http://scholars.ntou.edu.tw/handle/123456789/24257
Title: | Anomalous behavior recognition of underwater creatures using lite 3D full-convolution network | Authors: | Jung-Hua Wang Te-Hua Hsu Yi-Chung Lai Yan-Tsung Peng Zhen-Yao Chen Ying-Ren Lin Chang-Wen Huang Chung-Ping Chiang |
Issue Date: | 13-Nov-2023 | Publisher: | Springer Nature | Journal Volume: | 13 | Start page/Pages: | 20051 | Source: | Scientific Reports | Abstract: | Global warming and pollution could lead to the destruction of marine habitats and loss of species. The anomalous behavior of underwater creatures can be used as a biometer for assessing the health status of our ocean. Advances in behavior recognition have been driven by the active application of deep learning methods, yet many of them render superior accuracy at the cost of high computational complexity and slow inference. This paper presents a real-time anomalous behavior recognition approach that incorporates a lightweight deep learning model (Lite3D), object detection, and multitarget tracking. Lite3D is characterized in threefold: (1) image frames contain only regions of interest (ROI) generated by an object detector; (2) no fully connected layers are needed, the prediction head itself is a flatten layer of 1 × |
URI: | http://scholars.ntou.edu.tw/handle/123456789/24257 | DOI: | 10.1038/s41598-023-47128-2 |
Appears in Collections: | 水產養殖學系 電機工程學系 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.