Adaptive δ-Generalized Labeled Multi-Bernoulli Filter for Multi-Object Detection and Tracking

Abstract

The δ-generalized labeled multi-Bernoulli (δ-GLMB) filter is an efficient approach for multiobject tracking in case of high clutter density and low detection probability. However, the formulation of the original δ-GLMB filter requires that the birth δ-GLMB filtering density is known a priori. It is inapplicable for the birth object appearing from unknown positions. To address this problem, an adaptive δ-GLMB filter is proposed to detect and track the birth objects with unknown position information. This adaptive filter establishes the birth δ-GLMB filtering density by using measurements at previous three successive times. Simulation results indicate that the proposed adaptive δ-GLMB filter may efficiently detect and track the multiple objects with unknown positions. Simulation results also demonstrate that the proposed adaptive δ-GLMB filter performs better than the other existing adaptive filters.

Keywords

• Multi-object tracking
• δ-generalized labeled multi-Bernoulli filter
• object detection
• adaptive filter