Recognition of Plastic Bottles Region Using Improved DeepLab v3+
Saved in:
| Title: | Recognition of Plastic Bottles Region Using Improved DeepLab v3+ |
|---|---|
| Authors: | Murata, Yusuke, Kamiya, Tohru, 402, 神谷, 亨, 80295005, 55739611300, 25 |
| Publisher Information: | ALife Robotics |
| Publication Year: | 2025 |
| Collection: | Kyushu Institute of Technology Academic Repository (Kyutacar) / 九州工業大学学術機関リポジトリ |
| Subject Terms: | Deep Learning, Semantic Segmentation, Convolutional Neural Network (CNN), DeepLab v3+, Efficient Channel Attention Block (ECA Block), Mish function |
| Description: | Factory automation is one solution to the labor shortage. We focus on the sorting of plastic bottles in waste disposal plants and try to automate the process using robotic arms. In this paper, we propose an image analysis method for the recognition of plastic bottles limited to 500ml capacity. The method is semantic segmentation, and the deep learning model is DeepLab v3+. Modifications using ECA Block and Mish function show improvements at the points of misrecognition with the base model. ; conference paper |
| Document Type: | other/unknown material |
| File Description: | application/pdf |
| Language: | English |
| Relation: | Proceedings of International Conference on Artificial Life & Robotics (ICAROB2025); 825; 828; https://kyutech.repo.nii.ac.jp/record/2001637/files/10450823.pdf; https://hdl.handle.net/10228/0002001637; https://kyutech.repo.nii.ac.jp/records/2001637 |
| Availability: | https://kyutech.repo.nii.ac.jp/record/2001637/files/10450823.pdf https://hdl.handle.net/10228/0002001637 https://kyutech.repo.nii.ac.jp/records/2001637 |
| Rights: | Copyright (c) The 2025 International Conference on Artificial Life and Robotics (ICAROB2025), Feb.13-16, J:COM HorutoHall, Oita, Japan |
| Accession Number: | edsbas.6C4A44C6 |
| Database: | BASE |
Nájsť tento článok vo Web of Science | Abstract: | Factory automation is one solution to the labor shortage. We focus on the sorting of plastic bottles in waste disposal plants and try to automate the process using robotic arms. In this paper, we propose an image analysis method for the recognition of plastic bottles limited to 500ml capacity. The method is semantic segmentation, and the deep learning model is DeepLab v3+. Modifications using ECA Block and Mish function show improvements at the points of misrecognition with the base model. ; conference paper |
|---|