EFFICIENT HIERARCHICAL MOTION FILTERING FOR ENHANCED ACTION RECOGNITION IN DENSE VIDEO ENVIRONMENTS
Journal: International Journal of Mechanical Engineering and Technology(IJMET) (Vol.9, No. 1)Publication Date: 2018-01-28
Authors : Bijesh Dhyani;
Page : 1253-1262
Keywords : Hierarchical motion filtering; action detection; video segmentation; 2-D Harris corners; Motion History Image (MHI); Gaussian Mixture Model (GMM); activity categorization; UCF50 dataset; HMDB51 dataset; background motions; realtime applications.;
Abstract
This study suggests a powerful hierarchical motion filtering technique for enhancing the precision of action detection in busy video situations. In order to extract the most important motion information and minimise distracting background motions, it requires segmenting the person from the video, detecting 2-D Harris corners, computing the Motion History Image (MHI), while applying a hierarchical filtering technique. We utilise a Gaussian Mixture Model (GMM) to categorise the retrieved characteristics in order to categorise the activities. Our method produces cutting-edge outcomes on the two difficult datasets, UCF50 and HMDB51. The suggested method differs from existing approaches in a number of ways, including its ability to handle the distracting background motions brought on by moving objects in busy video environments, the accuracy of its action recognition results due to the hierarchical filtering technique and the use of GMM for classification, and its computational efficiency and suitability for real-time applications.
Other Latest Articles
- A NOVEL APPROACH FOR ACTION RECOGNITION IN VIDEOS BASED ON SPATIOTEMPORAL CORNERS AND OPTICAL FLOW ESTIMATION
- ASSESSMENT OF THE RELATIONSHIP BETWEEN CORPORATE SOCIAL RESPONSIBILITY ENVIRONMENTAL GOALS IMPLEMENTATION AND FINANCIAL AND OPERATIONAL INDICATORS OF AIRLINES
- RUSSIA-UKRAINE WAR: TRANSPORT AND LOGISTICS SUPPORT FOR GRAIN SUPPLY CHAIN IN REGIONAL FOOD SAFETY
- EDGE DETECTION TECHNIQUE BASED ON BILATERAL FILTERING AND ITERATIVE THRESHOLD SELECTION ALGORITHM AND TRANSFER LEARNING FOR TRAFFIC SIGN RECOGNITION
- EMG-BASED HAND GESTURE RECOGNITION SYSTEM WITH TRANSFERABLE ADAPTIVE DOMAIN ADVERSARIAL NEURAL NETWORK FOR VIRTUAL REALITY APPLICATIONS
Last modified: 2023-06-09 16:11:14