In this work, we compare multiple end-to-end neural networks that classify and segment numerous anatomies in fetal torso ultrasound (US) images. The novelty of this paper is not restricted by the fact that it extends the scarce literature on the recently proposed nnUNet approach, we are also the first who apply this framework on 2D US data and compare it with various state-of-the-art 2D segmentation models. Our fetal torso dataset comprises two planes – the four chambers of the heart and the three vessel trachea view – with distinct, however, non-mutually exclusive sets of anatomies, which poses another level of complexity. Consequently, besides segmenting observable anatomies, classifying the absence of such anatomies is of crucial importance for researchers and practitioners as well. We find that the nnUNet outperforms numerous state-of-the-art models both in the classification as well as the segmentation task. In more detail, our findings indicate that the nnUNet achieves the highest scores among all evaluation metrics. Finally, we discuss the benefits of the nnUNet and address potential drawbacks of its design regarding 2D segmentation.
Real-time behaviour analysis is of paramount importance to ensure the safety of passengers in border-crossing areas. It allows to recognize the security threats on time. Moreover, it can accelerate the security check since the security personnel only consider severe checks for passengers with suspicious behaviour. In this work, we consider the following suspicious patterns: (a) mindless turn, (b) peculiar interest to the security units, and (c) avoiding the security units. We propose an algorithm to compute an abnormal behaviour score in real-time. This score can help the security personnel to assess passenger movement patterns. We show the performance of our scoring algorithm via different synthetic examples.
In this article, the problem of the lack of robustness and reliability of surveillance systems through disturbing security irrelevant events such as tree shaking, birds flying, etc. is tackled. A novel scene analysis approach based on hypergraph-based trajectories is introduced for reducing the rate of false positives. The conception of hypergraph-based trajectories relaxes the notion of point-based trajectories by allowing multiple incidences between subsequent points in time. This allows a principled approach for the extraction of robust features based on bounding boxes resulting from existing 3rd party detection methods. The experimental part is based on data collected from single-view camera systems over a two-year non-stop recording in the frame of the Austrian KIRAS project SKIN1 on protecting critical infrastructure. The results show substantial reduction of irrelevant false alarms, hence improving the overall system’s performance.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.