Abstract: Presented are systems and methods for improving speed and quality of real-time per-pixel depth estimation of scene layouts from a single image by using a 3D end-to-end Convolutional Spatial Propagation Network (CSPN). An efficient linear propagation model performs propagation using a recurrent convolutional operation. The affinity among neighboring pixels may be learned through a deep convolutional neural network (CNN). The CSPN may be applied to two depth estimation tasks, given a single image: (1) to refine the depth output of existing methods, and (2) to convert sparse depth samples to a dense depth map, e.g., by embedding the depth samples within the propagation procedure. For stereo depth estimation, the 3D CPSN is applied to stereo matching by adding a diffusion dimension over discrete disparity space and feature scale space. This aids the recovered stereo depth to generate more details and to avoid error matching from noisy appearance caused by sunlight, shadow, and similar effects.

Abstract: A method and an apparatus for controlling an excavator are provided according to the embodiments.

Abstract: Embodiments of the present disclosure relate to a method and apparatus for controlling equipment. The method includes: acquiring an electrical signal collected by a displacement sensor; determining a displacement of a movable rod of a hydraulic cylinder relative to a cylinder tube of the hydraulic cylinder according to the electrical signal; determining, according to the displacement, a rotating angle of a mechanical arm connected to the movable rod relative to a mechanical arm connected to the cylinder tube; and controlling equipment according to the rotating angle.

Abstract: Embodiments of the present disclosure relate to a three-dimensional reconstruction method and apparatus for a material pile, an electronic device, and a computer-readable medium. The method may include: acquiring, in response to an instruction for controlling an excavator body of an excavator to rotate to transport materials being detected, a sequence of depth images of an excavated material pile collected by a binocular camera provided on a side of the excavator; and performing three-dimensional reconstruction based on the sequence of depth images of the material pile, to generate a three-dimensional model of the material pile.

Abstract: Embodiments of the present disclosure relate to a method and apparatus for selecting a target excavating point. The method includes: acquiring a height map of a material pile; discretizing the height map to obtain an excavating point set; acquiring an excavating trajectory set of an excavating point in the excavating point set; and selecting a target excavating point based on the excavating trajectory set of the excavating point in the excavating point set.

Abstract: Embodiments of the present disclosure relate to a method and apparatus for controlling an excavator to excavate. The method includes: acquiring a two-dimensional image of a material pile; generating a three-dimensional model of the material pile based on the two-dimensional image; analyzing the three-dimensional model to determine a target excavating point and a target excavating trajectory of the material pile; and controlling an excavator to excavate a material at the target excavating point along the target excavating trajectory.

Abstract: The present disclosure provides a method and device for acquiring 3D information of an object. The method includes: extracting two-dimensional (2D) key points of the object based on the image, and determining a candidate 3D model set matching the image; determining a plurality of first reference attitudes and positions of each candidate 3D model according to the 3D key points and the 2D key points; acquiring a plurality of reprojection error values between each candidate 3D model and the object at the plurality of first reference attitudes and positions; determining a first target attitude and position and a first target 3D model corresponding to a minimum reprojection error value in the first reprojection error value set; and acquiring the 3D information of the object based on the first target attitude and position and the first target 3D model.

Abstract: Embodiments of the present disclosure relate to a method and apparatus for generating a driving path. The method includes acquiring a two-dimensional image of a driving site obtained by a camera provided on an unmanned aerial vehicle through aerial photography, and a two-dimensional image of a site in front of a vehicle photographed by a camera provided on the vehicle; generating a global map based on the two-dimensional image of the driving site, and generating a local map based on the two-dimensional image of the site in front of the vehicle; and performing path planning based on the global map and the local map, to generate a global path and a local path, the local path following a direction of the global path.

Abstract: Embodiments of the present disclosure relate to a method and apparatus for outputting information. The method includes: acquiring a target excavating trajectory, the target excavating trajectory including at least two sub-trajectories; determining trajectory parameters of the at least two sub-trajectories; determining, based on the trajectory parameters, positions of a plurality of control points; and outputting the positions of the plurality of control points.

Abstract: Embodiments of the present disclosure disclose a control system and a control method of an unmanned engineering machinery. The system includes at least a slave computer, a master computer and an execution device. The slave computer is configured to receive a current sensing value fed back by a sensing device in the unmanned engineering machinery, and to send the current sensing value to the master computer. The master computer is configured to generate a control instruction according to the current sensing value and a predetermined target sensing value of the sensing device, and to send the control instruction to the execution device through the slave computer.

Abstract: Embodiments of the present disclosure disclose a fixing apparatus of a sensing system and a fixing method of a sensing system. The fixing apparatus includes an internal fixing module and an external fixing module, in which, the internal fixing module is configured to fix a sensing device in a sensing system of an unmanned construction machinery to the external fixing module in a predetermined fixing manner; and the external fixing module is configured to control the sensing device in the sensing system to perform an environment sensing on a target area of the unmanned construction machinery in a predetermined control manner.

Abstract: Embodiments of the present disclosure disclose a method and apparatus for recognizing a face. A specific embodiment of the method includes: acquiring at least two facial images of a to-be-recognized face under different illuminations using a near-infrared photographing device; generating at least one difference image based on a brightness difference between each two of the at least two facial images; determining a facial contour image of the to-be-recognized, face based on the at least one difference image; inputting the at least two facial images, the at least one difference image, and the facial contour image into a pre-trained real face prediction value calculation model to obtain a real face prediction value of the to-be-recognized face; and outputting prompt information for indicating successful recognition of a real face, in response to determining the obtained real face prediction value being greater than a preset threshold.

Abstract: Embodiments of the present disclosure relate to a device for detecting a rotary angle and an excavator. The device is used for the excavator. The device can include: a synchronous belt, arranged around a rotating shaft of a slewing mechanism of the excavator, a tooth-shaped surface of the synchronous belt being away from a surface of the rotating shaft; a transmission part, engaged with the tooth-shaped surface of the synchronous belt and arranged on a supporting base; an angle detection part, in transmission connection to the transmission part; and the supporting base, connected to a chassis of the excavator.

Abstract: Embodiments of the present disclosure provide a method and apparatus for generating information. A method may include: selecting a three-dimensional object model from a preset three-dimensional object model set based on a to-be-matched object image in a target two-dimensional image; determining, based on a normal vector of a ground plane of the target two-dimensional image, a plane equation of ground corresponding to the normal vector of the ground plane in a three-dimensional space; adjusting a rotation parameter and a translation parameter of the three-dimensional object model in the plane characterized by the plane equation; and generating, in response to determining that a contour of the adjusted three-dimensional object model matches a contour of the to-be-matched object image in the target two-dimensional image, three-dimensional information of an object corresponding to the to-be-matched object image based on the adjusted three-dimensional object model.

Abstract: A method, device and a computer-readable storage medium for optimizing simulation data are provided. The method for optimizing simulation data can include: inputting the simulation data generated by a simulator to a first generative adversarial network comprising a migration model; and optimizing the simulation data generated by the simulator with the migration model to generate optimized simulation data. In an embodiment of the present application, the simulation data is optimized by the generative adversarial network to enable the simulation data closer to the real data in representation. Therefore, the quality and accuracy of the simulation data can be ensured, the validity and reliability of the simulation data can be improved at least to some extent, and the cost for constructing the simulator can also be reduced.

Abstract: A simulation data augmentation method, a simulation data augmentation device and a simulation data augmentation terminal are provided according to embodiments of the present application. The method includes: acquiring a point cloud based on a plurality of frames, wherein the point cloud includes a plurality of obstacles labeled with real labeling data; dividing the point cloud into a plurality of preset regions, wherein each of the preset regions includes at least one obstacle; and adjusting the obstacle based on the real labeling data of the obstacle in the preset regions to obtain simulation data.

Abstract: A method and system for simulating a distribution of obstacles are provided. The method includes: acquiring a plurality of point clouds of a plurality of frames, wherein each point cloud includes a plurality of original obstacles; acquiring real labeling data of an acquisition vehicle, and obtaining data of a simulation position of the acquisition vehicle based on the real labeling data and a movement rule of the acquisition vehicle; determining the number of obstacles to be simulated based on the data of the simulation position of the acquisition vehicle; selecting the determined number of obstacles to be simulated, from a range with the simulation position of the acquisition vehicle as a center, wherein the range is less than or equal to a maximum scanning range of the vehicle; and acquiring real labeling data of the selected obstacles, and obtaining a position distribution of the selected obstacles.

Abstract: A data augmentation method, device are provided according to embodiments of the present application. The method includes: acquiring a point cloud of a frame, the point cloud comprising a plurality of original obstacles; obtaining a plurality of position voids by removing the original obstacles from the point cloud, and filling the position voids to obtain a real background of the point cloud; arranging a plurality of new obstacles labeled by labeling data, in the real background of the point cloud; and adjusting the new obstacles based on the labeling data of the new obstacles to obtain layout data of the new obstacles. The amount of real data is increased, and a diversity of the real data is improved.

Abstract: Embodiments of an obstacle distribution simulation method, device and terminal based on a probability graph are provided. The method can include: acquiring a plurality of point clouds of a plurality of frames; acquiring real labeling data of an acquisition vehicle at vehicle labeled positions, and acquiring data of a simulation position of the acquisition vehicle; determining the number of obstacles to be simulated at a position to be simulated; extracting real labeling data of the obstacles, and constructing a labeling data set; dividing the labeling data set into a plurality of grids and calculating occurrence probabilities of the plurality of obstacles; selecting the determined number of obstacles to be simulated according to the occurrence probabilities; and acquiring a position distribution of the selected obstacles to be simulated for the position to be simulated based on the real labeling data of the selected obstacles to be simulated.

Abstract: An obstacle distribution simulation method, device and terminal based on multiple models. The method can include: acquiring a point cloud, the point cloud including a plurality of obstacles labeled with real labeling data; extracting the real labeling data of the obstacles, and training a plurality of neural network models based on the real labeling data of the obstacles; extracting unlabeled data in the point cloud, inputting the unlabeled data into the neural network models, and outputting a plurality of prediction results. The plurality of prediction results can include a plurality of simulated obstacles with attribute data; selecting at least one simulated obstacle based on the plurality of prediction results; and inputting the attribute data of the selected simulated obstacle into the neural network models to obtain position coordinates of the simulated obstacle, and further obtain a position distribution of the simulated obstacle.