The present teaching relates to method, system, medium, and implementation of determining depth information in autonomous driving. Stereo images are first obtained from multiple stereo pairs selected from at least two stereo pairs. The at least two stereo pairs have stereo cameras installed with the same baseline and in the same vertical plane. Left images from the multiple stereo pairs are fused to generate a fused left image and right images from the multiple stereo pairs are fused to generate a fused right image. Disparity is then estimated based on the fused left and right images and depth information can be computed based on the stereo images and the disparity.

A method and apparatus for recognizing an object are provided, the method including extracting a feature from an input image and generating a feature map in a neural network. In parallel with the generating of the feature map, a region of interest (ROI) corresponding to an object of interest is extracted from the input image, and a number of object candidate regions used to detect the object of interest is determined based on a size of the ROI. The object of interest is recognized from the ROI based on the number of object candidate regions in the neural network.

The application provides an obstacle detecting method and obstacle detecting apparatus based on an unmanned vehicle, and a device, and a storage medium, where the method includes obtaining point cloud data collected by a detecting device, projecting the point cloud data onto a two-dimensional plane to obtain a two-dimensional projection grid graph, where the two-dimensional projection grid graph has multiple grids and two-dimensional data, and two-dimensional data is data obtained after the point cloud data is projected; generating multiple straight lines according to the two-dimensional projection grid graph, where each of the multiple straight lines has two-dimensional data, and each straight line has parameter information which represents the relationship between the straight line and other straight lines in the multiple straight lines; and determining orientation information of the obstacle according to the two-dimensional data and the parameter information of each of the multiple straight lines.

Systems and methods are provided for navigating a host vehicle. A processing device may be programmed to receive an image representative of an environment of the host vehicle; determine a planned navigational action for the host vehicle; analyze the image to identify a target vehicle travelling toward the host vehicle; determine a next-state distance between the host vehicle and the target vehicle that would result if the planned navigational action taken; determine a stopping distance for the host vehicle based on a braking rate, a maximum acceleration capability, and a current speed of the host vehicle; determine a stopping distance for the target vehicle based on a braking rate, a maximum acceleration capability, and a current speed of the target vehicle; and implement the planned navigational action if the determined next-state distance is greater than a sum of the stopping distances for the host vehicle and the target vehicle.

The present disclosure provides a method for processing at least one image comprising inputting the image to at least one neural network, the at least one network being configured to deliver, for each pixel of a group of pixels belonging to an object of a given type visible on the image, an estimation of object parameters that are parameters of the object. The method further comprising processing the estimations of the object parameters using an instance segmentation mask identifying instances of objects having the given type.

A method and apparatus for detecting an obstacle, an electronic device, and a storage medium. A specific implementation of the method includes: detecting, by a millimeter-wave radar, position points of candidate obstacles in front of a vehicle; detecting, by a camera, a left road boundary line and a right road boundary line of a road on which a vehicle is located; separating the position points of the candidate obstacles according to the left road boundary line and the right road boundary line of the road on which the vehicle is located, and extracting position points between the left road boundary line and the right road boundary line; projecting the position points between the left road boundary line and the right road boundary line onto an image; and detecting, based on projection points of the position points on the image, a target obstacle in front of the vehicle.

The present application provides a mobile robot, a control method and control system of the mobile robot. The control method comprises the following steps: acquiring a depth image obtained through photography of the at least one image acquisition device; wherein, the depth image contains a depth image of the target obstacle; identifying an obstacle type of the target obstacle from the depth image; controlling a navigation movement and/or behavior of the mobile robot based on an acquired positional relationship between the target obstacle and the mobile robot, and the identified obstacle type. In the present application, the type of the target obstacle can be detected effectively, and the behavior of the mobile robot can be controlled based on the detection result correspondingly.

Systems and methods are provided for navigating a host vehicle. At least one processing device may be programmed to receive an image representative of an environment of the host vehicle; determine a planned navigational action for the host vehicle; analyze the image to identify a target vehicle in the environment of the host vehicle; determine a next-state lateral distance between the host vehicle and the target vehicle that would result if the planned navigational action was taken; determine a lateral braking distance for the host vehicle and the target vehicle based on a maximum yaw rate capability, a maximum change in turn radius capability, and a current lateral speed of the host vehicle and the target vehicle; and implement the planned navigational action if the determined next-state distance is greater than a sum of the lateral braking distances for the host vehicle and the target vehicle.

The present application provides a mobile robot, a control method and control system of the mobile robot. The control method comprises the following steps: acquiring a depth image obtained through photography of the at least one image acquisition device; wherein, the depth image contains a depth image of the target obstacle; identifying an obstacle type of the target obstacle from the depth image; controlling a navigation movement and/or behavior of the mobile robot based on an acquired positional relationship between the target obstacle and the mobile robot, and the identified obstacle type. In the present application, the type of the target obstacle can be detected effectively, and the behavior of the mobile robot can be controlled based on the detection result correspondingly.

In various examples, a deep neural network (DNN) is trained to accurately predict, in deployment, distances to objects and obstacles using image data alone. The DNN may be trained with ground truth data that is generated and encoded using sensor data from any number of depth predicting sensors, such as, without limitation, RADAR sensors, LIDAR sensors, and/or SONAR sensors. Camera adaptation algorithms may be used in various embodiments to adapt the DNN for use with image data generated by cameras with varying parameters—such as varying fields of view. In some examples, a post-processing safety bounds operation may be executed on the predictions of the DNN to ensure that the predictions fall within a safety-permissible range.