Effects of disparity distribution on visual comfort for multiple objects of stereoscopic images

With the development of stereoscopic technology, more attention is attracted on the stereoscopic three-dimensional(S3 D) content and service, and researches on images and videos have emerged in large numbers. This paper focuses mainly on visual comfort affected by characteristics of disparity for multiple objects. To find the relationship between disparity distribution and visual comfort perception, several subject evaluation experiments are done. The study contains two spatial distribution types of disparity: 1) only one of the foreground objects has zero disparity; 2) one of the foreground objects has positive disparity, while the other one has negative disparity. The experimental results and relative regression analysis provide appropriate relationship between disparity distribution and visual comfort for both conditions, which is significant to meet the applicant field in S3 D content acquisition, display adjustment and quality evaluation.

Software Defined Traffic Engineering for Improving Quality of Service

The Software Defined Networking(SDN) paradigm separates the control plane from the packet forwarding plane, and provides applications with a centralized view of the distributed network state. Thanks to the flexibility and efficiency of the traffic flow management, SDN based traffic engineering increases network utilization and improves Quality of Service(QoS). In this paper, an SDN based traffic scheduling algorithm called CATS is proposed to detect and control congestions in real time. In particular, a new concept of aggregated elephant flow is presented. And then a traffic scheduling optimization model is formulated with the goal of minimizing the variance of link utilization and improving QoS. We develop a chaos genetic algorithm to solve this NP-hard problem. At the end of this paper, we use Mininet, Floodlight and video traces to simulate the SDN enabled video networking. We simulate both the case of live video streaming in the wide area backbone network and the case of video file transferring among data centers. Simulation results show that the proposed algorithm CATS effectively eliminates network congestions in subsecond. In consequence, CATS improves the QoS with lower packet loss rate and balanced link utilization.

Boosting Unsupervised Monocular Depth Estimation with Auxiliary Semantic Information

Learning-based multi-task models have been widely used in various scene understanding tasks,and complement each other,i.e.,they allow us to consider prior semantic information to better infer depth.We boost the unsupervised monocular depth estimation using semantic segmentation as an auxiliary task.To address the lack of cross-domain datasets and catastrophic forgetting problems encountered in multi-task training,we utilize existing methodology to obtain redundant segmentation maps to build our cross-domain dataset,which not only provides a new way to conduct multi-task training,but also helps us to evaluate results compared with those of other algorithms.In addition,in order to comprehensively use the extracted features of the two tasks in the early perception stage,we use a strategy of sharing weights in the network to fuse cross-domain features,and introduce a novel multi-task loss function to further smooth the depth values.Extensive experiments on KITTI and Cityscapes datasets show that our method has achieved state-of-the-art performance in the depth estimation task,as well improved semantic segmentation.

Image label transfer: Short video labelling by using frame auto-encoder

Short videos on the Internet have a huge amount, but most of them are unlabeled. In this paper, a rough short video labelling method based on the image classification neural network is proposed. Convolutional auto-encoder is applied to train and learn unlabeled video frames, in order to obtain feature in the specific level. With these features, the video key-frames are extracted by the feature clustering method. These key-frames which represent the video content are put into an image classification network, so that the labels of every video clip can be got. In addition, the different architectures of convolutional auto-encoder are estimated, and a better performance architecture through the experiment result is selected. In the final experiment, the video frame features from the convolutional auto-encoder are compared with those from other extraction methods, where it illustrates remarkable results by the proposed method.

Lighting control with Myo armband based on customized classifier

This paper focuses on gesture recognition and interactive lighting control.The collection of gesture data adopts the Myo armband to obtain surface electromyography(sEMG).Considering that many factors affect sEMG,a customized classifier based on user calibration data is used for gesture recognition.In this paper,machine learning classifiers k-nearest neighbor(KNN),support vector machines(SVM),and naive Bayesian(NB)classifier,which can be used in small sample sets,are selected to classify four gesture actions.The performance of the three classifiers under different training parameters,different input features,including root mean square(RMS),mean absolute value(MAV),waveform length(WL),slope sign change(SSC)number,zero crossing(ZC)number,and variance(VAR)are tested,and different input channels are also tested.Experimental results show that:The NB classifier,which assumes that the prior probability of features is polynomial distribution,has the best performance,reaching more than 95%accuracy.Finally,an interactive stage lighting control system based on Myo armband gesture recognition is implemented.

Research on emotional space for movie and TV drama videos

Emotional space refers to a multi-dimensional emotional model that describes a group of subjective feelings or emotions. Since the existing discrete emotional space is mainly aimed at human’s primary emotions, it cannot describe the complex emotions evoked when watching movies. In order to solve this problem, an emotional fusion space for videos was constructed by selecting movies and TV dramas with rich emotional semantics as the research objects. Firstly, emotional words based on movie and TV drama videos are acquired and analyzed by using subjective evaluation and semantic analysis methods. Then, the emotional word vectors obtained from the above analysis are fused, reduced dimension by t-distributed stochastic neighbor embedding(t-SNE) algorithm, and clustered by bisecting K-means clustering algorithm to get a discrete emotional space for movie and TV drama videos. This emotional fusion space can obtain different categories by changing the value of the emotion classification number without re-labeling and calculation.