Local Feature Extraction in the Near Infra-Red Domain for Wildlife Mammals Tracking Purpose

Abstract

Nowadays, research in area of intelligent transportation system is focused on analysis of traffic flow by computer vision techniques. Keypoint analysis represents detection, modelling and recognition of objects in traffic flow and object tracking as well. The main goal of this paper is to propose new approach to detect and modelling 3D objects that move on road surface. At the beginning, basic methods of object recognition and modelling of 3D object are shortly described. The modified algorithm based on background subtraction and creation of 3D model by depth map is proposed. Finally, the results of developed algorithm are depicted through the last part of this paper.

Keywords

• intelligent transportation system
• animal detection
• object recognition
• infrared domain
• local feature extraction