Eurasip Journal on Image and Video Processing最新文献

Robust vision-based hand pose estimation is highly sought but still remains a challenging task, due to its inherent difficulty partially caused by self-occlusion among hand fingers. In this paper, an innovative framework for real-time static hand gesture recognition is introduced, based on an optimized shape representation build from multiple shape cues. The framework incorporates a specific module for hand pose estimation based on depth map data, where the hand silhouette is first extracted from the extremely detailed and accurate depth map captured by a time-of-flight (ToF) depth sensor. A hybrid multi-modal descriptor that integrates multiple affine-invariant boundary-based and region-based features is created from the hand silhouette to obtain a reliable and representative description of individual gestures. Finally, an ensemble of one-vs.-all support vector machines (SVMs) is independently trained on each of these learned feature representations to perform gesture classification. When evaluated on a publicly available dataset incorporating a relatively large and diverse collection of egocentric hand gestures, the approach yields encouraging results that agree very favorably with those reported in the literature, while maintaining real-time operation.

In human anatomy, the central nervous system (CNS) acts as a significant processing hub. CNS is clinically divided into two major parts: the brain and the spinal cord. The spinal cord assists the overall communication network of the human anatomy through the brain. The mobility of body and the structure of the whole skeleton is also balanced with the help of the spinal bone, along with reflex control. According to the Global Burden of Disease 2010, worldwide, back pain issues are the leading cause of disability. The clinical specialists in the field estimate almost 80% of the population with experience of back issues. The segmentation of the vertebrae is considered a difficult procedure through imaging. The problem has been catered by different researchers using diverse hand-crafted features like Harris corner, template matching, active shape models, and Hough transform. Existing methods do not handle the illumination changes and shape-based variations. The low-contrast and unclear view of the vertebrae also makes it difficult to get good results. In recent times, convolutional nnural Network (CNN) has taken the research to the next level, producing high-accuracy results. Different architectures of CNN such as UNet, FCN, and ResNet have been used for segmentation and deformity analysis. The aim of this review article is to give a comprehensive overview of how different authors in different times have addressed these issues and proposed different mythologies for the localization and analysis of curvature deformity of the vertebrae in the spinal cord.

With the increasing application of computer vision technology in autonomous driving, robot, and other mobile devices, more and more attention has been paid to the implementation of target detection and tracking algorithms on embedded platforms. The real-time performance and robustness of algorithms are two hot research topics and challenges in this field. In order to solve the problems of poor real-time tracking performance of embedded systems using convolutional neural networks and low robustness of tracking algorithms for complex scenes, this paper proposes a fast and accurate real-time video detection and tracking algorithm suitable for embedded systems. The algorithm combines the object detection model of single-shot multibox detection in deep convolution networks and the kernel correlation filters tracking algorithm, what is more, it accelerates the single-shot multibox detection model using field-programmable gate arrays, which satisfies the real-time performance of the algorithm on the embedded platform. To solve the problem of model contamination after the kernel correlation filters algorithm fails to track in complex scenes, an improvement in the validity detection mechanism of tracking results is proposed that solves the problem of the traditional kernel correlation filters algorithm not being able to robustly track for a long time. In order to solve the problem that the missed rate of the single-shot multibox detection model is high under the conditions of motion blur or illumination variation, a strategy to reduce missed rate is proposed that effectively reduces the missed detection. The experimental results on the embedded platform show that the algorithm can achieve real-time tracking of the object in the video and can automatically reposition the object to continue tracking after the object tracking fails.