Detection and Tracking of Multiple Moving Objects in Real-World Scenarios using Attributed Relational Graph

This paper presents a new algorithm for detecting and tracking multiple moving objects in both outdoor and indoor environments. The proposed method measures the change of a combined color-texture feature vector in each image block to detect moving objects. The texture feature is extracted from DCT frequency domain. An attributed relational graph (ARG) is used to represent each object, in which vertices are associated to an objectpsilas sub-regions and edges represent spatial relations among them. Multiple cues including color, texture, and spatial position are integrated to describe each objectpsilas sub-regions. Object tracking and identification are accomplished by inexact graph matching, which enables us to track partially occluded objects and to cope with object articulation. An ARG adaptation scheme is incorporated into the system to handle the changes in object scale and appearance. The experimental results prove the efficiency of the proposed method.