StreetView-Waste: A Multi-Task Dataset for Urban Waste Management

2025-11-20

AI Summary

Existing waste management datasets lack container overflow detection and tracking annotations from the garbage truck’s perspective and are predominantly collected in static environments, limiting their applicability to real-world logistics scenarios. To address this, we introduce StreetView-Waste—the first multi-task urban sanitation dataset supporting trash bin detection, multi-object tracking, and semantic segmentation of overflow regions. We innovatively formulate and model the joint task of “container tracking + overflow segmentation,” and propose a model-agnostic multimodal fusion framework comprising a heuristic trajectory optimization strategy and a geometry-prior-driven segmentation enhancement module. Experiments demonstrate a 79.6% reduction in tracking-based counting error and a 27% improvement in mAP@0.5 for overflow segmentation using lightweight models. These advances significantly enhance the perception robustness and practicality of intelligent sanitation systems in complex street-level scenes.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Motion & Tracking
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Security and Privacy: Tracking, profiling, and countermeasures against them
• Web Mining and Content Analysis: Web data integration and cleaning

Abstract

Urban waste management remains a critical challenge for the development of smart cities. Despite the growing number of litter detection datasets, the problem of monitoring overflowing waste containers, particularly from images captured by garbage trucks, has received little attention. While existing datasets are valuable, they often lack annotations for specific container tracking or are captured in static, decontextualized environments, limiting their utility for real-world logistics. To address this gap, we present StreetView-Waste, a comprehensive dataset of urban scenes featuring litter and waste containers. The dataset supports three key evaluation tasks: (1) waste container detection, (2) waste container tracking, and (3) waste overflow segmentation. Alongside the dataset, we provide baselines for each task by benchmarking state-of-the-art models in object detection, tracking, and segmentation. Additionally, we enhance baseline performance by proposing two complementary strategies: a heuristic-based method for improved waste container tracking and a model-agnostic framework that leverages geometric priors to refine litter segmentation. Our experimental results show that while fine-tuned object detectors achieve reasonable performance in detecting waste containers, baseline tracking methods struggle to accurately estimate their number; however, our proposed heuristics reduce the mean absolute counting error by 79.6%. Similarly, while segmenting amorphous litter is challenging, our geometry-aware strategy improves segmentation mAP@0.5 by 27% on lightweight models, demonstrating the value of multimodal inputs for this task. Ultimately, StreetView-Waste provides a challenging benchmark to encourage research into real-world perception systems for urban waste management.

Problem

• Monitoring overflowing waste containers from garbage truck images
• Lacking annotations for container tracking in real-world environments
• Challenges in amorphous litter segmentation and container counting

Innovation

• Proposes heuristic-based method for waste container tracking
• Introduces model-agnostic framework using geometric priors
• Leverages multimodal inputs to enhance segmentation performance