FMODetect: Robust Detection of Fast Moving Objects

0546470 - ÚTIA 2022 RIV US eng C - Conference Paper (international conference)
Rozumnyi, D. - Matas, J. - Šroubek, Filip - Pollefeys, M. - Oswald, M.R.
FMODetect: Robust Detection of Fast Moving Objects.
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway: IEEE, 2021, s. 3541-3549. ISBN 978-1-6654-2812-5. E-ISSN 2380-7504.
[International Conference on Computer Vision (ICCV) 2021. Piscataway (on-line) (US), 11.10.2021-17.10.2021]
R&D Projects: GA ČR GA21-03921S
Institutional support: RVO:67985556
Keywords : tracking * convolutional neural network * deconvolution
OECD category: Computer hardware and architecture
http://library.utia.cas.cz/separaty/2021/ZOI/sroubek-0546470.pdf

We propose the first learning-based approach for fast moving objects detection. Such objects are highly blurred and move over large distances within one video frame. Fast
moving objects are associated with a deblurring and matting problem, also called deblatting. We show that the separation of deblatting into consecutive matting and deblurring allows achieving real-time performance, i.e. an order of magnitude speed-up, and thus enabling new classes of application. The proposed method detects fast moving objects as a truncated distance function to the trajectory by learning from synthetic data. For the sharp appearance estimation and accurate trajectory estimation, we propose a matting and fitting network that estimates the blurred appearance without background, followed by an energy minimization based deblurring. The state-of-the-art methods are outperformed in terms of recall, precision, trajectory estimation, and sharp appearance reconstruction. Compared to other methods, such as deblatting, the inference is of several orders of magnitude faster and allows applications such as real-time fast moving object detection and retrieval in large video collections.

Permanent Link: http://hdl.handle.net/11104/0323758