公开(公告)号：US11283247B2

公开(公告)日：2022-03-22

申请号：US17298607

申请日：2019-11-12

申请人： INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF SCIENCES

发明人： Guodong Yang ,  Xiaoyu Long ,  Weiqing Zhao ,  En Li ,  Zize Liang ,  Fengshui Jing ,  Han Wang ,  Hao Wang ,  Zishu Gao ,  Yunong Tian ,  Yuansong Sun ,  Sixi Lu ,  Guangyao Xu

IPC分类号： H02G1/02 ,  B25J5/02 ,  B61B7/06 ,  H02G7/16

摘要： A carrier mechanism for walking on a line includes a carrier platform constituted by a first mounting plate, a second mounting plate and a longitudinal movable plate, a walking apparatus, a clamping apparatus, a driving apparatus, and a self-balance control apparatus configured to adjust a posture of the carrier mechanism. The longitudinal movable plate is slidably arranged on the second mounting plate fixedly connected to the first mounting plate in parallel. The walking apparatus includes at least two sets of walking wheels arranged along a walking direction. The clamping apparatus is slidably arranged on the lower side of the longitudinal movable plate. The driving apparatus includes a first driving apparatus configured to drive the walking wheels to roll, and a second driving apparatus configured to drive the longitudinal movable plate to move. The clamping apparatus is driven by the longitudinal movable plate to clamp or release a to-be-inspected target.

公开(公告)号：US11429818B2

公开(公告)日：2022-08-30

申请号：US16960072

申请日：2019-12-10

申请人： INSTITUTE OF AUTOMATION, CHINESE ACADEMY OF SCIENCES

发明人： Guodong Yang ,  Yunong Tian ,  En Li ,  Zize Liang ,  Min Tan ,  Fengshui Jing ,  Zishu Gao ,  Hao Wang ,  Yuansong Sun ,  Sixi Lu

IPC分类号： G06K9/62 ,  G06N3/08 ,  G06V10/75

摘要： A multi-label object detection method based on an object detection network includes: selecting an image of an object to be detected as an input image; based on a trained object detection network, obtaining a class of the object to be detected, coordinates of a center of the object to be detected, and a length and a width of a detection rectangular box according to the input image; and outputting the class of the object to be detected, the coordinates of the center of the object to be detected, and the length and the width of the detection rectangular box. The method of the present invention can perform real-time and accurate object detection on different classes of objects with improved detection speed and accuracy, and can solve the problem of object overlapping and occlusion during the object detection.