Statistical Information Fusion for Multiple-View Sensor Data in Multi-Object Tracking

TL;DR

This paper introduces an adaptive statistical information fusion method for multi-view sensor data in multi-object tracking, improving accuracy and object inclusion over existing methods by dynamically tuning sensor weights based on information content.

Contribution

It enhances the Generalized Covariance Intersection with adaptive weights using Cauchy-Schwarz divergence and applies it within a Labeled Multi-Bernoulli filter for improved multi-object tracking.

Findings

Significantly outperforms state-of-the-art methods in tracking accuracy.

Effectively integrates multi-view sensor data with different fields of view.

Successfully adapts sensor weights for each object in the tracking process.

Abstract

This paper presents a novel statistical information fusion method to integrate multiple-view sensor data in multi-object tracking applications. The proposed method overcomes the drawbacks of the commonly used Generalized Covariance Intersection method, which considers constant weights allocated for sensors. Our method is based on enhancing the Generalized Covariance Intersection with adaptive weights that are automatically tuned based on the amount of information carried by the measurements from each sensor. To quantify information content, Cauchy-Schwarz divergence is used. Another distinguished characteristic of our method lies in the usage of the Labeled Multi-Bernoulli filter for multi-object tracking, in which the weight of each sensor can be separately adapted for each Bernoulli component of the filter. The results of numerical experiments show that our proposed method can successfully integrate information provided by multiple sensors with different fields of view. In such scenarios, our method significantly outperforms the state of art in terms of inclusion of all existing objects and tracking accuracy.