Video anomaly detection based on spatio-temporal relationships among objects

计算机科学 异常检测 人工智能 光学(聚焦) 模式识别(心理学) 对象(语法) 编码器 异常(物理) 编码(内存) 目标检测 凝聚态物理 操作系统 光学 物理
作者
Yan Wang,Tianying Liu,Jiaogen Zhou,Jihong Guan
出处
期刊:Neurocomputing [Elsevier BV]
卷期号:532: 141-151 被引量:18
标识
DOI:10.1016/j.neucom.2023.02.027
摘要

Video anomaly detection is to automatically identify predefined anomalous contents (e.g. abnormal objects, behaviors and scenes) in videos. The performance of video anomaly detection can be effectively improved by making the model focus more on the anomalous objects in videos. However, such existing approaches usually rely on pre-trained models, which not only require additional auxiliary information but also face the challenge of anomaly diversity in the real world. In this paper, we propose a new video anomaly detection method based on spatio-temporal relationships among objects. Concretely, we use a fully convolutional encoder-decoder network with symmetric skip connections as the backbone network, which can effectively extract features from the object regions at different scales. In the encoding stage, an attention mechanism is used to enhance the model's understanding of the spatio-temporal relationships among various types of objects in the video. In the decoding stage, a dynamic pattern generator is designed to memorize the inter-object spatio-temporal relationships, which thus enhances the reconstructions of normal samples while making the reconstructions of abnormal samples more difficult. We conduct extensive experiments on three widely used video anomaly detection datasets CUHK Avenue, ShanghaiTech Campus and UCSD Ped2, and the experimental results show that our proposed method can significantly improve the performance, and achieves state-of-the-art overall performance (considering both effectiveness and efficiency). In particular, our method achieves a state-of-the-art AUC of 98.4% on the UCSD Ped2 dataset that consists of various anomalies in real-world scenarios.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
2秒前
充电宝应助NVLEKU采纳,获得10
2秒前
3秒前
3秒前
天天快乐应助zhu采纳,获得10
4秒前
IRer79发布了新的文献求助10
4秒前
量子星尘发布了新的文献求助10
4秒前
麦丰完成签到,获得积分10
4秒前
4秒前
likke完成签到,获得积分20
5秒前
5秒前
FashionBoy应助li采纳,获得10
6秒前
6秒前
SciGPT应助薛定谔的猫采纳,获得10
6秒前
7秒前
7秒前
muming完成签到,获得积分20
8秒前
sanlunainiu发布了新的文献求助10
8秒前
林博研完成签到,获得积分20
8秒前
FashionBoy应助风趣的灵枫采纳,获得10
9秒前
10秒前
yihuiqing发布了新的文献求助10
11秒前
likke发布了新的文献求助10
11秒前
嗝嗝发布了新的文献求助10
11秒前
小兔狸花昕完成签到,获得积分20
12秒前
IRer79完成签到,获得积分10
14秒前
彭于晏应助noah采纳,获得10
14秒前
青年才俊发布了新的文献求助10
14秒前
zhu发布了新的文献求助10
15秒前
波波蛋完成签到,获得积分10
15秒前
16秒前
17秒前
18秒前
maguodrgon发布了新的文献求助10
21秒前
科研通AI5应助shell采纳,获得80
21秒前
波波蛋发布了新的文献求助10
21秒前
22秒前
九鹤完成签到,获得积分10
22秒前
jsy完成签到,获得积分10
22秒前
量子星尘发布了新的文献求助10
23秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Zeolites: From Fundamentals to Emerging Applications 1500
Architectural Corrosion and Critical Infrastructure 1000
Early Devonian echinoderms from Victoria (Rhombifera, Blastoidea and Ophiocistioidea) 1000
By R. Scott Kretchmar - Practical Philosophy of Sport and Physical Activity - 2nd (second) Edition: 2nd (second) Edition 666
Energy-Size Reduction Relationships In Comminution 500
Principles Of Comminution, I-Size Distribution And Surface Calculations 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 内科学 生物化学 物理 计算机科学 纳米技术 遗传学 基因 复合材料 化学工程 物理化学 病理 催化作用 免疫学 量子力学
热门帖子
关注 科研通微信公众号,转发送积分 4941339
求助须知:如何正确求助?哪些是违规求助? 4207390
关于积分的说明 13077624
捐赠科研通 3986257
什么是DOI,文献DOI怎么找? 2182529
邀请新用户注册赠送积分活动 1198125
关于科研通互助平台的介绍 1110387