.png){kind=icon}
返回
Data-centric approach for instance segmentation in optical waste sorting
.png){kind=icon}
PRE
AI
DOI：10.1016/j.wasman.2024.11.002.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Computer vision systems have been integrated into facilities dealing with the sorting of household waste. This solution allows for the sorting efficiency improvement and cost reduction. However, challenges associated with the poor annotation quality of existing waste segmentation datasets, unsuitable environment for recognition on a conveyor belt, or limited data for creating an effective and cost-efficient sorting system using visible range cameras significantly limit the application efficiency of computer vision systems. In this article, we report on the data-centric pipeline for enhancing the precision of predictions in multiclass household waste segmentation on a conveyor belt. In particular, we have demonstrated that by employing a pseudo-annotation approach combined with an object-based data augmentation algorithm, it is possible to train a model on a set of 'simple' images and achieve satisfactory results when estimating the model on a set of 'complex' images. We collected and prepared the dataset consisting of 5 k manually labeled data and additionally 10 k pseudo-labeled data by object-based augmentation. The proposed pipeline incorporates data balancing, transfer learning, and pseudo-labeling to improve the mean Average Precision (mAP) of the YOLOV8 segmentation model from 67 % to 83 % for 'simple' use case scenarios and from 42 % to 59 % or 'complex' industrial solutions.
Keyword:
Instance segmentation
Object-based augmentation
Optical waste management
Deep learning
Computer Vision
期刊
IF:
7.1
论文数:
1.0W
被引数:
5.3W
机构
引用论文
分享收藏分享收藏XtremeAugment: Getting More From Your Data Through Combination of Image Collection and Image Augmentation.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏UAV-YOLOv8: A Small-Object-Detection Model Based on Improved YOLOv8 for UAV Aerial Photography ScenariosUAV-YOLOv8: 基于改进YOLOv8的无人机航拍场景小目标检测模型SENSORS
OAAI
SENSORSIF3.5
OAAI分享收藏Auto-sorting commonly recovered plastics from waste household appliances and electronics using near-infrared spectroscopy使用近红外光谱从废弃的家用电器和电子产品中自动分类通常回收的塑料
PREAI
分享收藏
查看更多内容