The 17 thIEEE Int'l Conf on Advanced Video and Signal-based Surveillance
22-25 September | Washington DC, USA
Challenge I: DAODiS: Domain-Adapted Object Detection in Surveillance Videos
Abstract: Automatic analysis of image sequences is a key component of modern visual surveillance. Although very successful object detection methods have been recently developed using deep learning methodologies, their performance dramatically suffers if applied to surveillance videos due to domain shift. Clearly, domain shift is a critical and still open issue. This challenge attempts to advance research on domain adaptation in the context of surveillance videos. Its specific goal is the adaptation of object detection algorithms trained on still-image datasets (e.g., COCO) to surveillance videos by leveraging background subtraction. Algorithms will be judged on three performance metrics and on manual effort expended to annotate additional video frames. We believe this challenge can contribute to the AVSS community by charting a new research direction for visual surveillance. Furthermore, it can contribute to various application fields such as equipment monitoring and e-commerce (new product recognition).
Organizers: Atsushi Shimada (Kyushu Univ., email@example.com)
Janusz Konrad (Boston Univ., firstname.lastname@example.org)
Vincent Charvillat (ENSEEIHT, email@example.com)
Tsubasa Minematsu (Kyushu Univ., firstname.lastname@example.org)
Takashi Shibata (NEC Corp., email@example.com)
Yasutomo Kawanishi (Nagoya Univ., firstname.lastname@example.org)
Abstract: Small drones are a rising threat due to their possible misuse for illegal activities such as smuggling of drugs as well as for terrorism attacks using explosives or chemical weapons. The “International Workshop on Small-Drone Surveillance, Detection and Counteraction Techniques” (WOSDETC) is aimed at bringing together researchers from both academia and industry, to share recent advances in this field. In conjunction, the Drone-vs-Bird Detection Challenge is proposed. Indeed, given their characteristics, drones can be easily confused with birds, which makes the surveillance tasks even more challenging especially in maritime areas where bird populations may be massive. The challenge aims at attracting research efforts to identify novel solutions to the problem outlined above, i.e., discrimination between birds and drones at far distance, by providing a video dataset that may be difficult to obtain. The challenge goal is to detect a drone appearing at some time in a short video sequence where birds are also present: the algorithm should raise an alarm and provide a position estimate only when a drone is present, while not issuing alarms on birds. The dataset is continually increased over consecutive installments of the challenge and made available to the community afterwards.
Organizers: Angelo Coluccia (University of Salento, Lecce, Italy)
Alessio Fascista (University of Salento, Lecce, Italy)
Arne Schumann (Fraunhofer Institute, Karlsruhe, Germany)
Lars Sommer (Fraunhofer Institute, Karlsruhe, Germany)