Zusammenfassung
Das Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB befasst sich seit vielen Jahren mit der intelligenten Bild- und Videoauswertung im präventiv-polizeilichen und ermittlungstechnischen Bereich. Neuste Methoden der intelligenten Videoüberwachung werden dazu in realen Anwendungen getestet und weiterentwickelt. Bis 2023 wird beispielsweise gemeinsam mit dem Land Baden-Württemberg und dem Polizeipräsidium Mannheim eine intelligente Technik in einem Modellprojekt in Mannheim erprobt und weiterentwickelt, die zudem die Privatsphäre der Bevölkerung und den Datenschutz verbessert. Das Ziel ist es, ein Assistenzsystem zu entwickeln, das die Aufmerksamkeit der Videobeobachter im Führungs- und Lagezentrum auf polizeilich relevante Situationen lenkt, so dass die Beamten ausschließlich diese Szenen sehen und bewerten müssen. Zudem wird in diesem Beitrag das aktuelle Potenzial intelligenter Verfahren exemplarisch anhand des fraunhofereigenen Experimentalsystems ivisX aufgezeigt.
Die Autoren bedanken sich ganz herzlich bei Herrn Dr.-Ing. Markus Müller, Herrn Dr.-Ing. Jürgen Metzler und Herrn Andreas Specker für die inhaltliche Unterstützung beim Gesamtbeitrag.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Literatur
Andriluka M, Pishchulin L, Gehler P, Schiele B (2014) 2D human pose estimation: new benchmark and state of the art analysis. In: 2014 IEEE conference on computer vision and pattern recognition (CVPR). IEEE. https://doi.org/10.1109/CVPR.2014.471
Andriluka M, Iqbal U, Insafutdinov E, Pishchulin L, Milan A, Gall J, Schiele B (2018) PoseTrack: a benchmark for human pose estimation and tracking. In: 2018 IEEE international conference on computer vision and pattern recognition (CVPR). IEEE. https://doi.org/10.1109/CVPR.2018.00542
Cheng M, Cai K, Li M (2021) RWF-2000: an open large scale video database for violence detection. In: 2020 25th international conference on pattern recognition (ICPR). IEEE. https://doi.org/10.1109/ICPR48806.2021.9412502
Cormier M (2021) A data annotation process for human activity recognition in public places. In: Proceedings of the 2020 joint workshop of Fraunhofer IOSB and Institute for Anthropomatics, Vision and Fusion Laboratory, Bd 51. KIT Scientific Publishing, Karlsruhe. https://doi.org/10.5445/IR/1000135073
Cormier M, Moshkenan HM, Lörch F, Metzler J, Beyerer J (2021a) Do as we do: multiple person video-to-video transfer. arXiv:2104.04721. Tokyo
Cormier M, Seletkov D, Beyerer J (2021b) Towards lower precision quantization for pedestrian detection in crowded scenario. In: IEEE EUROCON 2021 – 19th international conference on smart technologies. Lviv. https://doi.org/10.1109/EUROCON52738.2021.9535539
Cormier M, Wolf S, Sommer L, Schumann A, Beyerer J (2021c) Fast pedestrian detection for real-world crowded scenarios on embedded GPU. In: IEEE EUROCON 2021 – 19th international conference on smart technologies. Lviv. https://doi.org/10.1109/EUROCON52738.2021.9535550
Cormier M, Röpke F, Golda T, Beyerer J (2021d) Interactive labeling for human pose estimation in surveillance video. In: IEEE/CVF international conference on computer vision workshops (interactive labeling and data augmentation for vision). Montreal. https://doi.org/10.1109/ICCVW54120.2021.00190
Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition, S 248–255. https://doi.org/10.1109/CVPR.2009.5206848
Du M, Yang F, Zou N, Hu X (2020) Fairness in deep learning: a computational perspective. arXiv:1908.08843
Eicher M, Scharpfenecker P, Ludwig D, Friedmann F, Netter F, Reuther M (2020) Process considerations: a reliable AI data labeling process (Whitepaper). https://wiki.eclipse.org/images/0/0e/WhitePaper_Process_considerations-A_reliable_AI_data_labeling_process.pdf. Zugegriffen am 11.07.2021
Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A (2010) The pascal visual object classes (VOC) challenge. Int J Comput Vis 88(2):303–338. https://doi.org/10.1007/s11263-009-0275-4
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB (2007) Network Enabled Surveillance and Tracking (NEST). https://www.iosb.fraunhofer.de/de/projekte-produkte/nest.html. Zugegriffen am 10.07.2021
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB (2017) Multisensoriell gestützte Erfassung von Straftätern in Menschenmengen bei komplexen Einsatzlagen (MUSKAT). https://www.iosb.fraunhofer.de/de/projekte-produkte/muskat.html. Zugegriffen am 10.07.2021
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB (2018) Integrated video investigation suite for forensic applications (ivisX). https://www.iosb.fraunhofer.de/de/projekte-produkte/ivisx.html. Zugegriffen am 10.07.2021
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB, Karlsruher Institut für Technologie (KIT), Universität Kassel, Hochschule Fresenius für Management, Wirtschaft und Medien GmbH, digivod GmbH, Sopra Steria SE, Videmo Intelligente Videoanalyse GmbH & Co. KG (2019) Kooperative Systemplattform für Videoupload, Bewertung, teilautomatisierte Analyse und Archivierung (PERFORMANCE). https://www.sifo.de/files/Projektumriss_PERFORMANCE.pdf. Zugegriffen am 10.07.2021
Golda T (2020) Part affinity field based activity recognition. In: Jürgen Beyerer, Tim Zander (Hrsg) Proceedings of the 2019 joint workshop of Fraunhofer IOSB and Institute for Anthropomatics, Vision and Fusion Laboratory. KIT Scientific Publishing. https://doi.org/10.5445/IR/1000126337
Golda T, Kalb T, Schumann A, Beyerer J (2019) Human pose estimation for real-world crowded scenarios. In: 2019 16th IEEE international conference on advanced video and signal based surveillance (AVSS). IEEE. https://doi.org/10.1109/AVSS.2019.8909823
Golda T, Blattmann A, Metzler J, Beyerer J (2020) Image domain adaption of simulated data for human pose estimation. In: Dijk J (Hrsg) Artificial intelligence and machine learning in defense applications II, 19, SPIE. https://doi.org/10.1117/12.2573888
He Y, Han J, Yu W, Hong X, Wei X, Gong Y (2020) City-scale multi-camera vehicle tracking by semantic attribute parsing and cross-camera tracklet matching. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops. Nashville, S 576–577. https://doi.org/10.1109/CVPRW53098.2021.00466
Hilsenbeck B, Münch D, Grosselfinger A, Hübner W, Arens M (2016) Action recognition in the longwave infrared and the visible spectrum using hough forests. In: Proceedings of the 2016 IEEE international symposium on multimedia (ISM). IEEE. https://doi.org/10.1109/ISM.2016.0072
Hsu HM, Huang TW, Wang G, Cai J, Lei Z, Hwang JN (2019) Multi-camera tracking of vehicles based on deep features re-ID and trajectory-based camera link models. In: CVPR workshops, S 416–424
IDEMIA Identity & Security Germany AG, Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB, Universität Kassel, Universität Konstanz, Philipps-Universität Marburg, Eberhard Karls Universität Tübingen, procilon IT-Logistics GmbH, AIT Austrian Institute of Technology, PKE Electronics AG, LIquA Linzer Institut für qualitative Analysen, Research Institute AG & Co KG, Bundesministerium für Inneres (2019) Flexibles, teilautomatisiertes Analysesystem zur Auswertung von Videomassendaten (FLORIDA). https://www.sifo.de/files/Projektumriss_FLORIDA.pdf. Zugegriffen am 10.07.2021
Köhl P, Specker A, Schumann A, Beyerer J (2020) The MTA dataset for multi-target multi-camera pedestrian tracking by weighted distance aggregation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops. Salt Lake City, S 1042–1043. https://doi.org/10.1109/CVPRW50498.2020.00529
Kothandaraman D, Chandra R, Manocha D (2021) BoMuDANet: unsupervised adaptation for visual scene understanding in unstructured driving environments. arXiv:2010.03523
Lin TY, Maire M, Belongie S, Bourdev L, Girshick R, Hays J, Perona P, Ramanan D, Zitnick CL, Dollár P (2014) Microsoft COCO: common objects in context. arXiv:1405.0312
Mehrabi N, Morstatter F, Saxena N, Lerman K, Galstyan A (2019) A survey on bias and fairness in machine learning. arXiv:1908.09635
Moritz L, Specker A, Schumann A (2021) A study of person re-identification design characteristics for aerial data. In: Pattern recognition and tracking XXXII, Bd 11735. International Society for Optics and Photonics, Bellingham, S 117350P
Qu C, Metzler J, Beyerer J (2018) ivisX: an integrated video investigation suite for forensic applications. In: IEEE winter conference on applications of computer vision workshops, WACVW 2018. https://doi.org/10.1109/WACVW.2018.00007
Ristani E, Tomasi C (2018) Features for multi-target multi-camera tracking and re-identification. In: Proceedings of the IEEE conference on computer vision and pattern recognition. Salt Lake City, S 6036–6046. https://doi.org/10.1109/CVPR.2018.00632
Ryoo MS, Aggarwal JK (2009) Spatio-temporal relationship match: video structure comparison for recognition of complex human activities. In: IEEE international conference on computer vision (ICCV). IEEE, Kyoto. https://doi.org/10.1109/ICCV.2009.5459361
Schumann A, Specker A, Beyerer J. (2018) Attribute-based person retrieval and search in video sequences. In: 2018 15th IEEE international conference on advanced video and signal based surveillance (AVSS). IEEE, Auckland, S 1–6. https://doi.org/10.1109/AVSS.2018.8639114
Sommer L, Specker A, Schumann A (2021) Deep learning based person search in aerial imagery. In: Automatic target recognition XXXI, Bd 11729. International Society for Optics and Photonics, Bellingham, S 117290O
Specker A (2020) A realistic predictor for pedestrian attribute recognition. In: Proceedings of the 2019 joint workshop of Fraunhofer IOSB and Institute for Anthropomatics, Vision and Fusion Laboratory, Bd 45. KIT Scientific Publishing, Triberg im Schwarzwald, S 95. https://doi.org/10.5445/IR/1000126699
Specker A (2021) A step towards explainable person re-identification rankings. In: Beyerer J, Zander T (Hrsg) Proceedings of the 2020 joint workshop of Fraunhofer IOSB and Institute for Anthropomatics, Vision and Fusion Laboratory. Karlsruhe, S 107. https://doi.org/10.5445/IR/1000135219
Specker A, Schumann A, Beyerer J (2019) An interactive framework for cross-modal attribute-based person retrieval. In: 2019 16th IEEE international conference on advanced video and signal based surveillance (AVSS). IEEE, Taipei, S 1–8. https://doi.org/10.1109/AVSS.2019.890983
Specker A, Schumann A, Beyerer J (2020a) A multitask model for person re-identification and attribute recognition using semantic regions. In: Artificial intelligence and machine learning in defense applications II, Bd 11543. International Society for Optics and Photonics, Bellingham, S 115430I
Specker A, Schumann A, Beyerer J (2020b) An evaluation of design choices for pedestrian attribute recognition in video. In: 2020 IEEE international conference on image processing (ICIP). IEEE, Abu Dhabi, S 2331–2335. https://doi.org/10.1109/ICIP40778.2020.9191264
Specker A, Stadler D, Florin L, Beyerer J (2021) An occlusion-aware multi-target multi-camera tracking system. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. Nashville, S 4173–4182. https://doi.org/10.1109/CVPRW53098.2021.00471
VICTORIA (2019) Video analysis for investigation of criminal and terrorist activities. https://www.victoria-project.eu. Zugegriffen am 10.07.2021
Wang X, Zhang X, Zhu Y, Guo Y, Yuan X, Xiang L, Wang Z, Ding G, Brady DJ, Dai Q, Fang L (2020) PANDA: a gigapixel-level human-centric video dataset. In: 2020 IEEE international conference on computer vision and pattern recognition (CVPR). IEEE. https://doi.org/10.1109/CVPR42600.2020.00333
Weinland D, Ronfard R, Boyer E (2006) Free viewpoint action recognition using motion history volumes. Comput Vis Image Underst 104(2–3):249–257. https://doi.org/10.1016/j.cviu.2006.07.013
Yang S, Quan Z, Nie M, Yang W (2021) TransPose: keypoint localization via transformer. In: IEEE/CVF international conference on computer vision (ICCV). Montreal
Zhao S, Li B, Reed C, Xu P, Keutzer K (2020) Multi-source domain adaptation in the deep learning era: a systematic survey. arXiv:2002.12169
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 Der/die Autor(en), exklusiv lizenziert an Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature
About this chapter
Cite this chapter
Golda, T., Cormier, M., Beyerer, J. (2023). Intelligente Bild- und Videoauswertung für die Sicherheit. In: Wehe, D., Siller, H. (eds) Handbuch Polizeimanagement. Springer Gabler, Wiesbaden. https://doi.org/10.1007/978-3-658-34388-0_87
Download citation
DOI: https://doi.org/10.1007/978-3-658-34388-0_87
Published:
Publisher Name: Springer Gabler, Wiesbaden
Print ISBN: 978-3-658-34387-3
Online ISBN: 978-3-658-34388-0
eBook Packages: Business and Economics (German Language)