A target detection method based on the fusion of prior positioning of a millimeter-wave radar and a visual feature includes: simultaneously obtaining, based on the millimeter-wave radar and a vehicle-mounted camera after being calibrated, point cloud data of the millimeter-wave radar and a camera image; performing spatial 3D coordinate transformation on the point cloud data to project transformed point cloud data onto a camera plane; generating a plurality of anchor samples based on projected point cloud data according to a preset anchor strategy, and obtaining a final anchor sample based on a velocity-distance weight of each candidate region; fusing RGB information of the camera image and intensity information of an RCS in the point cloud data to obtain a feature of the final sample; and inputting the feature of the final anchor sample into a detection network to generate category and position information of a target in a scenario.

A method is provided for classifying pixels of an image. An image comprising a plurality of pixels is captured by a sensor device. A neural network is used for estimating probability values for each pixel, each probability value indicating the probability for the respective pixel being associated with one of a plurality of predetermined classes. One of the classes is assigned to each pixel of the image based on the respective probability values to create a predicted segmentation map. For training the neural network, a loss function is generated by relating the predicted segmentation map to ground truth labels. Furthermore, an edge detection algorithm is applied to at least one of the predicted segmentation maps and the ground truth labels, wherein the edge detection algorithm predicts boundaries between objects. Generating the loss function is based on a result of the edge detection algorithm.

Systems, methods, tangible non-transitory computer-readable media, and devices associated with object association and tracking are provided. Input data can be obtained. The input data can be indicative of a detected object within a surrounding environment of an autonomous vehicle and an initial object classification of the detected object at an initial time interval and object tracks at time intervals preceding the initial time interval. Association data can be generated based on the input data and a machine-learned model. The association data can indicate whether the detected object is associated with at least one of the object tracks. An object classification probability distribution can be determined based on the association data. The object classification probability distribution can indicate a probability that the detected object is associated with each respective object classification. The association data and the object classification probability distribution for the detected object can be outputted.

A vehicle includes a sensor unit configured to acquire positional information of at least one object located in the vicinity of the vehicle, the sensor unit comprising a plurality of sensor modules. A controller is configured to determine a tracking filter based on a correspondence relationship between the plurality of sensor modules and the at least one object and to track the position of the at least one object using the positional information of the at least one object and the tracking filter.

A point cloud display method includes determining, from a first point cloud, points describing a target object, where the first point cloud describes a surrounding area of a vehicle in which the in-vehicle system is located, and the target object is to be identified by the in-vehicle system, generating a second point cloud based on the points, and displaying the second point cloud.

A photoelectric conversion apparatus includes a first semiconductor region of a first conductivity type at a first depth from a first surface, a second semiconductor region of a second conductivity type disposed at a second depth deeper than the first depth from the first surface so as to be in contact with the first semiconductor region, and a third semiconductor region of the second conductivity type extending from the first surface to a third depth shallower than the second depth and being in contact with the first semiconductor region and the second semiconductor region. The third semiconductor region has a higher impurity concentration than the second semiconductor region. A second electric potential lower than the first electric potential for a carrier of the first conductivity type is applied to the third semiconductor region. The second semiconductor region has an impurity concentration of 1×10.sup.12 [atom/cm.sup.3] or less.

Disclosed are techniques for annotating image frames using information from a light detection and ranging (LiDAR) sensor. An exemplary method includes receiving, from the LiDAR sensor, at least one LiDAR frame, receiving, from a camera sensor, at least one image frame, removing LiDAR points that represent a ground surface of the environment, identifying LiDAR points of interest in the at least one LiDAR frame, segmenting the LiDAR points of interest to identify at least one object of interest in the at least one LiDAR frame, and annotating the at least one image frame with a three-dimensional oriented bounding box of the at least one object of interest detected in the at least one image frame by projecting the three-dimensional oriented bounding boxes from the at least one LiDAR frame to the at least one image frame using cross-calibration transforms between the LiDAR sensor and the camera.

An obstacle avoiding guidance system includes a processing device and a guidance device. The processing device sets a movement range in a certain field. The guidance device is disposed on a vehicle and has a detection module, a positioning module, and a calculation module. The detection module detects the current position of the user. The positioning module detects the current position of the vehicle and generates a position signal. The calculation module compares the position signal with the movement range for controlling the vehicle to follow the user in the movement range. Therefore, the vehicle is prevented from entering an improper area and able to effectively follow the user.

A display method is applied to electronic equipment including a display assembly. A display content displayed by the display assembly includes a background and an object for reading located on the background. The display method includes: differentiating grayscales of background pixels of the background; and displaying the background based on the background pixels with the differentiated grayscales, and displaying the object for reading.

In a driving assistance device, a human body specifying unit acquires, as human body information, an image of a human body existing around a host vehicle in image data acquired by a camera. A quasi-skeleton estimation unit estimates a quasi-skeleton of the human body from the human body information. The radar or the LiDAR measures a distance to a part of the human body that corresponds to the quasi-skeleton.