IMM-JPDAF with Sensor Fusion for Enhanced Maneuvering Target Association

Tsui-Yu Chan and Shau-Shiun Jan

Peer Reviewed

Abstract:	Accurate multi-target tracking is essential in radar-based systems for surveillance, navigation, and autonomous operations applications. Challenges like clutter interference, ambiguous data association, and unpredictable target maneuvers complicate this process. This study proposes an enhanced tracking approach integrating sequential sensor fusion with the Interacting Multiple Model (IMM) and Joint Probabilistic Data Association Filter (JPDAF) framework. IMM enhances adaptability using multiple dynamic models, while JPDAF excels at data association by considering measurement probabilities across all targets. Sequential sensor fusion further improves estimation accuracy and system reliability by processing data from multiple sensors of the same type. The proposed sensor fusion IMM-JPDAF algorithm effectively addresses overlapping validation gates. Validated using practical aircraft data, the algorithm can avoid duplicate associations and maintain robust tracking in scenarios with closely spaced and crossing targets, achieving significant improvements in RMSE and update rates under multi-target conditions. Keywords—multiple target tracking, interacting multiple model filter, joint probabilistic data association filter, sensor fusion
Published in:	2025 IEEE/ION Position, Location and Navigation Symposium (PLANS) April 28 - 1, 2025 Salt Lake Marriott Downtown at City Creek Salt Lake City, UT
Pages:	631 - 635
Cite this article:	Chan, Tsui-Yu, Jan, Shau-Shiun, "IMM-JPDAF with Sensor Fusion for Enhanced Maneuvering Target Association," 2025 IEEE/ION Position, Location and Navigation Symposium (PLANS), Salt Lake City, UT, April 2025, pp. 631-635.
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In