A Hausdorff distance (HD) is one of commonly used measures for object matching. This work analyzes the conventional HD measures and proposes two robust HD measures based on m-estimation and least trimmed square (LTS) which are more efficient than the conventional HD measures. By computer simulation, the matching performance of the conventional and proposed HD measures is compared with synthetic and real images.

High Efficiency Video Coding (HEVC) is the state-of-the-art video coding standard. It adopts a hierarchical quad-tree-based coding unit (CU) partitioning structure that is flexible in various texture and motion characteristics of a video signal. However, the exhaustive partitioning process for finding optimal CU partitions requires a dramatic increase in computational complexity of the HEVC encoder compared with previous video coding standards. In this paper, a fast CU partitioning algorithm is proposed for HEVC encoder, which early on terminates the CU partitioning process based on the Bayesian decision rule using joint online and offline learning. An online learning method is first presented based on the minimum error Bayesian decision rule using a training picture selection method with scene change detection. Next, a joint online and offline learning method is presented, which additionally trains the loss of decision making of the proposed method based on the minimum risk Bayesian decision rule. The proposed method is implemented on an HEVC test software 15.0. Experimental results show that the proposed method reduces the computational complexity of HEVC encoder to 53.6% on an average with a 0.71% acceptable Bjøntegaard delta bitrate loss in random access configuration. For other configurations, 48.4%, 48.5%, and 54.2% encoding time saving are obtained on an average for low delay, low delay-P, and all intra-configurations, respectively.

We propose a novel image segmentation technique using the robust, adaptive least kth order squares (ALKS) estimator which minimizes the kth order statistics of the squares of residuals. The optimal value of k is determined from the data, and the procedure detects the homogeneous surface patch representing the relative majority of the pixels. The ALKS shows a better tolerance to structured outliers than other recently proposed similar techniques. The performance of the new, fully autonomous, range image segmentation algorithm is compared to several other methods.

Presents an integrated system for navigation parameter estimation using sequential aerial images, where the navigation parameters represent the positional and velocity information of an aircraft for autonomous navigation. The proposed integrated system is composed of two parts: relative position estimation and absolute position estimation. Relative position estimation recursively computes the current position of an aircraft by accumulating relative displacement estimates extracted from two successive aerial images. Simple accumulation of parameter values reduces the reliability of the extracted parameter estimates as an aircraft goes on navigating, resulting in a large positional error. Therefore, absolute position estimation is required to compensate for the positional error generated by the relative position estimation. Absolute position estimation algorithms using image matching and digital elevation model (DEM) matching are presented. In the image matching, a robust-oriented Hausdorff measure (ROHM) is employed, whereas in the DEM matching, an algorithm using multiple image pairs is used. Experiments with four real aerial image sequences show the effectiveness of the proposed integrated position estimation algorithm.

Violence recognition is challenging since recognition must be performed on videos acquired by a lot of surveillance cameras at any time or place. It should make reliable detections in real time and inform surveillance personnel promptly when violent crimes take place. Therefore, we focus on efficient violence recognition for real-time and on-device operation, for easy expansion into a surveillance system with numerous cameras. In this paper, we propose a novel violence detection pipeline that can be combined with the conventional 2-dimensional Convolutional Neural Networks (2D CNNs). In particular, frame-grouping is proposed to give the 2D CNNs the ability to learn spatio-temporal representations in videos. It is a simple processing method to average the channels of input frames and group three consecutive channel-averaged frames as an input of the 2D CNNs. Furthermore, we present spatial and temporal attention modules that are lightweight but consistently improve the performance of violence recognition. The spatial attention module named Motion Saliency Map (MSM) can capture salient regions of feature maps derived from the motion boundaries using the difference between consecutive frames. The temporal attention module called Temporal Squeeze-and-Excitation (T-SE) block can inherently highlight the time periods that are correlated with a target event. Our proposed pipeline brings significant performance improvements compared to the 2D CNNs followed by the Long Short-Term Memory (LSTM) and much less computational complexity than existing 3D-CNN-based methods. In particular, MobileNetV3 and EfficientNet-B0 with our proposed modules achieved state-of-the-art performance on six different violence datasets. Our codes are available at https://github.com/ahstarwab/Violence_Detection.