With the rapid development of optical network for data center techniques and artificial intelligent algorithms, it’s harder to train relevant professionals. Experimental course plays an important role for students to deepen understanding of complex theoretical knowledge. However, existing SDN-based experimental platforms face two challenges that increase the learning cost: (1) how to evaluate intelligent algorithms in optical network for data center rapidly and automatically, (2) how to provide a large-scale optical network for data center environment for students’ practice with acceptable cost. To overcome these two challenges, this paper proposed an innovative educational platform with two features: (1) Introducing an intelligent algorithm center in the control layer to store and manage students’ different customized intelligent algorithms. (2) Introducing the combination of physical domain and virtual domain in underlying devices layer to provide a large-scale network experimental environment for students. The main functions of the proposed platform have been realized. Many students have used this platform to evaluate their intelligent algorithms. The difficulty of evaluating intelligent algorithms is greatly reduced. Students can make it more clear how intelligent algorithm works on optical networks for data center.
With the technological development of stereoscopic display, an immersive 3D space with large size can be reconstructed more and more easily, and a 3D spatial interaction method with high-efficiency become more and more urgent. Gesture interaction, as the most natural and efficient way of human-computer interaction, can convey information very quickly and efficiently. However, the effective interaction distance of most existing gesture interaction methods is less than one meter, and can not meet the demand of the long distance 3D spatial interaction. In this paper, an efficient network named Gesture YOLO for long-distance gesture detection is proposed to achieve the small gesture object detection with improved accuracy. There are two modules in our Gesture YOLO, one is the Dual CSPDarknet53-tiny Backbone module for fusing person features and gesture features, and the other is the Progressive Multi-Scale Feature Fusion module for enhancing output features. The experimental results on our test set show that our Gesture YOLO can achieve higher gesture detection accuracy than the YOLOv4-tiny at distances ranging from 2m to 5m, and can mitigate the significant drop in gesture detection accuracy when the distance increases.
KEYWORDS: Video, 3D image processing, Video acceleration, 3D displays, 3D acquisition, Image processing, RGB color model, Solids, Networks, Image quality
Matting is a method to extract foreground objects of arbitrary shape from an image. In the field of 3D display, matting technology is of great significance. Through the study of this technology, we can extract high-quality target foreground, and then reduce unnecessary stereo matching calculation and improve the effect of 3D display. This paper primarily studies the human target in 3D light field, and proposes a real-time multi-view background matting algorithm based on deep learning. Three-dimensional video live broadcast puts forward high requirements for the real-time performance of the matting algorithm. We pre-compose a group of multi-view images taken at the same time into a multi-view combined image. The network directly carries on the background matting to the multi-view combined image and outputs a group of foreground images at one time. Because the background of the multi-view combined image is not holistic, a pre-photographed background picture without human is added to the input to assist the network for learning. In addition, we add a channel subtraction module to help the network better understand the role of the original image and background image in the matting task. The method in this paper is tested on our multi-view data set. For pictures with different background complexity, it can run about 65 frames per second and maintain a relatively stable accuracy. The method can efficiently generate multi-view matting results and meet the requirements of 3D video live broadcast.
Recent researches on object segmentation mostly concentrate on single-view images or objects in 3D settings. In this paper, a novel method for efficient multi-view foreground object segmentation is presented, using spatial consistency across adjacent views as constraints to generate identical masks. Even though the conventional segmentation results at different views are relatively accurate, there always are inconsistent regions where the boundaries of the mask are different over the same area across multiple views. The central idea of our method is to utilize the camera parameters to guide the refocusing procedure, during which each instance across different views is refocused using multi-view projections. The refocused images are then used as the input of instance segmentation network to predict the bounding box and object mask. The final step takes the network output as the prior information for the GMMs to achieve more accurate segmentation results. While many concrete implementations of the general idea are feasible, satisfactory results can be achieved with this simple and efficient approach. Experimental results demonstrate both qualitatively and quantitatively that the proposed method outputs excellent results with less background pixels, thus allowing us to improve the 3D display quality eventually. We hope this simple and effective method can be of help to future researches in relevant tasks.
The performance monitoring of fiber-optics communication is an important task in nowadays communication system. Link optical noise-to-signal ratio (OSNR) is one of the most important parameters that affect the performance of optical networks. The traditional internal measurement method may increase the network construction cost and operation complexity. To overcome these drawbacks, an ANN based link OSNR estimation method with external measurement is proposed in this paper. Route level OSNR values are measured at the edge nodes and are used for link level OSNR estimation with the trained ANN. Besides, a heuristic method for route set generation is proposed to generate the route set that introduce fewer extra network load. The experiment results demonstrate that the ANN based method can meet the practical requirement in both estimation accuracy and computation complexity. The proposed method can be an important part of optical network OSNR monitoring to ensure robust and intelligent network operation.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.