Automatic driving laser repositioning method and system based on point cloud descriptor

The invention discloses an automatic driving laser repositioning method and system based on a point cloud descriptor, and belongs to the technical field of automatic driving. The automatic driving laser repositioning device provided by the invention comprises a laser mapping module used for constructing a global feature point cloud map; the descriptor construction and matching module is used for constructing a point cloud descriptor database; the pose optimization module is used for obtaining a candidate key frame set and a current frame pose set when the automatic driving vehicle begins to be positioned or the positioning is lost, and then calculating the current vehicle pose predicted by each candidate key frame as a matching initial value; and a normal distribution transformation method is utilized to match the current frame with a global feature point cloud map provided by the laser mapping module, a matching initial value is optimized, an iterative nearest point algorithm is utilized ...

Visual SLAM (Simultaneous Localization and Mapping) system and method for autonomous vehicle

The invention discloses a visual SLAM (Simultaneous Localization and Mapping) system and method for an autonomous vehicle. The system comprises an image preprocessing module, a multi-target tracking module, a visual odometer module, an object state updating module and a rear-end optimization module. The method comprises the following steps: S1, preprocessing an image through an instance segmentation network; s2, judging the dynamic state and the static state of the object; s3, estimating the pose of the initial camera; s4, removing the dynamic object; and S5, executing an optimization strategy on the image key frame. The method has the beneficial effects that in a visual image, efficient dynamic object filtering can be realized, mapping ghosts are effectively reduced, the accuracy and robustness of positioning are improved, and the applicability of an automatic driving vehicle in a dynamic environment can be improved.

Loader weighing apparatus with GPRS data transmission

Automatic calibration method for vehicle-mounted binocular camera and GNSS/IMU

The invention relates to the technical field of automatic driving, and particularly discloses an automatic calibration method for a vehicle-mounted binocular camera and a GNSS/IMU (Global Navigation Satellite System/Inertial Measurement Unit), which comprises the following steps: determining an initial conversion matrix from the GNSS/IMU to the binocular camera; when the vehicle where the GNSS/IMU and the binocular camera are located travels in the first direction, a first measurement value of the GNSS/IMU is obtained, and the pose of the binocular camera is determined according to the first measurement value of the GNSS/IMU and the initial conversion matrix; constructing a first direction sparse feature map according to the binocular camera pose; when the vehicle where the GNSS/IMU and the binocular camera are located runs in the second direction, a second measurement value of the GNSS/IMU is obtained, the global pose of the binocular camera is obtained according to the sparse feature ...

Laser SLAM positioning method and device integrating target detection and tracking

The invention discloses a laser SLAM positioning method and device fusing target detection and tracking, and the method comprises the steps: receiving original laser point cloud information scanned by a laser radar sensor, and obtaining a potential dynamic object under a current radar coordinate system; after potential dynamic objects are removed, edge feature points and plane feature points are extracted, strong feature points and general feature points are screened out from the edge feature points and the plane feature points, the strong feature points and a local feature map are used for carrying out first point cloud registration, and an initial laser radar pose is obtained; performing multi-target tracking on the potential dynamic object, and attaching the same ID to the same potential dynamic object in different frames; judging whether the potential dynamic object in the current frame is a dynamic target, a target with an undetermined state or a static target through a sliding window ...

High-adaptability multi-sensor weighted fusion SLAM system and method

The invention discloses a high-adaptability multi-sensor weighted fusion SLAM system and method, and belongs to the technical field of data processing. The system comprises a data preprocessing module, a tight coupling front-end module and a mapping module. According to the multi-sensor fusion SLAM system provided by the invention, the advantages of a plurality of sensors are utilized to make up the respective defects, a weight distribution strategy is provided, weight distribution is implemented according to initialization detection, degradation detection and vehicle slip detection, weighted joint optimization is performed, the effect of nonlinear optimization is improved, the adaptability to the environment is high, and the method is suitable for large-scale popularization and application. The method can cope with the problems of laser radar degradation environment, vehicle slippage working condition, instability in the initial stage of mapping and the like, and is stable in positioning ...

Method and device for measuring rotation angle of external rotary table of portal crane for port

The invention discloses a method and device for measuring the rotation angle of an external rotary table of a portal crane for a port, and the method comprises the steps: 1, arranging a camera, an IMU and a magnetometer on the rotary table of the portal crane for the port, and arranging a plurality of visual labels at the circumferential direction of the rotary table at intervals; 2, according to magnetometer measurement data, IMU measurement data and image data of the visual label when the rotary table is in a static state, the posture of the visual label in a geographic coordinate system is obtained; step 3, according to the IMU measurement data, the magnetometer measurement data and the camera image data, according to whether the camera image data detects a visual label, obtaining a rotary table rotation angle of the rotary table in a static state; and step 4, according to the IMU measurement data, the magnetometer measurement data and the camera image data, according to the situation ...