A hierarchical framework for face tracking using state vector fusion for compressed video

نویسندگان

  • Jun Wang
  • Radhakrishna S. V. Achanta
  • Mohan S. Kankanhalli
  • Philippe Mulhem
چکیده

Faces usually are the most interesting objects in certain categories of video like home videos and news clips. In this paper a novel sensor fusion based face tracking system is presented that tracks faces in compressed video, and aids automatic video indexing. Tracking is done by fusing the measurements from three independent sensors – motion and colour based trackers (derived from [2]) and a face detector (presented in [1]) using a novel hierarchical framework based on Kalman filter state vector fusion. The tracking results show that the fused results are better than those of any individual sensors or their mean.

برای دانلود 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

A Sensor Fusion Based Object Tracker for Compressed Video

Object tracking is very important for automatic indexing of video content. This work shows tracking of objects directly using compressed MPEG video data. Two sensors, one using motion vectors and the other using DCT coefficients obtained from compressed video stream, provide measurements for the location of the object being tracked. The optimal estimate from the two measurements is found using ...

متن کامل

A multimedia content modeling and classification methodology using visual information for the protection of sensitive user groups

The thesis concerns the problems of visual tracking and violence detection in video sequences. For the visual tracking problem, two feature fusion frameworks are presented. For violence detection, a system that classifies movie segments as violent or non-violent is proposed. The first tracking framework called ’Model Fusion via Proposal’ (MFP) framework, provides a way to efficiently fuse visua...

متن کامل

Covariance Analysis of a vector tracking GPS receiver based on MMSE multiuser Detection

In high dynamic conditions, using vector tracking loops instead of scalar tracking loops in GPS receivers is proved as an efficient method to compensate the performance. The Minimum Mean Squared Error detector as a multiuser detector is applied in the vector tracking loop for more reliability and efficiency. The Kalman filter does the two tasks of tracking and extracting the navigation data aft...

متن کامل

On Face Tracking in Video Sequences

This paper proposes a framework to track faces in image sequences in a video. The technique combines face detection through using Support Vector Machine (SVM) with target tracking through using a Kalman filter. The adjacent locations of the target point are predicted in a search window that reduces the number of image regions that are candidates for faces. Thus, the method can predict the objec...

متن کامل

Neural Network Performance Analysis for Real Time Hand Gesture Tracking Based on Hu Moment and Hybrid Features

This paper presents a comparison study between the multilayer perceptron (MLP) and radial basis function (RBF) neural networks with supervised learning and back propagation algorithm to track hand gestures. Both networks have two output classes which are hand and face. Skin is detected by a regional based algorithm in the image, and then networks are applied on video sequences frame by frame in...

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

برای دانلود 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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2003