An Efficient Human Activity Recognition Technique Based on Deep Learning
TypeArticles dans des revues 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.
Evaluating Added Value of Augmented Reality to Assist Aeronautical Maintenance Workers - Experimentation on On-Field Use Case LOIZEAU, Quentin; DANGLADE, Florence; ABABSA, Fakhreddine; MERIENNE, Frédéric (2019)Augmented Reality (AR) technology facilitates interactions with information and understanding of complex situations. Aeronautical Maintenance combines complexity induced by the variety of products and constraints associated ...
Towards improving the future of manufacturing through digital twin and augmented reality technologies RABAH, Souad; ASSILA, Ahlem; KHOURI, Elio; MAIER, Florian; ABABSA, Fakhreddine; BOURNY, Valéry; MAIER, Paul; MERIENNE, Frédéric (Elsevier BV, 2018)We are on the cusp of a technological revolution that will fundamentally change our relationships to others and the way we live and work. These changes, in their importance, scope, and complexity, is different than what ...
PRUVOST, 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.
ABABSA, Fakhreddine; HE, Junhui; CHARDONNET, Jean-Rémy (2018)In augmented reality environments, the natural hand interaction between a virtual object and the user is a major issue to manipulate a rendered object in a convenient way. Microsoft’s HoloLens (Microsoft 2018) is an ...
FISCHINI, 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 ...