Long Distance Ground Target Tracking with Aerial Image-to-Position Conversion and Improved Track Association

Abstract

A small drone is capable of capturing distant objects at a low cost. In this paper, long distance (up to 1 km) ground target tracking with a small drone is addressed for oblique aerial images, and two novel approaches are developed. First, the coordinates of the image are converted to real-world based on the angular field of view, tilt angle, and altitude of the camera. Through the image-to-position conversion, the threshold of the actual object size and the center position of the detected object in real-world coordinates are obtained. Second, the track-to-track association is improved by adopting the nearest neighbor association rule to select the fittest track among multiple tracks in a dense track environment. Moving object detection consists of frame-to-frame subtraction and thresholding, morphological operation, and false alarm removal based on object size and shape properties. Tracks are initialized by differencing between the two nearest points in consecutive frames. The measurement statistically nearest to the state prediction updates the target’s state. With the improved track-to-track association, the fittest track is selected in the track validation region, and the direction of the displacement vector and velocity vectors of the two tracks are tested with an angular threshold. In the experiment, a drone hovered at an altitude of 400 m capturing video for about 10 s. The camera was tilted 30° downward from the horizontal. Total track life (TTL) and mean track life (MTL) were obtained for 86 targets within approximately 1 km of the drone. The interacting multiple mode (IMM)-CV and IMM-CA schemes were adopted with varying angular thresholds. The average TTL and MTL were obtained as 84.9–91.0% and 65.6–78.2%, respectively. The number of missing targets was 3–5; the average TTL and MTL were 89.2–94.3% and 69.7–81.0% excluding the missing targets.

Strong Interference UAV Motion Target Tracking Based on Target Consistency Algorithm

“…The MIA-Net effectively solved the cross-UAV association problem by constructing cross-UAV target topology relationships through a local-global matching algorithm, and effectively complemented the obscured targets by taking advantage of multiple UAV viewpoint mapping. Yeom [24] studied ground target tracking algorithms at long distances (up to 1 km) using small UAVs and improved the association between trajectories by selecting the most suitable of multiple trajectories in a dense trajectory environment using nearest neighbor association rules. The detection of moving targets in the algorithm also includes frame-to-frame subtraction and thresholding, morphological operations and false alarm elimination based on object size and shape property, and the target's trajectory is initialized by the difference between the two nearest points in consecutive frames; then, the measurement statistically nearest to the state prediction updates the target's state.…”

Thermal Image Tracking for Search and Rescue Missions with a Drone

“…Multiple-target tracking is performed via three stages: track initialization, maintenance, and termination [28][29][30]. The track maintenance consists of measurement-to-track association (measurement association), track update, and track-to-track association (track association).…”

“…Bold fonts inside red bold line boxes include the newly proposed contents in this paper. A scheme of the nearest neighbor measurement association, followed by track association, track termination, and validity testing, has been developed in previous works showing robust performance in ground target tracking from visible images acquired by a drone [29,30]. To the best of my knowledge, ref.…”

Modified Siamese Network Based on Feature Enhancement and Dynamic Template for Low-Light Object Tracking in UAV Videos

“…Visual object tracking is a fundamental task in computer vision that finds extensive applications in the unmanned aerial vehicle (UAV) domain. Recent years have witnessed the emergence of new trackers that exhibit exceptional performance in UAV tracking [1][2][3], which is largely attributed to the fine manual annotation of large-scale datasets [4][5][6][7]. However, the evaluation standards and tracking algorithms currently employed are primarily designed for favorable lighting conditions.…”

“…(3) running: This video sequence shows two running people, with the tracking target being the person on the left. The third row of Figure22presents the visualization results, indicating that some algorithms drift and track the wrong target as the relative position of the two targets changes.…”