To address the issues of insufficient granularity in feature extraction and limited adaptability to complex video surveillance scenarios in substations inherent in traditional power personnel behavior recognition methods, this study investigates behavior recognition technology tailored to the needs of power operation and maintenance. An end-to-end video behavior recognition framework is adopted to directly model raw surveillance videos, and a key frame extraction method based on spatiotemporal features is designed to improve inference efficiency. A behavior classification decoder is constructed to enhance the discriminative ability for multiple types of operational actions. The experimental results on the real substation operation video dataset show that the proposed method achieves an overall recognition rate of 93.7%, significantly outperforming traditional image recognition methods such as support vector machine (SVM) and multi-layer perceptron (MLP) in both recognition accuracy and processing speed. The research conclusion provides a technical reference for improving the intelligent monitoring ability of power field.
YANGJ, LIC M, HONGD J, et al. Real-time safety behavior detection technology of indoors power personnel based on human key points[J]. Journal of Shanghai Jiaotong University (Science), 2024, 29(2): 309-315.
WANGHong, DENGYuanshi, CHANGZhengwei, et al. Behavior recognition technology of power operating person based on deep learning[J]. Sichuan Electric Power Technology, 2022, 45(3): 23-28.
ZHOUZhenzhen, SONGYunhai, HEYuhao, et al. Extensible classification method for power personnel behavior based on pose estimation[J]. Electric Power, 2023, 56(11): 77-85.
YANYunfeng, CHENXi, JINHaoyuan, et al. Research status and development of computer-vision-based power workers' behavior analysis[J]. High Voltage Engineering, 2024, 50(5): 1842-1854.
[8]
FANGJ X, LIX W. Object detection related to irregular behaviors of substation personnel based on improved YOLOv4[J]. Applied Sciences, 2022, 12(9): 4301.
[9]
CHENS B, TANGW H, JIT Y, et al. Detection of safety helmet wearing based on improved faster R-CNN[C]//2020 International Joint Conference on Neural Networks. July 19-24, 2020. Glasgow, United Kingdom. IEEE, 2020: 1-7.
[10]
ELDEMERYH I, PASHAH H, HAMIDN A, et al. Temporal pedestrian behavior prediction using LSTM networks[C]//2025 7th Novel Intelligent and Leading Emerging Sciences Conference. October 25-27, 2025, Giza, Egypt. IEEE, 2025: 250-253.
[11]
IKOTUNA M, EZUGWUA E, ABUALIGAHL, et al. K-means clustering algorithms: a comprehensive review, variants analysis, and advances in the era of big data[J]. Information Sciences, 2023, 622: 178-210.
[12]
HUF. Survey on neural networks in natural language processing[C]//2023 IEEE International Conference on Control, Electronics and Computer Technology. April 28-30, 2023, Jilin, China. IEEE, 2023: 591-594.
[13]
WANJARIK, VERMAP. A review on the applications of machine learning and deep learning algorithms for image recognition[C]//2025 4th International Conference on Sentiment Analysis and Deep Learning. February 18-20, 2025, Bhimdatta, Nepal. IEEE, 2025: 1707-1711.
[14]
SINGHA, JANGIDA K, SRINIVASUB. Advancing neural network performance with probabilistic computing for ReLU function[C]//2025 38th International Conference on VLSI Design and 2024 23rd International Conference on Embedded Systems. January 4-8, 2025, Bangalore, India. IEEE, 2025: 237-242.
[15]
GHOLAMALINEZHADH, KHOSRAVIH. Pooling methods in deep neural networks, a review[EB/OL]. 2020: arXiv: 2009.07485.
[16]
MURTHYA, RAOP S, PALLAVIN S, et al. Optimizing convolutional neural networks: a comparative study of gradient-descent, Adam, and RMSprop optimizers for accuracy and loss in apple leaf disease detection[C]//2024 Second International Conference on Networks, Multimedia and Information Technology. August 9-10, 2024, Bengaluru, India. IEEE, 2024: 1-6.
[17]
AL-KABABJIA, BENSAALIF, DAKUAS P. Scheduling techniques for liver segmentation: ReduceLRonPlateau vs OneCycleLR[C]//Intelligent Systems and Pattern Recognition: Second International Conference,ISPR 2022,Recised Selected Papers. March 24-26, 2022, Hammamet, Tunisia.Springer International Publishing, 2022: 204-212.
[18]
LVP, ZHANGY. Prediction of organic chemical reactions using cyclical learning rate based long-short term memory[C]//2023 3rd International Conference on Mobile Networks and Wireless Communications. December 4-5, 2023, Tumkur, India. IEEE, 2024: 1-4.
[19]
TANQ C, CHENGT, LIJ Z, et al. Differential privacy adaptive gradient clipping method based on hessian matrix[C]//2025 3rd International Conference on Big Data and Privacy Computing. May 30 - June 1, 2025, Fuzhou, China. IEEE, 2025: 96-102.
[20]
CHAUHANA, TIWARIU, RV N. Post training mixed precision quantization of neural networks using first-order information[C]//2023 IEEE/CVF International Conference on Computer Vision Workshops. October 2-6, 2023, Paris, France. IEEE, 2023: 1335-1344.
[21]
MANZALIY, BARRYK A, ELFAR M. An improved KNN algorithm based on ensemble methods and correlation[C]//2023 7th IEEE Congress on Information Science and Technology. December 16-22, 2023, Agadir - Essaouira, Morocco. IEEE, 2024: 64-70.
[22]
CAIQ. Human behavior recognition algorithm based on HOG feature and SVM classifier[C]//2019 IEEE 10th International Conference on Software Engineering and Service Science. October 18-20, 2019, Beijing, China. IEEE, 2020: 233-236.
[23]
TOLSTIKHINI O, HOULSBYN, KOLESNIKOVA, et al. MLP-mixer: an all-MLP architecture for vision[C]//35th Conference on Neural Information Processing Systems. December 6,2021, Sydney, Australia. NeurIPS, 2021: 24261-72.
[24]
CAOZ, SIMONT, WEIS H, et al. Realtime multi-person 2D pose estimation using part affinity fields[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. July 21-26, 2017, Honolulu, HI, USA. IEEE, 2017: 1302-1310.