An Efficient Human Activity Recognition Technique Based on Deep Learning
Article dans une revue avec comité de lecture
In this paper, we present a new deep learning-based human activity recognition technique. First, we track and extract human body from each frame of the video stream. Next, we abstract human silhouettes and use them to create binary space-time maps (BSTMs) which summarize human activity within a defined time interval. Finally, we use convolutional neural network (CNN) to extract features from BSTMs and classify the activities. To evaluate our approach, we carried out several tests using three public datasets: Weizmann, Keck Gesture and KTH Database. Experimental results show that our technique outperforms conventional state-of-the-art methods in term of recognition accuracy and provides comparable performance against recent deep learning techniques. It’s simple to implement, requires less computing power, and can be used for multi-subject activity recognition.
Files in this item
Showing items related by title, author, creator and subject.
3D Human Pose Estimation with a Catadioptric Sensor in Unconstrained Environments Using an Annealed Particle Filter Article dans une revue avec comité de lectureABABSA, Fakhreddine; HADJ-ABDELKADER, Hicham; BOUI, Marouane (MDPI, 2020)The purpose of this paper is to investigate the problem of 3D human tracking in complex environments using a particle filter with images captured by a catadioptric vision system. This issue has been widely studied in the ...
Augmented Reality Application in Manufacturing Industry: Maintenance and Non-destructive Testing (NDT) Use Cases Communication avec acteABABSA, Fakhreddine (Springer International Publishing, 2020)In recent years, a structural transformation of the manufacturing industry has been occurring as a result of the digital revolution. Thus, digital tools are now systematically used throughout the entire value chain, from ...
Communication avec acteFISCHINI, Antoine; ABABSA, Fakhreddine; GRASSER, Mickaël (2018)Augmented Reality (AR) is a strong growing research topic in several areas including industry, training, art and entertainment. AR can help users to achieve very complex tasks by enhancing their vision with useful and ...
Communication avec actePRUVOST, Martin; MIALOCQ, Pierre; ABABSA, Fakhreddine (2018)This paper presents an AR system architecture for assisting complex assembly work by adding visual information superimposed on the physical assembly parts.
Image processing through deep learning after DI extraction for the SHM of aeronautic composite structures using Lamb waves Communication avec acteCe papier présente une méthode de classification des dommages présents dans des plaques composites utilisées dans le contexte aéronautique. les approches utilisées sont issues du traitement du signal, de l'image et de ...