Abstract

Detecting objects in an image and tracking them through a video sequence has been a fundamental problem in computer vision and has led to a significant amount of research in the last few decades. The main challenge is achieving invariance to facial appearance and motion. Variations result from many factors, including environmental conditions (lighting, clutter), imaging sensors (frame rate, quantization, and noise) and inherent non-rigid variations in the pose, shape, structure and motion of a face. This paper is proposed for the Detection and Tracking of Human using Computer vision based approach. The protection of critical transportation assets and infrastructure is an important one. In this paper, we developed components of an Automated Thermal video Surveillance system to track pedestrians and detect situations where people may be in danger, as well as suspicious motion or activities at or near critical transportation assets. A thermal Imaging based Automatic Smart Video Surveillance system involves Human detection, Human Tracking and Human Activity Recognition. The objective of this paper is to achieve good results for Human Detection, Human Tracking and Human Activity Recognition. The Video focus is also analyzed for the video Surveillance systems. This paper involves the improvement of extracting moving objects from an original digital thermal video input such as an AVI, FLV, MPEG file etc.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call