A Survey on Deep Learning Architectures in Human Activities Recognition Application in Sports Science, Healthcare, and Security

The invention discloses a human body abnormal behavior detection method based on spatio-temporal information and human-object interaction. The method comprises the following steps: S1, carrying out data acquisition and labeling, S2, extracting position information of a person and an object, S3, extracting motion information of a person and an object, S4, modeling a human and object feature interaction relationship, S5, carrying out behavior classification and fusion, and S6, carrying out detection result optimization. Aiming at the problems of abnormal actions of falling to the ground, climbing and limb conflicts and continuous abnormal state detection, a person interaction mode is adopted to assist in judging abnormal behaviors, the continuous state of the abnormal behaviors is detected in combination with the change condition of the gravity center, and besides, the abnormal behaviors can be detected. Normal actions such as walking, standing and sitting can also be detected.

Human body abnormal behavior detection method based on space-time information and human-object interaction

This study explores a CNN based model to identify abnormal behavior in elevator cabs, which I have named S-LRCN ( S-Long-term Recurrent Convolutional Network). It starts with the detection of key points of the human skeleton by using the Openpose method, then further detects and tracks the human body through the CenterNet and DeepSort methods, and finally integrates the Long Short Term Memory Network (LSTM) and Convolutional Neural Network (CNN) to form a deep learning model. In this study, a large dataset (500 video clips) collected from real elevator cabs with different backgrounds has been applied to ensure the robustness and generalizability of the proposed model. At last, this study applies the two mainstream dangerous human behaviors, i.e., door blocking and door picking as case studies to test and evaluate the usability and availability. Experimental results show that the model has a 85% recognition rate of abnormal behavior.

Recognition of Abnormal Human Behavior in Elevators based on CNN

The invention relates to a monitoring video multi-dimensional pedestrian behavior intelligent analysis system and method. The system comprises an individual behavior analysis module, a small group behavior analysis module, a group behavior analysis module, a scene analysis module, a pedestrian behavior dimension evaluation module, an intelligent gateway, an application logic integration module anda video source management module. The method comprises the following steps: acquiring a monitoring video data stream, extracting video frames from the monitoring video data stream, and performing scene classification and pedestrian behavior dimension selection by using key video frame data; combining the scene and pedestrian behavior dimension information; performing decisions selected by the pedestrian behavior analysis module and transmission of management data; and performing intelligent behavior recognition through a pedestrian behavior analysis model of a scene integrated in the pedestrian behavior analysis module under the selected behavior dimension, and outputting a final pedestrian behavior recognition result. Pedestrian behavior recognition in various complex monitoring scenes and pedestrian behavior dimensions can be supported.

Monitoring video multi-dimensional pedestrian behavior intelligent analysis system and method

https://iopscience.iop.org/article/10.1088/1742-6596/1634/1/012016/pdf

Lightweight Crowd Counting Network based on Depthwise Separable Convolution

Video analysis for human action recognition is one of the most important research areas in pattern recognition and computer vision due to its wide applications. Deep learning-based approaches have been proven more effective than conventional feature engineering-based models. However, the performance is still unreliable when facing real-world application scenarios. Inspired by the Convolutional Neural Network (CNN) and Recurrent Long-Short Term Model (LSTM), this paper presents an augmented treble-stream deep neural network architecture that supports direct extraction of spatial-temporal features from video streams and their corresponding dense optical flows. This innovative approach assists effective detection of complex video event features that are annotated by rich event "appearance" and motion features. Substantially improved recognition accuracy is recorded during the experiments that are carried and benchmarked over public video event datasets, for example, UCF 101 and HMDB 51. Analytical evaluation approves the validity and effectiveness of the treble-stream neural network design.

Dengguo Yao

Papers

Recognition of Abnormal Human Behavior in Elevators based on CNN

Monitoring video multi-dimensional pedestrian behavior intelligent analysis system and method

Lightweight Crowd Counting Network based on Depthwise Separable Convolution

An Augmented Treble Stream Deep Neural Network for Video Analysis