ROADWork: A Dataset and Benchmark for Learning to Recognize, Observe, Analyze and Drive Through Work Zones

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ghosh, Anurag, Zheng, Shen, Tamburo, Robert, Vuong, Khiem, Alvarez-Padilla, Juan, Zhu, Hailiang, Cardei, Michael, Dunn, Nicholas, Mertz, Christoph, Narasimhan, Srinivasa G.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912687989981184
author Ghosh, Anurag
Zheng, Shen
Tamburo, Robert
Vuong, Khiem
Alvarez-Padilla, Juan
Zhu, Hailiang
Cardei, Michael
Dunn, Nicholas
Mertz, Christoph
Narasimhan, Srinivasa G.
author_facet Ghosh, Anurag
Zheng, Shen
Tamburo, Robert
Vuong, Khiem
Alvarez-Padilla, Juan
Zhu, Hailiang
Cardei, Michael
Dunn, Nicholas
Mertz, Christoph
Narasimhan, Srinivasa G.
contents Perceiving and autonomously navigating through work zones is a challenging and underexplored problem. Open datasets for this long-tailed scenario are scarce. We propose the ROADWork dataset to learn to recognize, observe, analyze, and drive through work zones. State-of-the-art foundation models fail when applied to work zones. Fine-tuning models on our dataset significantly improves perception and navigation in work zones. With ROADWork dataset, we discover new work zone images with higher precision (+32.5%) at a much higher rate (12.8$\times$) around the world. Open-vocabulary methods fail too, whereas fine-tuned detectors improve performance (+32.2 AP). Vision-Language Models (VLMs) struggle to describe work zones, but fine-tuning substantially improves performance (+36.7 SPICE). Beyond fine-tuning, we show the value of simple techniques. Video label propagation provides additional gains (+2.6 AP) for instance segmentation. While reading work zone signs, composing a detector and text spotter via crop-scaling improves performance +14.2% 1-NED). Composing work zone detections to provide context further reduces hallucinations (+3.9 SPICE) in VLMs. We predict navigational goals and compute drivable paths from work zone videos. Incorporating road work semantics ensures 53.6% goals have angular error (AE) < 0.5 (+9.9 %) and 75.3% pathways have AE < 0.5 (+8.1 %).
format Preprint
id arxiv_https___arxiv_org_abs_2406_07661
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ROADWork: A Dataset and Benchmark for Learning to Recognize, Observe, Analyze and Drive Through Work Zones
Ghosh, Anurag
Zheng, Shen
Tamburo, Robert
Vuong, Khiem
Alvarez-Padilla, Juan
Zhu, Hailiang
Cardei, Michael
Dunn, Nicholas
Mertz, Christoph
Narasimhan, Srinivasa G.
Computer Vision and Pattern Recognition
Robotics
Perceiving and autonomously navigating through work zones is a challenging and underexplored problem. Open datasets for this long-tailed scenario are scarce. We propose the ROADWork dataset to learn to recognize, observe, analyze, and drive through work zones. State-of-the-art foundation models fail when applied to work zones. Fine-tuning models on our dataset significantly improves perception and navigation in work zones. With ROADWork dataset, we discover new work zone images with higher precision (+32.5%) at a much higher rate (12.8$\times$) around the world. Open-vocabulary methods fail too, whereas fine-tuned detectors improve performance (+32.2 AP). Vision-Language Models (VLMs) struggle to describe work zones, but fine-tuning substantially improves performance (+36.7 SPICE). Beyond fine-tuning, we show the value of simple techniques. Video label propagation provides additional gains (+2.6 AP) for instance segmentation. While reading work zone signs, composing a detector and text spotter via crop-scaling improves performance +14.2% 1-NED). Composing work zone detections to provide context further reduces hallucinations (+3.9 SPICE) in VLMs. We predict navigational goals and compute drivable paths from work zone videos. Incorporating road work semantics ensures 53.6% goals have angular error (AE) < 0.5 (+9.9 %) and 75.3% pathways have AE < 0.5 (+8.1 %).
title ROADWork: A Dataset and Benchmark for Learning to Recognize, Observe, Analyze and Drive Through Work Zones
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2406.07661