In spite of excellent performance of deep learning-based computer vision algorithms, they are not suitable for real-time surveillance to detect abnormal behavior because of very high computational complexity. In this paper, we propose a real-time surveillance system for abnormal behavior analysis in a closed-circuit television (CCTV) environment by constructing an algorithm and system optimized for a CCTV environment. The proposed method combines pedestrian detection and tracking to extract pedestrian information in real-time, and detects abnormal behaviors such as intrusion, loitering, fall-down, and violence. To analyze an abnormal behavior, it first determines intrusion/loitering through the coordinates of an object and then determines fall-down/violence based on the behavior pattern of the object. The performance of the proposed method is evaluated using an intelligent CCTV data set distributed by Korea Internet and Security Agency (KISA).
To increase the accuracy of medical image analysis using supervised learning-based AI technology, a large amount of accurately labeled training data is required.
However, the supervised learning approach may not be applicable to real-world medical imaging due to the lack of labeled data, privacy of patients and the cost of expertise.
To handle these issues, we present a bidirectional meta-Kronecker factored optimizer (BM-KFO) framework for fast semantic segmentation of MRI images using only a few images.
To increase computational efficiency and a stable learning process, we adopted Kronecker-factored decomposition in the parameter optimization process with a model-agnostic meta-learning (MAML) framework.
The proposed framework is compatible with any model without network component modification, and learns the learning process and meta-initial points while training the unseen data.
We also used average Hausdorff distance loss (AHD-Loss) as our objective function with cross-entropy loss to focus on the morphology of lesions or organs in medical images.
Based on experiments, we demonstrate that BM-KFO with AHD-Loss can be used for general applications of medical image segmentation, and it outperforms the baseline method in a few-shot learning tasks.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.