Enregistré dans:
Détails bibliographiques
Auteurs principaux: Kong, Quan, Kawana, Yuki, Saini, Rajat, Kumar, Ashutosh, Pan, Jingjing, Gu, Ta, Ozao, Yohei, Opra, Balazs, Anastasiu, David C., Sato, Yoichi, Kobori, Norimasa
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2407.15350
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911963876950016
author Kong, Quan
Kawana, Yuki
Saini, Rajat
Kumar, Ashutosh
Pan, Jingjing
Gu, Ta
Ozao, Yohei
Opra, Balazs
Anastasiu, David C.
Sato, Yoichi
Kobori, Norimasa
author_facet Kong, Quan
Kawana, Yuki
Saini, Rajat
Kumar, Ashutosh
Pan, Jingjing
Gu, Ta
Ozao, Yohei
Opra, Balazs
Anastasiu, David C.
Sato, Yoichi
Kobori, Norimasa
contents In this paper, we address the challenge of fine-grained video event understanding in traffic scenarios, vital for autonomous driving and safety. Traditional datasets focus on driver or vehicle behavior, often neglecting pedestrian perspectives. To fill this gap, we introduce the WTS dataset, highlighting detailed behaviors of both vehicles and pedestrians across over 1.2k video events in hundreds of traffic scenarios. WTS integrates diverse perspectives from vehicle ego and fixed overhead cameras in a vehicle-infrastructure cooperative environment, enriched with comprehensive textual descriptions and unique 3D Gaze data for a synchronized 2D/3D view, focusing on pedestrian analysis. We also pro-vide annotations for 5k publicly sourced pedestrian-related traffic videos. Additionally, we introduce LLMScorer, an LLM-based evaluation metric to align inference captions with ground truth. Using WTS, we establish a benchmark for dense video-to-text tasks, exploring state-of-the-art Vision-Language Models with an instance-aware VideoLLM method as a baseline. WTS aims to advance fine-grained video event understanding, enhancing traffic safety and autonomous driving development.
format Preprint
id arxiv_https___arxiv_org_abs_2407_15350
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle WTS: A Pedestrian-Centric Traffic Video Dataset for Fine-grained Spatial-Temporal Understanding
Kong, Quan
Kawana, Yuki
Saini, Rajat
Kumar, Ashutosh
Pan, Jingjing
Gu, Ta
Ozao, Yohei
Opra, Balazs
Anastasiu, David C.
Sato, Yoichi
Kobori, Norimasa
Computer Vision and Pattern Recognition
In this paper, we address the challenge of fine-grained video event understanding in traffic scenarios, vital for autonomous driving and safety. Traditional datasets focus on driver or vehicle behavior, often neglecting pedestrian perspectives. To fill this gap, we introduce the WTS dataset, highlighting detailed behaviors of both vehicles and pedestrians across over 1.2k video events in hundreds of traffic scenarios. WTS integrates diverse perspectives from vehicle ego and fixed overhead cameras in a vehicle-infrastructure cooperative environment, enriched with comprehensive textual descriptions and unique 3D Gaze data for a synchronized 2D/3D view, focusing on pedestrian analysis. We also pro-vide annotations for 5k publicly sourced pedestrian-related traffic videos. Additionally, we introduce LLMScorer, an LLM-based evaluation metric to align inference captions with ground truth. Using WTS, we establish a benchmark for dense video-to-text tasks, exploring state-of-the-art Vision-Language Models with an instance-aware VideoLLM method as a baseline. WTS aims to advance fine-grained video event understanding, enhancing traffic safety and autonomous driving development.
title WTS: A Pedestrian-Centric Traffic Video Dataset for Fine-grained Spatial-Temporal Understanding
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.15350