Saved in:
Bibliographic Details
Main Authors: Wu, Tao, Xu, Qing, He, Xiangjian, Weekes, Oakleigh, Brown, James, Duan, Wenting
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.00398
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909979849523200
author Wu, Tao
Xu, Qing
He, Xiangjian
Weekes, Oakleigh
Brown, James
Duan, Wenting
author_facet Wu, Tao
Xu, Qing
He, Xiangjian
Weekes, Oakleigh
Brown, James
Duan, Wenting
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_00398
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RoLID-11K: A Dashcam Dataset for Small-Object Roadside Litter Detection
Wu, Tao
Xu, Qing
He, Xiangjian
Weekes, Oakleigh
Brown, James
Duan, Wenting
Computer Vision and Pattern Recognition
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.
title RoLID-11K: A Dashcam Dataset for Small-Object Roadside Litter Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.00398