首页|Findings from Harbin Engineering University Broaden Understanding of Robotics (R eal-Time Underwater Fish Detection and Recognition Based on CBAM-YOLO Network wi th Lightweight Design)
Findings from Harbin Engineering University Broaden Understanding of Robotics (R eal-Time Underwater Fish Detection and Recognition Based on CBAM-YOLO Network wi th Lightweight Design)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Research findings on robotics are disc ussed in a new report. According to news reporting out of Harbin, People's Repub lic of China, by NewsRx editors, research stated, "More and more underwater robo ts are deployed to investigate marine biodiversity autonomously, and tools are n eeded by underwater robots to discover and acknowledge marine life." Funders for this research include National Natural Science Foundation of China. The news reporters obtained a quote from the research from Harbin Engineering Un iversity: "This paper has proposed a convolutional neural network-based method f or intelligent fish detection and recognition with a dataset used for training a nd testing generated and augmented from an open-source Fish Database regarding 6 different types. Firstly, to improve image quality, a hybrid image enhancement algorithm is used to preprocess underwater images with a weighted fusion strateg y of multiple traditional methodologies and comparisons have been made to prove the effectiveness according to various indexes. Secondly, to increase detection and recognition accuracy, different attention modules are integrated into the YO LOv5m network structure and the convolutional block attention module(CBAM) has outperformed other modules in recall rate and mAP while maintaining the capabilit y of real-time processing. Lastly, to meet real-time requirements, lightweight a djustments have been made to CBAM-YOLOv5m with the GSConv module and C3Ghost mod ule and a nearly 25% reduction in network parameters and a 20% reduction in computational consumption are obtained. Besides, the lightweight ne twork has realized better accuracy than YOLOv5m."
Harbin Engineering UniversityHarbinPeople's Republic of ChinaAsiaEmerging TechnologiesMachine LearningNano-r obotRobotics
NETL
NSTL
