Affiliation:
1. Department of Computing, Gachon University, Seongnam-si 13120, Republic of Korea
2. Advanced Research Team, NHN Cloud Corp., Seongnam-si 13487, Republic of Korea
Abstract
Nowadays, deep learning (DL)-based video surveillance services are widely used in smart cities because of their ability to accurately identify and track objects, such as vehicles and pedestrians, in real time. This allows a more efficient traffic management and improved public safety. However, DL-based video surveillance services that require object movement and motion tracking (e.g., for detecting abnormal object behaviors) can consume a substantial amount of computing and memory capacity, such as (i) GPU computing resources for model inference and (ii) GPU memory resources for model loading. This paper presents a novel cognitive video surveillance management with long short-term memory (LSTM) model, denoted as the CogVSM framework. We consider DL-based video surveillance services in a hierarchical edge computing system. The proposed CogVSM forecasts object appearance patterns and smooths out the forecast results needed for an adaptive model release. Here, we aim to reduce standby GPU memory by model release while avoiding unnecessary model reloads for a sudden object appearance. CogVSM hinges on an LSTM-based deep learning architecture explicitly designed for future object appearance pattern prediction by training previous time-series patterns to achieve these objectives. By referring to the result of the LSTM-based prediction, the proposed framework controls the threshold time value in a dynamic manner by using an exponential weighted moving average (EWMA) technique. Comparative evaluations on both simulated and real-world measurement data on the commercial edge devices prove that the LSTM-based model in the CogVSM can achieve a high predictive accuracy, i.e., a root-mean-square error metric of 0.795. In addition, the suggested framework utilizes up to 32.1% less GPU memory than the baseline and 8.9% less than previous work.
Funder
National Research Foundation of Republic of Korea
Gachon University
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference40 articles.
1. Number of Internet of Things (IoT) Connected Devices Worldwide from 2019 to 2021, with Forecasts from 2022 to 2030 (in billions) (2023, January 03). Statista. Available online: https://www.statista.com/statistics/1183457/iot-connected-devices-worldwide/.
2. Evolutionary deep learning: A survey;Zhan;Neurocomputing,2022
3. Long short-term memory;Hochreiter;Neural Comput.,1997
4. Rajavel, R., Ravichandran, S.K., Harimoorthy, K., Nagappan, P., and Gobichettipalayam, K.R. (2022). IoT-based smart healthcare video surveillance system using edge computing. J. Ambient. Intell. Humaniz. Comput., 1–13.
5. A surveillance video real-time analysis system based on edge-cloud and fl-yolo cooperation in coal mine;Xu;IEEE Access,2021
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献