公开(公告)号：US20220309772A1

公开(公告)日：2022-09-29

申请号：US17687664

申请日：2022-03-06

申请人： Satellite Application Center for Ecology and Environment, MEE

发明人： Jixi Gao ,  Wenming Shen ,  Mingyong Cai ,  Xinsheng Zhang ,  Wenfei Tai ,  Xuewei Shi ,  Xuhui Chen ,  Sihan Liu ,  Tong Xiao ,  Wandong Ma ,  Jing Li ,  Yuanli Shi ,  Lixia Wang ,  Hongwei Zhang ,  Zhihua Ren

IPC分类号： G06V10/80 ,  G06V10/82 ,  G06V10/762 ,  G06V20/52 ,  G06V40/20

摘要： A human activity recognition fusion method and system for ecological protection red line is disclosed. The method includes: obtaining a pre-stage remote sensing image and a post-stage remote sensing image of a target ecological protection red line region, and performing a data pre-processing; inputting the pre-processed pre-stage remote sensing image and the post-stage remote sensing image into a human activity recognition model after a pre-training; identifying a human activity pattern of the target ecological protection red line region as a first detection result; segmenting, calculating and analyzing the latest image data corresponding to the target ecological protection red line region based on a geographical country situation data to obtain a change pattern as a second detection result; and fusing the first detection result and the second detection result to obtain a change detection pattern of the target ecological protection red line region.

公开(公告)号：US12118772B2

公开(公告)日：2024-10-15

申请号：US17687664

申请日：2022-03-06

申请人： Satellite Application Center for Ecology and Environment, MEE

发明人： Jixi Gao ,  Wenming Shen ,  Mingyong Cai ,  Xinsheng Zhang ,  Wenfei Tai ,  Xuewei Shi ,  Xuhui Chen ,  Sihan Liu ,  Tong Xiao ,  Wandong Ma ,  Jing Li ,  Yuanli Shi ,  Lixia Wang ,  Hongwei Zhang ,  Zhihua Ren

IPC分类号： G06V20/52 ,  G06V10/762 ,  G06V10/80 ,  G06V10/82 ,  G06V40/20

CPC分类号： G06V10/803 ,  G06V10/762 ,  G06V10/806 ,  G06V10/82 ,  G06V20/52 ,  G06V40/20

摘要： A human activity recognition fusion method and system for ecological protection red line is disclosed. The method includes: obtaining a pre-stage remote sensing image and a post-stage remote sensing image of a target ecological protection red line region, and performing a data pre-processing; inputting the pre-processed pre-stage remote sensing image and the post-stage remote sensing image into a human activity recognition model after a pre-training; identifying a human activity pattern of the target ecological protection red line region as a first detection result; segmenting, calculating and analyzing the latest image data corresponding to the target ecological protection red line region based on a geographical country situation data to obtain a change pattern as a second detection result; and fusing the first detection result and the second detection result to obtain a change detection pattern of the target ecological protection red line region.