DroTrack: High-speed Drone-based Object Tracking Under Uncertainty

Publication Year: 2020 Publication Type : JournalArticle


We present DroTrack, a high-speed visual singleobject tracking framework for drone-captured video sequences. Most of the existing object tracking methods are designed to tackle well-known challenges, such as occlusion and cluttered backgrounds. The complex motion of drones, i.e., multiple degrees of freedom in three-dimensional space, causes high uncertainty. The uncertainty problem leads to inaccurate location predictions and fuzziness in scale estimations. DroTrack solves such issues by discovering the dependency between object representation and motion geometry. We implement an effective object segmentation based on Fuzzy C Means (FCM). We incorporate the spatial information into the membership function to cluster the most discriminative segments. We then enhance the object segmentation by using a pre-trained Convolution Neural Network (CNN) model. DroTrack also leverages the geometrical angular motion to estimate a reliable object scale. We discuss the experimental results and performance evaluation using two datasets of 51,462 drone-captured frames. The combination of the FCM segmentation and the angular scaling increased DroTrack precision by up to 9% and decreased the centre location error by 162 pixels on average. DroTrack outperforms all the high-speed trackers and achieves comparable results in comparison to deep learning trackers. DroTrack offers high frame rates up to 1000 frame per second (fps) with the best location precision, more than a set of state-of-the-art real-time trackers.


@article{DBLP:journals/corr/abs-2005-00828, archiveprefix = {arXiv},
    author = {Ali Hamdi and Flora D. Salim and Du Yong Kim},
    bibsource = {dblp computer science bibliography, https://dblp.org},
    biburl = {https://dblp.org/rec/journals/corr/abs-2005-00828.bib},
    eprint = {2005.00828},
    journal = {CoRR},
    timestamp = {Mon, 03 Aug 2020 01:00:00 +0200},
    title = {DroTrack: High-speed Drone-based Object Tracking Under Uncertainty},
    url = {https://arxiv.org/abs/2005.00828},
    volume = {abs/2005.00828},
    year = {2020}


Related Publications

RUP: Large Room Utilisation Prediction with carbon dioxide sensor
Type : JournalArticle
Show More
A Scalable Room Occupancy Prediction with Transferable Time Series Decomposition of CO 2 Sensor Data
Type : JournalArticle
Show More
Topical Event Detection on Twitter
Type : ConferenceProceeding
Show More

© 2021 Flora Salim - CRUISE Research Group.