1. Главная
  2. Ресурсы
  3. Библиотечный поиск
Benchmarking DeepTrackers on AerialVideos Abu Md Niamul TaufiqueBreton MinnehanAndreas Savakis2020 год

Benchmarking Deep Trackers on Aerial Videos
review

Полный текстСтраница публикацииПубликация в OpenAlex
Аннотация: In recent years, deep learning-based visual object trackers have achieved state-of-the-art performance on several visual object tracking benchmarks. However, most tracking benchmarks are focused on ground level videos, whereas aerial tracking presents a new set of challenges. In this paper, we compare ten trackers based on deep learning techniques on four aerial datasets. We choose top performing trackers utilizing different approaches, specifically tracking by detection, discriminative correlation filters, Siamese networks and reinforcement learning. In our experiments, we use a subset of OTB2015 dataset with aerial style videos; the UAV123 dataset without synthetic sequences; the UAV20L dataset, which contains 20 long sequences; and DTB70 dataset as our benchmark datasets. We compare the advantages and disadvantages of different trackers in different tracking situations encountered in aerial data. Our findings indicate that the trackers perform significantly worse in aerial datasets compared to standard ground level videos. We attribute this effect to smaller target size, camera motion, significant camera rotation with respect to the target, out of view movement, and clutter in the form of occlusions or similar looking distractors near tracked object.
Год издания: 2020
Авторы: Abu Md Niamul Taufique, Breton Minnehan, Andreas Savakis
Издательство: Multidisciplinary Digital Publishing Institute
Источник: Sensors
Ключевые слова: Video Surveillance and Tracking Methods, UAV Applications and Optimization, Fire Detection and Safety Systems
Другие ссылки: Sensors (PDF)
Sensors (HTML)
arXiv (Cornell University) (PDF)
arXiv (Cornell University) (HTML)
DOAJ (DOAJ: Directory of Open Access Journals) (HTML)
Europe PMC (PubMed Central) (PDF)
Europe PMC (PubMed Central) (HTML)
PubMed Central (HTML)
arXiv (Cornell University) (PDF)
arXiv (Cornell University) (HTML)
PubMed (HTML)
DataCite API (HTML)