SortWaste: A Densely Annotated Dataset for Object Detection in Industrial Waste Sorting

TL;DR

SortWaste introduces a densely annotated dataset for object detection in industrial waste sorting, along with a new metric to assess scene complexity, revealing challenges in cluttered environments and advancing research in automated waste management.

Contribution

The paper presents the first real-world, densely annotated waste sorting dataset and proposes ClutterScore, a metric for scene difficulty, along with benchmarking state-of-the-art detection models.

Findings

Achieved 59.7% mAP on plastic detection

Detection performance drops in highly cluttered scenes

ClutterScore correlates with detection difficulty

Abstract

The increasing production of waste, driven by population growth, has created challenges in managing and recycling materials effectively. Manual waste sorting is a common practice; however, it remains inefficient for handling large-scale waste streams and presents health risks for workers. On the other hand, existing automated sorting approaches still struggle with the high variability, clutter, and visual complexity of real-world waste streams. The lack of real-world datasets for waste sorting is a major reason automated systems for this problem are underdeveloped. Accordingly, we introduce SortWaste, a densely annotated object detection dataset collected from a Material Recovery Facility. Additionally, we contribute to standardizing waste detection in sorting lines by proposing ClutterScore, an objective metric that gauges the scene's hardness level using a set of proxies that affect visual complexity (e.g., object count, class and size entropy, and spatial overlap). In addition to these contributions, we provide an extensive benchmark of state-of-the-art object detection models, detailing their results with respect to the hardness level assessed by the proposed metric. Despite achieving promising results (mAP of 59.7% in the plastic-only detection task), performance significantly decreases in highly cluttered scenes. This highlights the need for novel and more challenging datasets on the topic.