文献类型：期刊文献

英文题名：FMRFT: Fusion Mamba and DETR for Query Time Sequence Intersection Fish Tracking

作者：Yao, Mingyuan[1,2,3];Huo, Yukang[1,2,3];Tian, Qingbin[1,2,3];Zhao, Jiayin[1,2,3];Liu, Xiao[1,2,3];Wang, Ruifeng[4];Xue, Lin[5];Wang, Haihua[1,2,3]

第一作者：Yao, Mingyuan

通讯作者：Wang, HH[1]

机构：[1]Natl Innovat Ctr Digital Fishery, 17 Qinghua East Rd, Beijing 100083, Peoples R China;[2]Minist Agr & Rural Affairs, Key Lab Smart Farming Aquat Anim & Livestock, 17 Qinghua East Rd, Beijing 100083, Peoples R China;[3]China Agr Univ, Coll Informat & Elect Engn, 17 Qinghua East Rd, Beijing 100083, Peoples R China;[4]China Agr Univ, Coll Engn, 17 Qinghua East Rd, Beijing 100083, Peoples R China;[5]Beijing Union Univ, Smart City Coll, 97 North Fourth Ring East Rd, Beijing 100101, Peoples R China

第一机构：Natl Innovat Ctr Digital Fishery, 17 Qinghua East Rd, Beijing 100083, Peoples R China

通讯机构：[1]corresponding author), China Agr Univ, Coll Informat & Elect Engn, 17 Qinghua East Rd, Beijing 100083, Peoples R China.

年份：2025

卷号：237

外文期刊名：COMPUTERS AND ELECTRONICS IN AGRICULTURE

收录：;EI(收录号：20253018828241);Scopus(收录号：2-s2.0-105011050102);WOS:【SCI-EXPANDED(收录号:WOS:001570951200003)】；

基金：This research was supported by the Mandarin fish factory farming service project, China (202305510811525) , the Research and creation of key technologies for digital fishery intelligent equipment, China (2021TZXD006) , the Intelligent aquaculture service project of water purification fish, China (202305510810180) and the Automatic counting software system for factory breeding standard fry, China (202305410811526).

语种：英文

外文关键词：Mamba In Mamba; RT-DETR; Multi-fish tracking; Fusion MIM

摘要：Early detection of abnormal fish behavior caused by disease or hunger can be achieved through fish tracking using deep learning techniques, which holds significant value for industrial aquaculture. However, underwater reflections and some reasons with fish, such as the high similarity, rapid swimming caused by stimuli and mutual occlusion bring challenges to multi-target tracking of fish. To address these challenges, we prepare a complex multi-scenario sturgeon tracking dataset and introduce the FMRFT model, a real-time end-to-end fish tracking solution. The model incorporates the low video memory consumption Mamba In Mamba (MIM) architecture, which facilitates multi-frame temporal memory and feature extraction, thereby addressing the challenges to track multiple fish across frames. Additionally, the FMRFT model with the Query Time Sequence Intersection (QTSI) module effectively manages occluded objects and reduces redundant tracking frames using the superior feature interaction and prior frame processing capabilities of RT-DETR. This combination significantly enhances the accuracy and stability of fish tracking. Trained and tested on the sturgeon dataset, the model achieves an IDF1 score of 90.3% and a MOTA accuracy of 94.3%. Experimental results show that the proposed FMRFT model effectively addresses the challenges of high similarity and mutual occlusion in fish populations, enabling accurate tracking in factory farming environments.(Code and Datasets have been released at https://github.com/ymy1946676292/FMRFT)