Abstract: The present invention relates to the field of inland vessel identification and ranging technology, and discloses a method, system, medium, equipment and terminal for identifying and ranging inland vessels. In the stage of vessel identification, based on the classical YOLO-V4 network model, the MobileNetV1 network is used to replace the feature extraction network CSPDarknet53 of the YOLO-V4 model; In the stage of vessel ranging, a binocular stereo vision ranging model is established, and the FSRCNN is used for super-resolution reconstruction of the original image pairs to enhance the vessel feature information; the ORB algorithm is used to achieve feature detection and matching at the sub-pixel level to obtain the parallax value between image pairs, and the depth information of the vessel target is obtained by triangulation principle and coordinate conversion.

Abstract: The present invention relates to the field of inland vessel identification and ranging technology, and discloses a method, system, medium, equipment and terminal for identifying and ranging inland vessels. In the stage of vessel identification, based on the classical YOLO-V4 network model, the MobileNetV1 network is used to replace the feature extraction network CSPDarknet53 of the YOLO-V4 model; In the stage of vessel ranging, a binocular stereo vision ranging model is established, and the FSRCNN is used for super-resolution reconstruction of the original image pairs to enhance the vessel feature information; the ORB algorithm is used to achieve feature detection and matching at the sub-pixel level to obtain the parallax value between image pairs, and the depth information of the vessel target is obtained by triangulation principle and coordinate conversion.

Abstract: Disclosed is a coverage path planning method for multiple unmanned surface mapping vehicles, comprising: simultaneously creating submaps and an overall map; outputting its own position information and obstacle information, transmitting to BLli and updating BLlm; defining a behavior strategy list (BS); determining the BS with priority for path planning, outputting a to or th state if any criterion is satisfied; when trapped in a local optimum, updating map layers layer-by-layer going upwards, searching for tp in the corresponding layers, performing a BS determination, and outputting a tr instruction; if no target point is found even at the highest layer, checking each CSPi?{FNi,UFNi}, and determining a termination. As such, the coverage rate and coverage effect of multiple unmanned surface mapping vehicles in a complex environment can be increased, thus increasing the operational efficiency of the unmanned surface mapping vehicles.

Abstract: An optimized coverage-path planning method for a single unmanned surface mapping vessel (USMV), includes: initializing GT values of all grids as ue, pre-configuring each grid assigned value BVa0, inputting coordinates, continuing to update a pre-configured map; importing a static map according to the grids; inputting coordinates and continuing to update the pre-configured map according to the static map; outputting, by a USMV, position information ? and obstacle information ? thereof according to the pre-configured map, and starting to update the map; outputting a grid status list GT_list according to the updated map, and receiving, by a BL0-level map, input map information and USMV information, starting path planning, and outputting a target point tp to the USMV; if the solution is trapped in a local optimum at the BL0 level, updating each map level in ascending order, and searching the corresponding level for the tp.