Multiple object characterization of recyclable domestic waste using binocular stereo vision

Abstract

Recycling and recovery of domestic waste pose significant challenges in terms of accurate object positioning and ranging, areas where conventional methods, heavily reliant on monocular image processing, often fail due to limited distance data and reduced precision. This study introduces an innovative strategy for the localization and ranging of recyclable waste objects, leveraging the NanoDet-Plus model within a binocular stereo vision context. A dataset, the Binocular Recyclable Domestic Waste Dataset (BRDWD), was constructed, with transfer learning executed via the pretrained MULTI-TRASH monocular dataset. Procedures encompassed stereo camera calibration and rectification to address geometric distortions, while the integration of the Semi-Global Block Matching (SGBM) algorithm supplied disparity details for triangulation-based distance computations. Enhancements to the NanoDet-Plus model led to improved target accuracy, evidenced by a mean average precision at a threshold of 0.5 ([email protected]) reaching 91.88% and a detection speed of 15 frames per second (FPS). Assessments verified a ranging error below 5% within the 0.5 to 1.2-meter span, aligning well with the requirements of typical recyclable waste sorting and recycling situations. Additionally, a human-machine interface was developed utilizing Pyside6, enabling image uploads, real-time result visualization, and interactive process control, thereby furnishing pivotal advancements for the automation and intellectualization of waste categorization and recycling.

Keywords:

• Binocular ranging
• environmental pollution
• NanoDet-Plus
• object detection
• pyside6 interface

Acknowledgement

We thank Jiangsu Beier Machinery for providing equipment and sample support.

Author contributions

Qunbiao Wu: Writing - Review & Editing, Validation, Project administration. Tao Liang: Data curation, Software, Writing- Original draft. Haifeng Fang: Funding acquisition, Supervision. Jin Cao: Supervision. Mingqiang Wang: Supervision. Defang He: Supervision.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data availability statement

The data that support the findings of this study are available from the corresponding author upon reasonable request.

Additional information

Funding

This research effort has been generously supported by the Qing Lan Project of Higher Education Institutions in Jiangsu Province and the Science and Technology Plan Project of Jiangsu Province, specifically its International Science and Technology Cooperation Special Fund (Project No.: BZ2022029).