scholarly journals Improving Video Segmentation by Fusing Depth Cues and the ViBe Algorithm

2017 ◽  
Author(s):  
Xiaoqin Zhou ◽  
Xiaofeng Liu ◽  
Aimin Jiang ◽  
Bin Yan ◽  
Chenguang Yang
Keyword(s):  
Video Segmentation ◽  
Human Motion ◽  
Color Information ◽  
Depth Sensing ◽  
Depth Cameras ◽  
Depth Cues ◽  
3D Space ◽  
Sensing Technology ◽  
Effectiveness And Efficiency ◽  
Vibe Algorithm

Depth-sensing technology has led to broad applications of inexpensive depth cameras that can capture human motion and scenes in 3D space. Background subtraction algorithms can be improved by fusing color and depth cues, thereby allowing many issues encountered in classical color segmentation to be solved. In this paper, we propose a new fusion method that combines depth and color information for foreground segmentation based on an advanced color-based algorithm. First, a background model and a depth model are developed. Then, based on these models, we propose a new updating strategy that can eliminate ghosting and black shadows almost completely. Extensive experiments have been performed to compare the proposed algorithm with other, conventional RGB-D algorithms. The experimental results suggest that our method extracts foregrounds with higher effectiveness and efficiency.

scholarly journals Improving Video Segmentation by Fusing Depth Cues and the Visual Background Extractor (ViBe) Algorithm

Sensors ◽  
2017 ◽  
Vol 17 (5) ◽  
pp. 1177 ◽  
Author(s):  
Xiaoqin Zhou ◽  
Xiaofeng Liu ◽  
Aimin Jiang ◽  
Bin Yan ◽  
Chenguang Yang
Keyword(s):  
Video Segmentation ◽  
Depth Cues ◽  
Visual Background ◽  
Vibe Algorithm

Using infrared depth-sensing technology to improve the brachytherapy operating room experience

Brachytherapy ◽  
2020 ◽  
Vol 19 (3) ◽  
pp. 323-327
Author(s):  
Kevin Martell ◽  
Calvin Law ◽  
Yaser Hasan ◽  
Amandeep Taggar ◽  
Elizabeth Barnes ◽  
...  
Keyword(s):  
Operating Room ◽  
Depth Sensing ◽  
Sensing Technology

Research on Action Recognition of Human Body Based on Kinect Sensor

2014 ◽  
Vol 644-650 ◽  
pp. 4162-4166
Author(s):  
Dan Dan Guo ◽  
Xi’an Zhu
Keyword(s):  
Action Recognition ◽  
Recognition Rate ◽  
Human Action Recognition ◽  
Human Action ◽  
Human Motion ◽  
Skeletal Structure ◽  
Depth Sensor ◽  
Depth Sensors ◽  
3D Space ◽  
3D Information

An effective Human action recognition method based on the human skeletal information which is extracted by Kinect depth sensor is proposed in this paper. Skeleton’s 3D space coordinates and the angles between nodes of human related actions are collected as action characteristics through the research of human skeletal structure, node data and research on human actions. First, 3D information of human skeletons is acquired by Kinect depth sensors and the cosine of relevant nodes is calculated. Then human skeletal information within the time prior to current state is stored in real time. Finally, the relevant locations of the skeleton nodes and the variation of the cosine of skeletal joints within a certain time are analyzed to recognize the human motion. This algorithm has higher adaptability and practicability because of the complicated sample trainings and recognizing processes of traditional method is not taken up. The results of the experiment indicate that this method is with high recognition rate.

A HSV Space Shadow Method Based Human Motion Detection

2013 ◽  
Vol 706-708 ◽  
pp. 597-600
Author(s):  
Hui Dang
Keyword(s):  
Color Space ◽  
Human Action ◽  
Human Motion ◽  
Shadow Detection ◽  
Fundamental Issue ◽  
Color Information ◽  
Shadow Method ◽  
Hsv Color Space ◽  
Human Motion Detection ◽  
Action Analysis

Human Action Analysis is a fundamental issue that can be applied to different application domains. In this paper, we present a HSV color space based shadow method. The process of the algorithm mainly includes three steps: motional object detection, shadow detection of the object and post-processing. In order to enhance the accuracy of shadow detection, the value of and in the method can be select elaborately. The experiment result indicates the presented algorithm can detect shadow effectively and make full use of the color information.

scholarly journals A Survey of Applications and Human Motion Recognition with Microsoft Kinect

2015 ◽  
Vol 29 (05) ◽  
pp. 1555008 ◽  
Author(s):  
Roanna Lun ◽  
Wenbing Zhao
Keyword(s):  
Research And Development ◽  
Performing Arts ◽  
Human Motion ◽  
Microsoft Kinect ◽  
Kinect Sensor ◽  
Language Recognition ◽  
Depth Sensing ◽  
Sign Language Recognition ◽  
Motion Recognition ◽  
Human Motion Recognition

Microsoft Kinect, a low-cost motion sensing device, enables users to interact with computers or game consoles naturally through gestures and spoken commands without any other peripheral equipment. As such, it has commanded intense interests in research and development on the Kinect technology. In this paper, we present, a comprehensive survey on Kinect applications, and the latest research and development on motion recognition using data captured by the Kinect sensor. On the applications front, we review the applications of the Kinect technology in a variety of areas, including healthcare, education and performing arts, robotics, sign language recognition, retail services, workplace safety training, as well as 3D reconstructions. On the technology front, we provide an overview of the main features of both versions of the Kinect sensor together with the depth sensing technologies used, and review literatures on human motion recognition techniques used in Kinect applications. We provide a classification of motion recognition techniques to highlight the different approaches used in human motion recognition. Furthermore, we compile a list of publicly available Kinect datasets. These datasets are valuable resources for researchers to investigate better methods for human motion recognition and lower-level computer vision tasks such as segmentation, object detection and human pose estimation.

scholarly journals Exploring RGBDepth Fusion for Real-Time Object Detection

Sensors ◽  
2019 ◽  
Vol 19 (4) ◽  
pp. 866 ◽  
Author(s):  
Tanguy Ophoff ◽  
Kristof Van Beeck ◽  
Toon Goedemé
Keyword(s):  
Object Detection ◽  
Real Time ◽  
Network Architecture ◽  
Depth Information ◽  
Special Focus ◽  
Single Shot ◽  
Depth Sensing ◽  
Real Time Processing ◽  
Depth Cameras ◽  
Optimal Fusion

In this paper, we investigate whether fusing depth information on top of normal RGB data for camera-based object detection can help to increase the performance of current state-of-the-art single-shot detection networks. Indeed, depth sensing is easily acquired using depth cameras such as a Kinect or stereo setups. We investigate the optimal manner to perform this sensor fusion with a special focus on lightweight single-pass convolutional neural network (CNN) architectures, enabling real-time processing on limited hardware. For this, we implement a network architecture allowing us to parameterize at which network layer both information sources are fused together. We performed exhaustive experiments to determine the optimal fusion point in the network, from which we can conclude that fusing towards the mid to late layers provides the best results. Our best fusion models significantly outperform the baseline RGB network in both accuracy and localization of the detections.

Sign in / Sign up

Export Citation Format

Share Document