Multi-Object Tracking with Deep Learning Ensemble for Unmanned Aerial System Applications

TL;DR

This paper introduces a robust multi-object tracking system for unmanned aerial systems that combines a deep learning-based kinematic prediction model with visual similarity measures, improving tracking accuracy in challenging aerial surveillance scenarios.

Contribution

The work presents DeepEKF, a novel sequence-to-sequence kinematic prediction model integrated with attention-based visual scoring within a multi-hypothesis tracking framework for UAS applications.

Findings

Enhanced tracking accuracy in unpredictable motion scenarios

Improved performance with significant frame gaps

Effective integration of kinematic and visual models

Abstract

Multi-object tracking (MOT) is a crucial component of situational awareness in military defense applications. With the growing use of unmanned aerial systems (UASs), MOT methods for aerial surveillance is in high demand. Application of MOT in UAS presents specific challenges such as moving sensor, changing zoom levels, dynamic background, illumination changes, obscurations and small objects. In this work, we present a robust object tracking architecture aimed to accommodate for the noise in real-time situations. We propose a kinematic prediction model, called Deep Extended Kalman Filter (DeepEKF), in which a sequence-to-sequence architecture is used to predict entity trajectories in latent space. DeepEKF utilizes a learned image embedding along with an attention mechanism trained to weight the importance of areas in an image to predict future states. For the visual scoring, we experiment with different similarity measures to calculate distance based on entity appearances, including a convolutional neural network (CNN) encoder, pre-trained using Siamese networks. In initial evaluation experiments, we show that our method, combining scoring structure of the kinematic and visual models within a MHT framework, has improved performance especially in edge cases where entity motion is unpredictable, or the data presents frames with significant gaps.