首页|Data from Shanxi Agricultural University Provide New Insights into Robotics (Seg mentation Method of * * Zanthoxylum bungeanum* * Cluster Based on Improved Mask R-CNN)
Data from Shanxi Agricultural University Provide New Insights into Robotics (Seg mentation Method of * * Zanthoxylum bungeanum* * Cluster Based on Improved Mask R-CNN)
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 – Investigators discuss new findings in robotics. According to news reporting from Jinzhong, People’s Republic of China, by NewsRx journalists, research stated, “The precise segmentation of * * Zantho xylum bungeanum* * clusters is crucial for developing picking robots.” Funders for this research include Key Research And Development Program of Shanxi Province. The news editors obtained a quote from the research from Shanxi Agricultural Uni versity: “An improved Mask R-CNN model was proposed in this study for the segmen tation of * * Zanthoxylum bungeanum* * clusters in natural environments. Firstly , the Swin-Transformer network was introduced into the model’s backbone as the f eature extraction network to enhance the model’s feature extraction capabilities . Then, the SK attention mechanism was utilized to fuse the detailed information into the mask branch from the low-level feature map of the feature pyramid netw ork (FPN), aiming to supplement the image detail features. Finally, the distance intersection over union (DIOU) loss function was adopted to replace the origina l bounding box loss function of Mask R-CNN. The model was trained and tested bas ed on a self-constructed * * Zanthoxylum bungeanum* * cluster dataset. Experimen ts showed that the improved Mask R-CNN model achieved 84.0% and 77 .2% in detection mAP 50 box and segmentation mAP 50 mask , respect ively, representing a 5.8% and 4.6% improvement over the baseline Mask R-CNN model.”
Shanxi Agricultural UniversityJinzhongPeople’s Republic of ChinaEmerging TechnologiesMachine LearningNano-ro botRobotics
NETL
NSTL
