AI-based vision techniques for human activity recognition in surveillance videos

Deep Features Evaluation Method of Human Action Recognition Based on Convolutional Neural Network

Human Action Recognition (HAR) in unconstrained video remains difficult due to cluttered backgrounds, camera motion, and long-range temporal dependencies. The recognition of human action is the most complex study in the area of Artificial Intelligence (AI) and Computer Vision (CV). Machine vision for online and offline video processing is typically employed in the development of human behavior recognition systems. In video broadcasting and analysis, identifying the type and content of human actions present in the footage is a fundamental requirement. In this article, we propose a compact and deployable Convolutional Neural Network-Long Short Term Memory (CNN-LSTM) framework that combines a 2D convolutional backbone (AlexNet) for frame-level descriptors with an LSTM head for sequence modeling. The approach is evaluated on three representative benchmarks KTH (6 classes), Hollywood-2 (12 actions), and UCF-50 (50 actions). The system attains strong aggregate performance, reaching 98.5% accuracy on KTH, 93.0% accuracy on UCF-50, and 96.0% mAP on Hollywood-2, with improvements distributed broadly across classes. Error–length analyses show that recognition quality rises steadily with longer clips and that the recurrent module extracts the largest gains, while precision–recall and ROC curves with superior Area Under the Curve (AUC) and reliability demonstrate improved ranking and probability calibration across operating points. Despite a larger parameter count than several baselines, the design achieves the most favorable efficiency profile measured at 18ms per frame latency, 135 mJ per frame energy, and the highest throughput placing it on the accuracy–latency–energy Pareto frontier. An ablation study confirms the centrality of temporal modeling (6-12 percentage-point drops without the LSTM), the benefit of longer temporal windows, and the usefulness of stepped learning-rate schedules for stable optimization. The results indicate a robust, real-time-capable solution for video understanding in both offline analytics and online deployment.

A Comprehensive Review of Human Activity Recognition Methods: Trends, Challenges, and Future Directions

Human Activity Recognition (HAR) is a fast-growing research area that focuses on identifying human actions using data collected from sensors and vision-based devices. It plays an important role in applications like health monitoring, smart homes, surveillance, sports analysis, and human-computer interaction. In recent years, several methods have been developed to improve the performance of HAR systems using machine learning, deep learning, and hybrid models. This paper presents a detailed review of different methods used in HAR. The study is divided into three main categories: vision-based methods, sensor-based methods, and hybrid approaches that combine both types. Each method is discussed with examples from recent research, along with their advantages and limitations. A comparison is also provided in the form of a table to highlight the performance and challenges of each approach. Although HAR systems have achieved good results in controlled environments, several challenges still remain. These include poor generalization to new users or unknown environments, difficulty in recognizing complex or overlapping activities, dependence on large datasets, and lack of real-time performance. This paper also discusses these research gaps based on recent findings. The future of HAR depends on building more accurate, reliable, and real-time systems that can adapt to different situations. The paper concludes by suggesting possible directions for future work, such as the development of lightweight models, use of standard datasets, better handling of real-time data, and making models more interpretable.

Enhancing Human Activity Recognition using YOLO-based Preprocessing in Deep Learning Frameworks

Human action recognition (HAR) plays a crucial role in safety monitoring, intelligent surveillance systems, and human-computer interaction applications. In this study, we evaluate and compare several deep learning architectures for HAR using the Weizmann dataset, using a YOLO-based preprocessing, including CNN, CNN with attention mechanism, MobileNetV2, and InceptionV3. The proposed YOLO-based preprocessing method was specifically designed to enhance feature extraction efficiency by isolating human subjects from background clutter, thereby reducing noise and improving spatial focus. Experimental results demonstrate that the YOLO-based CNN achieved state-of-the-art performance with an accuracy of 99.6%, significantly outperforming the CNN-Attention model (98.6%), MobileNetV2 (96.1%), and InceptionV3 (93.7%). These findings underscore the importance of robust preprocessing techniques and highlight the superiority of the proposed YOLO-based method in handling complex real-world scenarios.

Query-Driven Intelligent Surveillance using Deep Learning for Activity Recognition and Video Summarization

Surveillance systems have experienced rapid growth which results in production of large video data streams. The monitoring process for this data becomes challenging because its volume exceeds human capacity and this situation creates potential for errors. Our research presents a hybrid intelligent surveillance system which conducts automatic video analysis through its two core operational components. The system employs two primary components to achieve its objectives. The SlowFast-based model enables users to track activities through their development across various time intervals. The system employs YOLO-based models to identify critical objects which include fire and weapons and road accidents through real-time monitoring. The system achieves improved stability through the implementation of a temporal debouncing method. The system uses multiple frame detection checks to improve detection accuracy which helps prevent false alarms. The system includes a module dedicated to video summarization which creates a summary from detected activities and visual changes. The system discards unneeded video content while retaining essential information through this process. The model uses a dataset that contains 4758 video clips which display various classification types. The system reaches 85% validation accuracy which demonstrates its ability to handle new data successfully. The system operates on devices with limited resources while providing an immediate alert system to inform users about essential incidents. The system delivers an easy-to-use and effective solution for intelligent video surveillance operations.

Human Activity Recognition using RGB-DVS Cameras: A Multi-modal Heat Conduction Model and A Benchmark Dataset

Computer vision-based human motion recognition: technological evolution, key challenges, and cutting-edge trends

Human motion recognition is an important research direction in computer vision, aiming to automatically analyze human pose changes and action semantics from images or videos captured by visual sensors. This paper systematically reviews the evolution of computer vision-based human motion recognition technology, from traditional handcrafted feature methods to convolutional neural networks and recurrent neural networks in the deep learning era, and then to the recently emerging Transformer architectures and vision-language models. The core ideas and technical characteristics of various approaches are comprehensively analyzed. On this basis, key challenges in current research are deeply explored, including the complexity of spatiotemporal feature extraction, robustness issues with occlusion and viewpoint changes, difficulties in fine-grained action and few-shot learning, and the trade-off between multimodal fusion and computational efficiency. Finally, future development trends are discussed, pointing out that cutting-edge directions such as 3D human pose estimation, fisheye lens adaptation, micro-action detection, and attribute-aware generation will drive the field toward higher precision, stronger generalization capabilities, and broader application scenarios. This paper aims to provide systematic technical reference and forward-looking insights for researchers in human motion analysis and intelligent human-computer interaction.