Detecting Vehicle Motion using Deep Gaussian Mixture Model with SCI-kit Learn
Tamilarasu Viswanathan1, N. Vinothkumar2
1Tamilarasu Viswanathan, Department of Electrical and Electronics Engineering, Kumaraguru College of Technology, Coimbatore (Tamil Nadu), India.
2N.Vinothkumar, Department of Electrical and Electronics Engineering, Kumaraguru College of Technology, Coimbatore (Tamil Nadu), India.
Manuscript received on 28 September 2019 | Revised Manuscript received on 10 November 2019 | Manuscript Published on 22 November 2019 | PP: 1216-1218 | Volume-8 Issue-6S3 September 2019 | Retrieval Number: F12070986S319/19©BEIESP | DOI: 10.35940/ijeat.F1207.0986S319
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Detecting vehicle motions are a progressively significant part in road surveillance and Traffic organizing systems. This paper presents a new Deep Gaussian based mixture model that predicts accurate in detecting vehicle motions. Although the existing arrangements based on conventional Gaussian mixture model which is limited in insufficient of many distinct points which eliminate covariance and solutions relative to infinite likelihood. In the proposed scheme, the deep learning neural network is used for including the more points with nested mixture models. To overcome the effects of adding more points the modification achieved in architecture development. The validation of proposed scheme is achieved with real-time videos and process with scikit learn based model.
Keywords: Motion Detection, Deep Gaussian Mixture Model, Neural Network, Computer Vision And Scikit Learn.
Scope of the Article: Deep Learning