Track Anything Rapter(TAR)

TL;DR

This paper presents TAR, an advanced UAV tracking system that integrates pre-trained models and multimodal queries for precise object tracking in various scenarios, validated against ground truth and tested with multiple modalities.

Contribution

Develops TAR, a novel UAV tracking system combining pre-trained models and multimodal queries for improved object detection and tracking.

Findings

TAR achieves stable and precise tracking on a custom drone.

The system effectively handles occlusions using foundational models.

Multi-modality support enhances tracking versatility.

Abstract

Object tracking is a fundamental task in computer vision with broad practical applications across various domains, including traffic monitoring, robotics, and autonomous vehicle tracking. In this project, we aim to develop a sophisticated aerial vehicle system known as Track Anything Rapter (TAR), designed to detect, segment, and track objects of interest based on user-provided multimodal queries, such as text, images, and clicks. TAR utilizes cutting-edge pre-trained models like DINO, CLIP, and SAM to estimate the relative pose of the queried object. The tracking problem is approached as a Visual Servoing task, enabling the UAV to consistently focus on the object through advanced motion planning and control algorithms. We showcase how the integration of these foundational models with a custom high-level control algorithm results in a highly stable and precise tracking system deployed on a custom-built PX4 Autopilot-enabled Voxl2 M500 drone. To validate the tracking algorithm's performance, we compare it against Vicon-based ground truth. Additionally, we evaluate the reliability of the foundational models in aiding tracking in scenarios involving occlusions. Finally, we test and validate the model's ability to work seamlessly with multiple modalities, such as click, bounding box, and image templates.