We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
基于改进Mask R-CNN的生活垃圾检测.
- Authors
张睿萍; 宁 芊; 雷印杰; 陈炳才
- Abstract
In recent years, People pay more and more attention to garbage classification and recycling, but garbage classification consumes a lot of manpower and material resources and the sorting efficiency is low. To solve the problem that the garbage detection method based on rectangular bounding box is not effective enough when applied to multi-classification environment, a garbage detection method based on improved Mask R-CNN is proposed. Instead of the traditional ResNet, this method uses the improvedResNeXt101asthebackbonenetworkforfeatureextraction, which improves the accuracy of objectdetectionandtheaccuracyofbackgroundboundarysegmentation. Experimental results show that compared with the traditional Mask R-CNN model, the proposed models average classification accuracy is 91. 1 %, improved by 2. 35 %. Finally, the experimental comparison with the current popular object detectionalgorithmsshowsthattheclassificationaccuracyandsegmentationaccuracyoftheproposedalgorithm are excel ent, which proves the feasibility and e fectiveness of the proposed method in the garbage detection task.
- Publication
Computer Engineering & Science / Jisuanji Gongcheng yu Kexue, 2022, Vol 44, Issue 11, p2003
- ISSN
1007-130X
- Publication type
Article
- DOI
10.3969/j.issn.1007-130X.2022.11.013