首页|New Findings on Robotics from Zhejiang University Summarized (Real-time Tilapia Fillet Defect Segmentation On Edge Device for Robotic Trimming)
New Findings on Robotics from Zhejiang University Summarized (Real-time Tilapia Fillet Defect Segmentation On Edge Device for Robotic Trimming)
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-Researchers detail new data in Robotic s. According to news reporting out of Zhejiang, People's Republic of China, by N ewsRx editors, research stated, "The implementation of robotic tilapia fillet tr imming instead of manual labor is a pivotal advancement in intelligent fish proc essing, offering substantial superiority in operational efficiency and product q uality. The study presents an improved model called TFDS-YOLOv8n for tilapia fil let defects segmentation." Financial support for this research came from Natural Science Foundation of Zhej iang Province. Our news journalists obtained a quote from the research from Zhejiang University,"The model incorporates Coordinate Attention (CA) into the feature extraction layer, thereby enhancing its ability to capture characteristics at various level s of the input. Additionally, the feature fusion layer is reconstructed as Slim- Neck to reduce the number of parameters without compromising prediction accuracy . Furthermore, the bounding box loss function is modified by MPDIoU to expedite the model convergence. The proposed model was tested employing the dataset colle cted from the practical tilapia processing plant. Ablation experiments demonstra te that TFDS-YOLOv8n achieves a reduction of 0.29 MB in parameters and 1 Gin Flo ating Point Operations (FLOPs) while increasing bbox_mAP and mask_ mAP by 2.8 % and 2.5 %, respectively. Eventually, the model is further accelerated by TensorRT and deployed on the edge device."
ZhejiangPeople's Republic of ChinaAs iaEmerging TechnologiesMachine LearningRoboticsRobotsZhejiang University
NETL
NSTL
