A deep convolutional neural network to simultaneously localize and recognize waste types in images. (1st May 2021)

• Record Type: Journal Article
• Authors: Liang, Shuang; Gu, Yu
• Is Part Of: Waste management. Volume 126(2021)
• Page Start: 247
• Page End: 257
• Publication Date: 2021-05-01
• Subjects: Multi-task learning -- Object detection -- Convolutional neural network -- Attention mechanism -- Waste classification benchmark -- Waste recognition and localization; Hazardous wastes -- Periodicals; Refuse and refuse disposal -- Periodicals; 363.728
• DOI: 10.1016/j.wasman.2021.03.017
• Languages: English
• ISSNs: 0956-053X

Abstract

Highlights: A new dataset is construct for automatic recognition and classification of wastes. A multi-task learning model for recognizing and localizing wastes is proposed. A visual interpretation method is designed to show the model's distinctive ability. Remarkable performance and superiority over SOTA methods is obtained by the model. Abstract: Accurate waste classification is key to successful waste management. However, most current studies have focused exclusively on single-label waste classification from images, which goes against common sense. In this paper, we move beyond single-label waste classification and propose a benchmark for evaluating the multi-label waste classification and localization tasks to advance waste management via deep learning-based methods. We propose a multi-task learning architecture (MTLA) based on a convolutional neural network, which can be used to simultaneously identify and locate wastes in images. The MTLA comprises a backbone network with proposed attention modules, a novel multi-level feature pyramid network, and a group of joint learning multi-task subnets. To achieve joint optimization of waste identification and location, we designed the loss functions according to the concepts of focusing and joint . The proposed MTLA achieved performance similar to that of experts and had high scores for multiple tasks related to waste management. Its F1 score exceeded 95.50% (95.12% to 95.88%, with a 95% confidence interval) on the multi-label waste classification task, and the average precision score was over 81.50% (@IoU = 0.5) on the waste localization task. To improve interpretation, heatmaps were used to visualize the salient features extracted by the MTLA. The proposed MTLA is a promising auxiliary tool that can improve the automation of waste management systems.