-
公开(公告)号:US11935213B2
公开(公告)日:2024-03-19
申请号:US18183173
申请日:2023-03-14
发明人: Dengwang Li , Pu Huang , Tingxuan Hong , Jie Xue , Hua Lu , Xueyao Liu , Baolong Tian , Changming Gu , Bin Jin , Xiangyu Zhai
CPC分类号: G06T5/002 , G06T7/0012 , G06T2207/20084 , G06T2207/20172 , G06T2207/30092
摘要: A laparoscopic image smoke removal method based on a generative adversarial network, and belongs to the technical field of computer vision. The method includes: processing a laparoscopic image sample to be processed using a smoke mask segmentation network to acquire a smoke mask image; inputting the laparoscopic image sample to be processed and the smoke mask image into a smoke removal network, and extracting features of the laparoscopic image sample to be processed using a multi-level smoke feature extractor to acquire a light smoke feature vector and a heavy smoke feature vector; and acquiring, according to the light smoke feature vector, the heavy smoke feature vector and the smoke mask image, a smoke-free laparoscopic image by filtering out smoke information and maintaining a laparoscopic image by using a mask shielding effect. The method has the technical effects of robustness and ability of being embedded into a laparoscopic device for use.
-
公开(公告)号:US20230377097A1
公开(公告)日:2023-11-23
申请号:US18183173
申请日:2023-03-14
发明人: Dengwang Li , Pu Huang , Tingxuan Hong , Jie Xue , Hua Lu , Xueyao Liu , Baolong Tian , Changming Gu , Bin Jin , Xiangyu Zhai
CPC分类号: G06T5/002 , G06T7/0012 , G06T2207/20084 , G06T2207/20172 , G06T2207/30092
摘要: A laparoscopic image smoke removal method based on a generative adversarial network, and belongs to the technical field of computer vision. The method includes: processing a laparoscopic image sample to be processed using a smoke mask segmentation network to acquire a smoke mask image; inputting the laparoscopic image sample to be processed and the smoke mask image into a smoke removal network, and extracting features of the laparoscopic image sample to be processed using a multi-level smoke feature extractor to acquire a light smoke feature vector and a heavy smoke feature vector; and acquiring, according to the light smoke feature vector, the heavy smoke feature vector and the smoke mask image, a smoke-free laparoscopic image by filtering out smoke information and maintaining a laparoscopic image by using a mask shielding effect. The method has the technical effects of robustness and ability of being embedded into a laparoscopic device for use.
-