Due to a shortage of medical staff, psychiatric nurses often find themselves responsible for as many as 16 or more patients, making it challenging to provide personalized attention to individuals requiring both physical and mental care. For this reason, we propose a real-time abnormal behavior recognition algorithm in hospitals. Our system utilizes real-time video analysis to detect and track the locations of mental patients, enabling the identification of their abnormal behaviors. Specifically, we have defined distinct abnormal behaviors commonly observed in closed wards, such as Self-Harm, Falldown, and Hit. To improve recognition performance, we applied the continual learning method, allowing the system to adapt and enhance its capabilities. In addition, the architecture can create our abnormal behavior dataset. The average abnormal behavior recognition accuracy of the system exceeds 90%. By decreasing the likelihood of encountering dangerous incidents, our proposed method not only improves the wellbeing of patients but also fosters a safer working environment for medical staff.

Traffic simulation is an essential tool for analyzing and predicting real-world traffic scenarios. It leverages real-world data to provide insights into various situations, even when data collection is impractical or inefficient. A critical aspect of simulation realism lies in developing sophisticated agent behavior models. In this paper, we propose an event-based rerouting framework for the UNIQ-SALT traffic simulation platform, designed to improve the realism of agent behaviors. Unlike static plans where vehicles follow predefined routes, this framework enables agents to dynamically respond to changing traffic conditions, facilitating the reproduction of diverse scenarios. Also, the framework was calibrated using real-world data from Daejeon in South Korea, and tested under a flood control event scenario. The evaluation, conducted through R-Square analysis of traffic flow, demonstrated high similarity between simulated and real-world data, achieving an R-Square (R2) value near 0.9. These results indicate the framework's effectiveness in accurately replicating real-world traffic dynamics during specific events. This research underscores the value of event-based models in enhancing simulation realism and supporting data-driven decision-making.

Existing emotional talking 3D facial animation primarily focus on animating emotional faces using a specific emotion condition. However, in real-world situations, no one consistently speaks with just one emotion. Thus, previous emotion-based approaches have very limited applicability in real-world applications. To address this issue, we propose SDETalk, a novel learning framework that animates the emotional talking faces by leveraging the emotional source from a speech. Unlike previous studies, which use static one-hot emotion conditions, the proposed network regresses complex emotional states from speech. It enables the network to animate natural facial animation from an emotional speech without using a specific emotional condition. Furthermore, we design the proposed method to produce head motions because head motion is an important factor to enhance the naturalness of talking face animation. By doing this, our approach simultaneously achieves accurate lip motion, natural expressions, and rhythmical head motions from emotional speech. Through extensive experiments in both qualitative and quantitative manners, it is demonstrated that our method outperforms other state-of-the-art methods by animating realistic and expressive 3D faces.

The city traffic simulation is one of solutions to analyze and forecast the traffic state for urban road network. In order to simulate the real traffic situation well, the fine-tuning simulation inputs, including road network and traffic demands, closer to real measured data is important. In this paper, we propose the UNIQ-SALT, which is a cell-based traffic simulator, with the RTDG (Recurrent Traffic Demand Generation) model as an adjustment model for the simulation inputs. This RTDG model recurrently calibrates the simulation results with real traffic data in Daejeon and Sejong, South Korea until obtaining predefined target error rate between simulated and real values. Finally, we show the simulated result is under 10% error coverage, MAPE, on main spots of the simulation area and the correlation between the simulated data and the real data is reasonable as near 0.9 of the R2value.

Although various stereo matching methods are studied in many years, the accurate 3D reconstruction from multiview stereos in high-fidelity is still challenging due to the surface inconsistency caused by various factors such as specular illumination. In this paper, we propose an accurate PatchMatch based multiview stereo matching method with a quadric support window that efficiently captures the surface of a complex structured object. Our method takes three novel contributions. Firstly, delicate surface configurations are used for representing the complex structure of an object. By using a general 3D quadric function, the structured object surfaces can be estimated more accurately. In addition, an illumination robust framework is proposed, where the patch dissimilarities are precisely measured with disentangled representation. The matching cost is defined based on disentangled measurements of the object photometric and geometric properties, balancing the pixel intensities between images robust to illumination. Lastly, a multiview propagation method is proposed to confirm shape consistency among views. Through the disparity refinement to unify plane parameters of the views, the object surface is estimated from a global perspective. Consequently, the dense and smooth 3D shape of the object is reconstructed accurately. We evaluate our proposed method on the Middlebury stereo set and conduct comprehensive experiments on facial images. Both quantitative and qualitative results demonstrate that the proposed method shows significant improvements over state-of-the-art methods.

Blendshape is one of the most common facial representation used for 3D animation, 3D game and virtual reality. In this paper, four representative blendshape approaches are benchmarked: global, delta, mean-delta, and SVD-based blend-shapes. When fitting the blendshape models to sparse facial points, the obtained facial shape highly depends on fitting approach due to the lack of the fitted points. Therefore, it is important to set up appropriate criteria for comparing and verifying the performance of the approaches. In this paper, we use four kinds of metrics that are utilized to measure the performance of the approaches: fitting, landmark, and vertex errors and coefficient sparsity. Through the experimental results, it is verified that the benchmarks are very effective to measure the subjective quality of blendshape.

In this paper, we present a robust framework for facial pose estimation from binocular stereoscopic vision. Unlike prior work on the facial pose estimation that employs the whole landmarks even located in the wrong position, we propose a landmark selection method to remove the erroneous landmarks for better performance, especially in the large facial pose case. For this purpose, we train a convolutional neural network (CNN) in order to measure the confidence of each facial landmark detected by using a well-known landmark detection algorithm. Also, by fitting selected landmarks to 3D space, our framework becomes more robust even when a small number of landmarks are selected. Due to the absence of public dataset for the binocular stereo facial pose, we construct facial pose data sets using a motion sensor for performance validation. In our experiments, our method achieves the higher accuracy of the pose estimation than the previous method, especially for large facial pose cases.

Facial landmark is one of the most basic elements for obtaining facial information such as facial expression and emotion. However, detecting dense landmarks on an image is challenging due to various facial poses. In this paper, a deep architecture for dense facial landmark detection, called ConcatNet, is proposed. In our architecture, we propose a CNN-based dense landmark detector on part regions of a face, which extends a given set of sparse landmarks to more accurate and dense landmarks. By introducing interface layers for coordinate normalization and part region localization, we concatenate a network for sparse landmark detection to ConcatNet in a global-to-local manner and the whole network to operate in an end-to-end manner. The experimental results on LFW and 300W datasets show that ConcatNet not only expands the number of the sparse landmarks but also increases the accuracy of the landmark positions remarkably. Also, ConcatNet shows high accuracy in detecting the dense landmarks with a smaller dataset and without additional data on an image such as 3D position annotations when compared to 3D model-based detection method.

A grid technology is one of key issues for healthcare services provided in collaborative environments. In this paper, a SLA-adaptive workflow integrated grid resource management system for supporting collaborative heart disease simulator application in Physio-Grid service is proposed. At first, we propose the system architecture and framework that integrates workflow function into policy quorum based resource management (PQRM) system, one of existing grid resource management systems, for collaborative healthcare services. In addition, we derived the cost-adaptive policy adjustment scheme to adjust a gap between conditions and actions of workflow management and resource management policies for the proposed system. Based on this adjustment scheme, an appropriate policy can be selected according to QoS constraints of collaborated healthcare applications given by SLA negotiated with users. Finally, we evaluate proposed system using a collaborative heart disease simulation service and show the proposed system outperforms a general grid management system throughout performance comparisons under different types of SLA.