Low-value recyclable waste identification based on NIR feature analysis and RGB-NIR fusion

• Published in: Infrared physics & technology Vol. 131; p. 104693
• Main Authors: Ji, Tianchen, Fang, Huaiying, Zhang, Rencheng, Yang, Jianhong, Fan, Lulu, Hu, Yangyang, Cai, Zhengxing
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.06.2023
• Subjects: Feature selection; Low-value recyclable waste; Near-infrared spectroscopy; Object detection; Waste identification; Low-value recyclable waste; Feature selection; Waste identification; Object detection; Near-infrared spectroscopy
• ISSN: 1350-4495; 1879-0275
• DOI: 10.1016/j.infrared.2023.104693

•An RGB-NIR acquisition platform and a dataset generation method were proposed for fusion data collection and production.•A characteristic band selection method based on ANOVA and band ratio analysis was proposed to distinguish various types of waste.•An RGB-NIR fusion method was proposed for waste identification, which proved effective in the color and material identification of low-value recyclable waste. Low-value recyclable waste is one of the main components of solid waste, which is challenging to recycle because of its low density, small size, multiple categories, and large quantity. However, the primarily used spectral-based sorting is expensive, so incineration and landfill are still the main disposal methods in developing countries. In order to reduce the cost of sorting equipment, improve the accuracy and efficiency of identification, and facilitate the promotion of automatic sorting, this paper combines RGB and limited NIR data to realize cost-effective sorting. Firstly, an RGB-NIR instance segmentation dataset of white, color, and transparent PE, PP, and PET plastic flakes was produced, which are the main components of low-value recyclable waste. Then PCA and ANOVA were used to analyze the characteristics of the amplitude and band ratio of NIR data, where six characteristic bands were obtained. After that, the effect of the multi-channel NIR instance segmentation algorithm was tested based on 12 combinations of 6 bands, and the F1-score of the two better band combinations (1193, 1218, 1666 nm and 1134, 1193, 1218, 1349, 1398, 1666 nm) were 0.965 and 0.980, respectively. Finally, the selected 3-band NIR data and RGB data were mixed to create a fusion identification algorithm, which achieved the best material recognition accuracy (F1-score = 0.981) and color recognition accuracy (F1-score = 0.972). Moreover, the 9-categories comprehensive F1-score of the RGB-NIR fusion model is 0.961, which shows that it can recognize both material and color recognition.