RoLID-11K: A Dashcam Dataset for Small-Object Roadside Litter Detection

TL;DR

RoLID-11K introduces a large-scale dashcam dataset for small-object roadside litter detection, enabling the development of scalable monitoring systems and benchmarking modern detectors in challenging driving scenarios.

Contribution

The paper presents RoLID-11K, the first extensive dataset for small-object litter detection from dashcam footage, and benchmarks various detection models on this new challenging dataset.

Findings

Transformers like CO-DETR achieve high localization accuracy.

Real-time models are limited by coarse feature hierarchies.

RoLID-11K provides a challenging benchmark for small-object detection in driving scenes.

Abstract

Roadside litter poses environmental, safety and economic challenges, yet current monitoring relies on labour-intensive surveys and public reporting, providing limited spatial coverage. Existing vision datasets for litter detection focus on street-level still images, aerial scenes or aquatic environments, and do not reflect the unique characteristics of dashcam footage, where litter appears extremely small, sparse and embedded in cluttered road-verge backgrounds. We introduce RoLID-11K, the first large-scale dataset for roadside litter detection from dashcams, comprising over 11k annotated images spanning diverse UK driving conditions and exhibiting pronounced long-tail and small-object distributions. We benchmark a broad spectrum of modern detectors, from accuracy-oriented transformer architectures to real-time YOLO models, and analyse their strengths and limitations on this challenging task. Our results show that while CO-DETR and related transformers achieve the best localisation accuracy, real-time models remain constrained by coarse feature hierarchies. RoLID-11K establishes a challenging benchmark for extreme small-object detection in dynamic driving scenes and aims to support the development of scalable, low-cost systems for roadside-litter monitoring. The dataset is available at https://github.com/xq141839/RoLID-11K.