Multiple People Tracking Using Non-iterative Tensor Voting Method

نویسنده

  • Shipra Ojha
چکیده

Human tracking is an emerging research field in computer vision and video surveillance. Lightning changes and occlusion are the main challenges faced during tracking. This paper focuses on people tracking both in indoor and outdoor scenes. Our method is based on color modeling using tensor voting framework, which can handle these challenges. The lightning conditions are controlled by homomorphic filtering and occlusion is handled by modelling the color clothing of each individual. Tensor voting is non-iterative method in which only the scale has to be specified at beginning and is able to build number of clusters automatically. The experimental work shows that our method can track the person successfully and also handle occlusion by finding the centroid of a person.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Multiple Target Tracking in Wireless Sensor Networks Based on Sensor Grouping and Hybrid Iterative-Heuristic Optimization

A novel hybrid method for tracking multiple indistinguishable maneuvering targets using a wireless sensor network is introduced in this paper. The problem of tracking the location of targets is formulated as a Maximum Likelihood Estimation. We propose a hybrid optimization method, which consists of an iterative and a heuristic search method, for finding the location of targets simultaneously. T...

متن کامل

Continuous Multi-Views Tracking using Tensor Voting

This paper presents a new approach for continuous tracking of moving objects observed by multiple fixed cameras. The continuous tracking of moving objects in each view is realized using a Tensor Voting based approach. We infer objects trajectories by performing a perceptual grouping in 2D+t using Tensor Voting. Also, a multi-scale approach bridging gaps in object trajectories is presented. The ...

متن کامل

Perfect Tracking of Supercavitating Non-minimum Phase Vehicles Using a New Robust and Adaptive Parameter-optimal Iterative Learning Control

In this manuscript, a new method is proposed to provide a perfect tracking of the supercavitation system based on a new two-state model. The tracking of the pitch rate and angle of attack for fin and cavitator input is of the aim. The pitch rate of the supercavitation with respect to fin angle is found as a non-minimum phase behavior. This effect reduces the speed of command pitch rate. Control...

متن کامل

Continuous Multi-View Tracking using Tensor Voting

We present a novel approach for continuous tracking of moving objects observed by multiple fixed cameras. The continuous tracking of moving objects in each view is realized using a Tensor Voting based approach. We infer objects trajectories by performing a perceptual grouping in 2D+t. Gaps are bridged using a multi-scale approach in object trajectories. The trajectories obtained from the multip...

متن کامل

Are Iterations and Curvature Useful for Tensor Voting?

Tensor voting is an efficient algorithm for perceptual grouping and feature extraction, particularly for contour extraction. In this paper two studies on tensor voting are presented. First the use of iterations is investigated, and second, a new method for integrating curvature information is evaluated. In opposition to other grouping methods, tensor voting claims the advantage to be non-iterat...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015