Vehicle Classification and Distance Estimation using Support Vector Machine
J. Jayasurya1, R. Seenu2, M. Jagannath3
1J. Jayasurya, School of Electronics Engineering, Vellore Institute of Technology (VIT), Chennai (Tamil Nadu), India.
2R. Seenu, School of Electronics Engineering, Vellore Institute of Technology (VIT), Chennai (Tamil Nadu), India.
3M. Jagannath, School of Electronics Engineering, Vellore Institute of Technology (VIT), Chennai (Tamil Nadu), India.
Manuscript received on 01 May 2019 | Revised Manuscript received on 15 May 2019 | Manuscript published on 30 May 2019 | PP: 2175-2178 | Volume-8 Issue-7, May 2019 | Retrieval Number: G6108058719/19©BEIESP
Open Access | Ethics and 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: While driving a vehicle, the driver must pay attention to the environment around the vehicle. If the driving period increases, the driver loses his attention that would eventually lead to road accident. There are literatures which address the prevention of road accidents by considering several factors like environmental conditions, traffic density, psychological nature of the driver, etc. Among the factors, the detection of vehicle in front is considered as one of the road safety measures. In this paper, the datasets are collected from GTI vehicle image database and KITTI vision benchmark suite. The algorithm is developed for vehicle classification and the distance estimation by employing a conventional computer vision technique called Histogram of Oriented Gradients (HOG), combined with a machine learning algorithm called Support Vector Machine (SVM). The proposed algorithm could be implemented on autonomous vehicle system to assist the driver effectively and also reduce the vehicle collision.
Keyword: Vehicle Collision; Automatic Guided Vehicle; Histogram of Oriented Gradients; Support Vector Machine.
Scope of the Article: Classification.