Tracking non-rigid, moving objects based on color cluster flow

In this contribution we present an algorithm for tracking non-rigid, moving objects in a sequence of colored images, which were recorded by a non-stationary camera. The application background is vision-based driving assistance in the inner city. In an initial step, object parts are determined by a divisive clustering algorithm, which is applied to all pixels in the first image of the sequence. The feature space is defined by the color and position of a pixel. For each new image the clusters of the previous image are adapted iteratively by a parallel k-means clustering algorithm. Instead of tracking single points, edges, or areas over a sequence of images, only the centroids of the clusters are tracked. The proposed method remarkably simplifies the correspondence problem and also ensures a robust tracking behavior.

• Type: Conference
• Year: 1997
• Where: CVPR
• Authors: Bernd Heisele, Ulrich Kressel, W. Ritter
• Keywords: Computer Vision, CVPR 1997, Divisive Clustering Algorithm, K-means Clustering Algorithm, Non-stationary Camera, Robust Tracking Behavior, Vision-based Driving Assistance