| bibtype |
C -
Conference Paper (international conference)
|
| ARLID |
0546470 |
| utime |
20240111141056.2 |
| mtime |
20211012235959.9 |
| DOI |
10.1109/ICCV48922.2021.00352 |
| title
(primary) (eng) |
FMODetect: Robust Detection of Fast Moving Objects |
| specification |
| page_count |
9 s. |
| media_type |
E |
|
| serial |
| ARLID |
cav_un_epca*0546469 |
| ISBN |
978-1-6654-2812-5 |
| ISSN |
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) |
| title
|
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) |
| page_num |
3541-3549 |
| publisher |
| place |
Piscataway |
| name |
IEEE |
| year |
2021 |
|
|
| keyword |
tracking |
| keyword |
convolutional neural network |
| keyword |
deconvolution |
| author
(primary) |
| ARLID |
cav_un_auth*0352947 |
| name1 |
Rozumnyi |
| name2 |
D. |
| country |
CZ |
|
| author
|
| ARLID |
cav_un_auth*0075799 |
| name1 |
Matas |
| name2 |
J. |
| country |
CZ |
|
| author
|
| ARLID |
cav_un_auth*0101209 |
| name1 |
Šroubek |
| name2 |
Filip |
| institution |
UTIA-B |
| full_dept (cz) |
Zpracování obrazové informace |
| full_dept |
Department of Image Processing |
| department (cz) |
ZOI |
| department |
ZOI |
| full_dept |
Department of Image Processing |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| author
|
| ARLID |
cav_un_auth*0415064 |
| name1 |
Pollefeys |
| name2 |
M. |
| country |
CH |
|
| author
|
| ARLID |
cav_un_auth*0415065 |
| name1 |
Oswald |
| name2 |
M.R. |
| country |
CH |
|
| source |
|
| cas_special |
| project |
| project_id |
GA21-03921S |
| agency |
GA ČR |
| ARLID |
cav_un_auth*0412209 |
|
| abstract
(eng) |
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\nmoving 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.\n |
| action |
| ARLID |
cav_un_auth*0415066 |
| name |
International Conference on Computer Vision (ICCV) 2021 |
| dates |
20211011 |
| mrcbC20-s |
20211017 |
| place |
Piscataway (on-line) |
| country |
US |
|
| RIV |
JD |
| FORD0 |
20000 |
| FORD1 |
20200 |
| FORD2 |
20206 |
| reportyear |
2022 |
| num_of_auth |
5 |
| presentation_type |
PO |
| inst_support |
RVO:67985556 |
| permalink |
http://hdl.handle.net/11104/0323758 |
| cooperation |
| ARLID |
cav_un_auth*0376357 |
| name |
ČVUT Fakulta elektrotechnická |
| institution |
ČVUT FEL |
| country |
CZ |
|
| cooperation |
| ARLID |
cav_un_auth*0376740 |
| name |
ETH Zürich |
|
| confidential |
S |
| arlyear |
2021 |
| mrcbU14 |
SCOPUS |
| mrcbU24 |
PUBMED |
| mrcbU34 |
WOS |
| mrcbU56 |
pdf 5.5MB |
| mrcbU63 |
cav_un_epca*0546469 Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) IEEE 2021 Piscataway 3541 3549 978-1-6654-2812-5 2380-7504 |
|