Human Action recognition (HAR) has been a prominent area of research within machinelearning over the last few decades. Its applications span domains such as visual surveillance, robotics, and pedestrian detection. De...
详细信息
ISBN:
(纸本)9783031708183;9783031708190
Human Action recognition (HAR) has been a prominent area of research within machinelearning over the last few decades. Its applications span domains such as visual surveillance, robotics, and pedestrian detection. Despite the numerous techniques introduced by computer vision researchers to address HAR, persistent challenges include dealing with redundant features and computational cost. This paper specifically addresses the challenge of silhouette-based human activity recognition. While previous research on silhouette-based HAR has predominantly focused on recognition from a singular perspective, the aspect of view invariance has often been overlooked. This paper presents a novel framework that aims to achieve view-invariant Human Action recognition. The proposed approach integrates a pre-processingstage based on the extraction of multiple 2D Differential History Binary Motions (DHBMs) from spatio-temporal frames capturing human motion. These multi-batch DHBMs are then used to capture and analyse human behaviour using the Decimal Descriptor pattern (DDP) approach. This strategy enhances the extraction of intricate details from image data, contributing to a more robust HAR methodology. The selected features are processed by the Sparse stacked Auto-encoder (SSAE), a representative of deep learning methods, to provide effective detection of human activity. The subsequent classification is performed using Softmax. The experiments are conducted on publicly available datasets, namely IXMAS and KTH. The results of the study demonstrate the superior performance of our methodology compared to previous approaches, achieving higher levels of accuracy.
The most significant and primary source of income in the economy of the southern region of India is the production of coconuts. Recent observations have shown that the majority of coconut trees are afflicted with dise...
详细信息
The analysis of illness pictures generated by using high-tech digital instruments forms the basis of a diverse array of medical diagnoses. The use of artificial intelligence (AI) in the evaluation of medical images ha...
详细信息
Plastic fragments that contain microplastic can have an impact on ecosystems and human health. Since the 1970s, the complexity of microplastic analysis has been a big challenge. This study introduces a machine learnin...
详细信息
With the increased usage of social media and associated cyber frauds, current scenario demands for authenticated information. This in turn necessitates for the valid and verified information of individuals from variou...
详细信息
The training of basketball players is a complex and hard work. In the game, how to finish the ball quickly and accurately, and how to improve the goal rate and score through correct and effective methods. This paper f...
详细信息
In order to recognize patterns in images, this study tests the performance of many 'machinelearning algorithms' and feature extraction methods. Here, synthetic photographs of handwritten digits are used to co...
详细信息
With the frequent occurrence of geological disasters, landslide identification has become an important research problem. In recent years, with the application and research of deep learning in the fields of computer vi...
详细信息
Over the years there has been huge improvements in the performance of imageprocessing Algorithms due to increase in computation power of Devices as well as use of Neural Networks. This paper focuses on comparison of ...
详细信息
Real-time hand tracking differs greatly from RGB video tracking of frequently monitored objects. Because it is a biological object, the hand experiences both physical and behavioral changes as it moves. If a basic RGB...
详细信息
暂无评论