文献类型：会议论文

英文题名：An adaptive dead fish detection approach using SSD-MobileNet

作者：Yu, Guoyan[1,2];Wang, Lin[3];Hou, Mingxin[1,2];Liang, Yicha[1,4];He, Taihua[1,2]

机构：[1]Guangdong Ocean Univ, Sch Mech & Power Engn, Zhanjiang, Peoples R China;[2]Southern Marine Sci & Engn Guangdong Lab Zhanjian, Zhanjiang, Peoples R China;[3]Guangdong Ocean Univ, Sch Mech & Power Engn, Guangdong Prov Ocean Equipment & Mfg Engineer Tec, Zhanjiang, Peoples R China;[4]Guangdong Prov Ocean Equipment & Mfg Engineer Tec, Zhanjiang, Peoples R China

会议论文集：Chinese Automation Congress (CAC)

会议日期：NOV 06-08, 2020

会议地点：Shanghai, PEOPLES R CHINA

语种：英文

外文关键词：SSD-Mobile Net; real-time object detection; Net Adapt; dead fish

外文摘要：Aiming at the difficulty in the recognition of dead fish in a large cage, a method of detecting dead fish on water surface based on SSD-MobileNet is proposed. In this paper, the models of SSD-MobileNet V1, V2, and V3 are compared, which are suitable for an embedded mobile terminal. Through theoretical and experimental analysis, it has been proved that SSD-MobileNet V3 is not only real-time object detection algorithm, but also a new architecture combining hardware network architecture search (NAS) and NetAdapt. SSD-MobileNet V3 realizes the cooperation between automatic search algorithm and network design, and the complementary method improves the overall technical level.