eprintid: 10143471 rev_number: 7 eprint_status: archive userid: 699 dir: disk0/10/14/34/71 datestamp: 2022-02-15 14:17:44 lastmod: 2022-02-15 14:17:44 status_changed: 2022-02-15 14:17:44 type: proceedings_section metadata_visibility: show sword_depositor: 699 creators_name: Sayed, M creators_name: Brostow, G title: Improved Handling of Motion Blur in Online Object Detection ispublished: pub divisions: C05 divisions: F48 divisions: B04 divisions: UCL keywords: Computer vision, Computational modeling, Machine vision, Object detection, Cameras, Pattern recognition, Automobiles note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: We wish to detect specific categories of objects, for on-line vision systems that will run in the real world. Object detection is already very challenging. It is even harder when the images are blurred, from the camera being in a car or a hand-held phone. Most existing efforts either focused on sharp images, with easy to label ground truth, or they have treated motion blur as one of many generic corruptions.Instead, we focus especially on the details of egomotion induced blur. We explore five classes of remedies, where each targets different potential causes for the performance gap between sharp and blurred images. For example, first deblurring an image changes its human interpretability, but at present, only partly improves object detection. The other four classes of remedies address multi-scale texture, out-of-distribution testing, label generation, and conditioning by blur-type. Surprisingly, we discover that custom label generation aimed at resolving spatial ambiguity, ahead of all others, markedly improves object detection. Also, in contrast to findings from classification, we see a noteworthy boost by conditioning our model on bespoke categories of motion blur.We validate and cross-breed the different remedies experimentally on blurred COCO images and real-world blur datasets, producing an easy and practical favorite model with superior detection rates. date: 2021-11-13 date_type: published publisher: IEEE official_url: https://doi.org/10.1109/CVPR46437.2021.00175 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1938776 doi: 10.1109/CVPR46437.2021.00175 isbn_13: 9781665445092 lyricists_name: Brostow, Gabriel lyricists_id: GBROS38 actors_name: Flynn, Bernadette actors_id: BFFLY94 actors_role: owner full_text_status: public pres_type: paper series: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) publication: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition volume: 2021 place_of_pub: Nashville, TN, USA pagerange: 1706-1716 event_title: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) event_dates: 20 Jun 2021 - 25 Jun 2021 issn: 2575-7075 book_title: Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) citation: Sayed, M; Brostow, G; (2021) Improved Handling of Motion Blur in Online Object Detection. In: Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). (pp. pp. 1706-1716). IEEE: Nashville, TN, USA. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10143471/1/2011.14448.pdf