Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Huang, Yuzhi, Li, Chenxin, Zhang, Haitao, Lin, Zixu, Lin, Yunlong, Liu, Hengyu, Li, Wuyang, Liu, Xinyu, Gao, Jiechao, Huang, Yue, Ding, Xinghao, Yuan, Yixuan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2506.05175
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908395108302848
author Huang, Yuzhi
Li, Chenxin
Zhang, Haitao
Lin, Zixu
Lin, Yunlong
Liu, Hengyu
Li, Wuyang
Liu, Xinyu
Gao, Jiechao
Huang, Yue
Ding, Xinghao
Yuan, Yixuan
author_facet Huang, Yuzhi
Li, Chenxin
Zhang, Haitao
Lin, Zixu
Lin, Yunlong
Liu, Hengyu
Li, Wuyang
Liu, Xinyu
Gao, Jiechao
Huang, Yue
Ding, Xinghao
Yuan, Yixuan
contents Video anomaly detection (VAD) is crucial in scenarios such as surveillance and autonomous driving, where timely detection of unexpected activities is essential. Although existing methods have primarily focused on detecting anomalous objects in videos -- either by identifying anomalous frames or objects -- they often neglect finer-grained analysis, such as anomalous pixels, which limits their ability to capture a broader range of anomalies. To address this challenge, we propose a new framework called Track Any Anomalous Object (TAO), which introduces a granular video anomaly detection pipeline that, for the first time, integrates the detection of multiple fine-grained anomalous objects into a unified framework. Unlike methods that assign anomaly scores to every pixel, our approach transforms the problem into pixel-level tracking of anomalous objects. By linking anomaly scores to downstream tasks such as segmentation and tracking, our method removes the need for threshold tuning and achieves more precise anomaly localization in long and complex video sequences. Experiments demonstrate that TAO sets new benchmarks in accuracy and robustness. Project page available online.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05175
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Track Any Anomalous Object: A Granular Video Anomaly Detection Pipeline
Huang, Yuzhi
Li, Chenxin
Zhang, Haitao
Lin, Zixu
Lin, Yunlong
Liu, Hengyu
Li, Wuyang
Liu, Xinyu
Gao, Jiechao
Huang, Yue
Ding, Xinghao
Yuan, Yixuan
Computer Vision and Pattern Recognition
Video anomaly detection (VAD) is crucial in scenarios such as surveillance and autonomous driving, where timely detection of unexpected activities is essential. Although existing methods have primarily focused on detecting anomalous objects in videos -- either by identifying anomalous frames or objects -- they often neglect finer-grained analysis, such as anomalous pixels, which limits their ability to capture a broader range of anomalies. To address this challenge, we propose a new framework called Track Any Anomalous Object (TAO), which introduces a granular video anomaly detection pipeline that, for the first time, integrates the detection of multiple fine-grained anomalous objects into a unified framework. Unlike methods that assign anomaly scores to every pixel, our approach transforms the problem into pixel-level tracking of anomalous objects. By linking anomaly scores to downstream tasks such as segmentation and tracking, our method removes the need for threshold tuning and achieves more precise anomaly localization in long and complex video sequences. Experiments demonstrate that TAO sets new benchmarks in accuracy and robustness. Project page available online.
title Track Any Anomalous Object: A Granular Video Anomaly Detection Pipeline
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.05175