-overlapped area at which the first imaging area does not overlap with the second imaging area, the overlapped image part includes a overlapped area at which the first imaging area overlaps with the second imaging area.