A detection-based multiple object tracking method

TLDR

Object detection makes local decisions, while tracking validates detections over time, acting as a temporal detector that makes global decisions across frames. The paper proposes a method for tracking multiple objects whose number is unknown and varies during tracking. The method maintains a graph of multiple hypotheses about object counts and trajectories, extends and prunes it with image evidence, feeds location predictions back to detection, and selects the most probable hypothesis as the tracking result. The method tightly integrates detection and tracking, and experimental results demonstrate its effectiveness.

Abstract

In this paper we describe a method for tracking multiple objects whose number is unknown and varies during tracking. Based on preliminary results of object detection in each image which may have missing and/or false detection, the multiple object tracking method keeps a graph structure where it maintains multiple hypotheses about the number and the trajectories of the objects in the video. The image information drives the process of extending and pruning the graph, and determines the best hypothesis to explain the video. While the image-based object detection makes a local decision, the tracking process confirms and validates the detection through time, therefore, it can be regarded as temporal detection which makes a global decision across time. The multiple object tracking method gives feedbacks which are predictions of object locations to the object detection module. Therefore, the method integrates object detection and tracking tightly. The most possible hypothesis provides the multiple object tracking result. The experimental results are presented.