TY - GEN
T1 - Fast-DAVAD
T2 - 9th IEEE Smart World Congress, SWC 2023
AU - Shen, Haocheng
AU - Guo, Bin
AU - Ding, Yasan
AU - Xiao, Jie
AU - Lv, Mingze
AU - Yu, Zhiwen
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - The development of artificial intelligence of things (AIoT) makes it possible to detect video anomalies on intelligent edge devices with low transmission delay and data privacy. However, the performance of these applications is constrained by the domain shift between the diverse real-world environment and the training data. Despite the existence of many advanced domain adaptation methods, it is difficult to deploy these methods on resource-constrained intelligent edge devices due to their model complexity. In addition, there is a lack of large amounts of labeled real-scenario data to complete model training. In this paper, we propose the Fast-DAVAD, an unsupervised end-to-end lightweight adaptive video anomaly detection framework. It solves the domain shift problem through multi-level adversarial domain adaptation. Furthermore, it achieves short training time and inference latency on resource-constrained edge devices with Residual Unet, and applies a memory module to guarantee detection accuracy. Extensive experiments on public datasets and multiple platforms, such as PC and NVIDIA Jetson, demonstrate that the effectiveness and superiority of Fast-DAVAD compared with state-of-the-art domain adaptation-based video anomaly detection solutions.
AB - The development of artificial intelligence of things (AIoT) makes it possible to detect video anomalies on intelligent edge devices with low transmission delay and data privacy. However, the performance of these applications is constrained by the domain shift between the diverse real-world environment and the training data. Despite the existence of many advanced domain adaptation methods, it is difficult to deploy these methods on resource-constrained intelligent edge devices due to their model complexity. In addition, there is a lack of large amounts of labeled real-scenario data to complete model training. In this paper, we propose the Fast-DAVAD, an unsupervised end-to-end lightweight adaptive video anomaly detection framework. It solves the domain shift problem through multi-level adversarial domain adaptation. Furthermore, it achieves short training time and inference latency on resource-constrained edge devices with Residual Unet, and applies a memory module to guarantee detection accuracy. Extensive experiments on public datasets and multiple platforms, such as PC and NVIDIA Jetson, demonstrate that the effectiveness and superiority of Fast-DAVAD compared with state-of-the-art domain adaptation-based video anomaly detection solutions.
KW - domain adaptation
KW - edge computing
KW - video anomaly detection
UR - http://www.scopus.com/inward/record.url?scp=85187378211&partnerID=8YFLogxK
U2 - 10.1109/SWC57546.2023.10448698
DO - 10.1109/SWC57546.2023.10448698
M3 - 会议稿件
AN - SCOPUS:85187378211
T3 - Proceedings - 2023 IEEE SmartWorld, Ubiquitous Intelligence and Computing, Autonomous and Trusted Vehicles, Scalable Computing and Communications, Digital Twin, Privacy Computing and Data Security, Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PCDS/Metaverse 2023
BT - Proceedings - 2023 IEEE SmartWorld, Ubiquitous Intelligence and Computing, Autonomous and Trusted Vehicles, Scalable Computing and Communications, Digital Twin, Privacy Computing and Data Security, Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PCDS/Metaverse 2023
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 28 August 2023 through 31 August 2023
ER -