Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Large Scale Vehicle Re-Identification by Knowledge Transfer from Simulated Data and Temporal Attention

 
: Eckstein, Viktor; Schumann, Arne; Specker, Andreas

:
Postprint urn:nbn:de:0011-n-5970200 (805 KByte PDF)
MD5 Fingerprint: 9a50a9d99005b09c0471aab0235aca80
Created on: 1.8.2020


Institute of Electrical and Electronics Engineers -IEEE-; IEEE Computer Society:
IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020. Proceedings : 14-19 June 2020, virtual
Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2020
ISBN: 978-1-7281-9360-1
ISBN: 978-1-7281-9361-8
pp.2626-2631
Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) <2020, Online>
English
Conference Paper, Electronic Publication
Fraunhofer IOSB ()

Abstract
Automated re-identification (re-id) of vehicles is the foundation of many traffic analysis applications across camera networks, e.g. vehicle tracking, counting, or traffic density and flow estimation. The re-id task is made difficult by variations in lighting, viewpoint, image quality and similar vehicle models and colors that can occur across the network. These influences can cause a high visual appearance variation for the same vehicle while different vehicles may appear near identical under similar conditions. However, with a growing number of available datasets and well crafted deep learning models, much progress has been made. In this work we summarize the results of our participation in the NVIDIA AI City Challenge 2020 for vehicle reid. We address the re-id task by relying on well-proven design choices from the closely related person re-id literature. In addition to this, we explicitly address viewpoint and occlusions variation. The former is addressed by incorporating vehicle viewpoint classification results into our matching distance. The required viewpoint classifier is trained predominantly on simulated data and we show that it can be applied to real-world imagery with minimal domain adaptation. We address occlusion by relying on temporal attention scores which emphasize video frames that contain minimal occlusion. Finally, we further boost re-id accuracy by applying video-based re-ranking and an ensemble of complementary models. Our models, code, and simulated data is available at https://github.com/corner100/2020-aicitychallenge-IOSB-VeRi.

: http://publica.fraunhofer.de/documents/N-597020.html