In this paper, we propose violent event detection in video using fusion of global histograms of oriented gradients (GHOG) and GIST feature descriptors. The significant features are extracted from GHOG, GIST, and GHOG + GIST. Finally, significant features are used with the support vector machine (SVM) classifier for the detection of a violent event. The proposed feature descriptor method used Hockey Fight and Violent-Flows dataset for the experimentation, and empirical results show that the proposed GHOG + GIST fusion feature descriptor is effective and efficient than other state of the art techniques.
CITATION STYLE
Lohithashva, B. H., Manjunath Aradhya, V. N., & Guru, D. S. (2021). Violent Event Detection: An Approach Using Fusion GHOG-GIST Descriptor. In Lecture Notes in Electrical Engineering (Vol. 700, pp. 881–890). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-15-8221-9_82
Mendeley helps you to discover research relevant for your work.