A robust vehicle tracking in low-altitude UAV videos

• Published in: Machine vision and applications Vol. 34; no. 5; p. 77
• Main Authors: Maraş, Bahri, Arica, Nafiz, Ertüzün, Ayşın
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.09.2023; Springer Nature B.V
• Subjects: Altitude; Artificial neural networks; Aspect ratio; Benchmarks; Boxes; Cameras; Communications Engineering; Computer Science; Datasets; Image Processing and Computer Vision; Low altitude; Networks; Neural networks; Original Paper; Pattern Recognition; Probability; Remote sensing; Rescaling; Robustness; Rotation; Scale (ratio); Telematics; Tracking; Vehicles; Video; Vision systems; Visual aspects; Visual object tracking; Unmanned air vehicle; Arial videos; Convolutional neural network; Particle filter

In this study, we concentrate on solving variations in scale, aspect ratio, rotation, visual model and target motion problems for vehicle tracking in low-altitude UAV videos. The contributions of this work are threefold: 1. By introducing a particle rescaling mechanism where each particle is resized...