Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Advances in Computer, Signals and Systems
  4. Vol 8, Issue 3, 2024

Research on Employee Abnormal Behavior Detection Algorithm Based on Improved SSD

Download as PDF

DOI: 10.23977/acss.2024.080318 | Downloads: 8 | Views: 95

Author(s)

Rong Zhou 1, Haibo Peng 2, Siyao Liu 3

Affiliation(s)

1 Yunnan KISC Electronic Information Technology Co., Ltd., Kunming, Yunnan, 650300, China
2 Yunnan Open University, Kunming, Yunnan, 650300, China
3 Kunming University of Science and Technology Oxbridge College, Kunming, Yunnan, 650300, China

Corresponding Author

Haibo Peng

ABSTRACT

Detection of employee abnormal behavior is a hot topic in the field of video surveillance. In order to improve the accuracy and real-time performance of detection, this paper proposes an employee abnormal behavior detection algorithm based on SSD and improves the SSD algorithm. The improved SSD algorithm can effectively detect abnormal behaviors such as long-term immobility, sudden increase in activity, abnormal aggregation, abnormal body language and abnormal work performance. This paper introduces the technical route of enhanced SSD algorithm, including data preprocessing, network structure improvement, feature extraction, multi-scale prediction, target detection head design, loss function definition, post-processing technology, model training strategy and so on. The introduction of advanced feature fusion technology and the optimization of network structure make the improved SSD algorithm improve in three key performance indexes: detection time, detection accuracy and energy efficiency. Experimental results show that the maximum detection time of the improved algorithm is only 900ms, and the detection accuracy is 77.5%-95.4%. With the improvement of the energy efficiency ratio from 2.5 to 4.5, the changes of these indicators are very important for real-time monitoring system, which can greatly shorten the response time and reduce energy consumption.

KEYWORDS

Improving SSD Algorithm, Employee Abnormal Behavior Detection, Real Time Monitoring, Energy Efficiency Ratio

CITE THIS PAPER

Rong Zhou, Haibo Peng, Siyao Liu, Research on Employee Abnormal Behavior Detection Algorithm Based on Improved SSD. Advances in Computer, Signals and Systems (2024) Vol. 8: 129-136. DOI: http://dx.doi.org/10.23977/acss.2024.080318.

REFERENCES

[1] Tie Fuzhen. Algorithm for detecting abnormal behavior of crowds in video surveillance based on improved optical flow method [J]. Modern Electronic Technology, 2024,47 (7): 45-48.
[2] Zhu Xianyuan, Wang Songlin, Zhou Yefan, Han Haifeng. An Improved Classroom Abnormal Behavior Perception Detection Algorithm for YOLOv5 [J]. Journal of Qiqihar University (Natural Science Edition), 2023,39 (1): 46-52.
[3] Li Zhuoqing, Jia Zhentang. Abnormality behavior monitoring system and algorithm design based on deep learning [J]. Microcomputer Application, 2024,40 (3): 7-10.
[4] Zhao Lian, Zhou Lei, Guo Yuheng, Chen Huagui. Abnormal Behavior Detection in Factory Scenarios [J]. Software Guide, 2024,23 (1): 57-62.
[5] Zhu Qiang, Sun Chen, Xu Pan Yuchi, Yan Yunfeng. A two-stage detection algorithm for abnormal behavior in smart construction sites based on FCOS [J]. Zhejiang Electric Power, 2023,42 (4): 65-71.
[6] Liu D, Gao S, Chi W, et al. Pedestrian detection algorithm based on improved SSD[J]. International Journal of Computer Applications in Technology, 2021, 65(1): 25-35.
[7] Meng J, Jiang P, Wang J, et al. A mobilenet-SSD model with FPN for waste detection[J]. Journal of Electrical Engineering & Technology, 2022, 17(2): 1425-1431.
[8] Zhao M, Zhong Y, Sun D, et al. Accurate and efficient vehicle detection framework based on SSD algorithm[J]. IET Image Processing, 2021, 15(13): 3094-3104.
[9] Chen W, Qiao Y, Li Y. Inception-SSD: An improved single shot detector for vehicle detection[J]. Journal of Ambient Intelligence and Humanized Computing, 2022, 13(11): 5047-5053.
[10] Wang Y, Liu X, Guo R. An object detection algorithm based on the feature pyramid network and single shot multibox detector[J]. Cluster Computing, 2022, 25(5): 3313-3324.
[11] Yan C, Zhang H, Li X, et al. R-SSD: Refined single shot multibox detector for pedestrian detection[J]. Applied Intelligence, 2022, 52(9): 10430-10447.
[12] Feng T. Mask RCNN-based single shot multibox detector for gesture recognition in physical education[J]. Journal of Applied Science and Engineering, 2022, 26(3): 377-385.
[13] Farokhah L. Perbandingan Metode Deteksi Wajah Menggunakan OpenCV Haar Cascade, OpenCV Single Shot Multibox Detector (SSD) dan DLib CNN[J]. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 2021, 5(3): 609-614.
[14] Rogelio J, Dadios E, Bandala A, et al. Alignment control using visual servoing and mobilenet single-shot multi-box detection (SSD): A review[J]. International Journal of Advances in Intelligent Informatics, 2022, 8(1): 97-114.
[15] Zhang H, Hong X, Zhu L. Detecting small objects in thermal images using single-shot detector[J]. Automatic Control and Computer Sciences, 2021, 55(2): 202-211.
[16] Liu S, Huang L, Zhao Y, et al. Lightweight Single Shot Multi-Box Detector: A fabric defect detection algorithm incorporating parallel dilated convolution and dual channel attention[J]. Textile Research Journal, 2024, 94(1-2): 209-224.
[17] Zhang H, Niu M, Chen X, et al. (Retracted) Target recognition and localization based on lightweight single-shot multibox detector network for robotics[J]. Journal of Electronic Imaging, 2022, 31(6): 618-619.
[18] Kabolizadeh M, Abbasi M. Automatic Detection and Extraction of Qanat from Satellite Images with High Spatial Resolution of Google Earth based on Conventional Neural Networks Single-Shot Multi-box Detection (SSD)[J]. Engineering Journal of Geospatial Information Technology, 2023, 11(3): 85-102.
[19] Wen G, Cao P, Wang H, et al. MS-SSD: Multi-scale single shot detector for ship detection in remote sensing images [J]. Applied Intelligence, 2023, 53(2): 1586-1604.
[20] Juneja A, Juneja S, Soneja A, et al. Real time object detection using CNN based single shot detector model[J]. Journal of Information Technology Management, 2021, 13(1): 62-80.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 19516
Visits: 297448

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.