Virtual Reality Video Image Classification Based on Texture Features

Abstract

As one of the most widely used methods in deep learning technology, convolutional neural networks have powerful feature extraction capabilities and nonlinear data fitting capabilities. However, the convolutional neural network method still has disadvantages such as complex network model, too long training time and excessive consumption of computing resources, slow convergence speed, network overfitting, and classification accuracy that needs to be improved. Therefore, this article proposes a dense convolutional neural network classification algorithm based on texture features for images in virtual reality videos. First, the texture feature of the image is introduced as a priori information to reflect the spatial relationship between pixels and the unique characteristics of different types of ground features. Second, the grey level cooccurrence matrix (GLCM) is used to extract the grey level correlation features of the image in space. Then, Gauss Markov Random Field (GMRF) is used to establish the statistical correlation characteristics between neighbouring pixels, and the extracted GLCM-GMRF texture feature and image intensity vector are combined. Finally, based on DenseNet, an improved shallow layer dense convolutional neural network (L-DenseNet) is proposed, which can compress network parameters and improve the feature extraction ability of the network. The experimental results show that compared with the current classification method, this method can effectively suppress the influence of coherent speckle noise and obtain better classification results.

Collaborative Indoor Positioning by Localization Comparison at an Encounter Position

“…Specifically, we use a gradient boosting framework, LightGBM [38]. The effectiveness of the gradient-boosting machine (GBM) algorithm has been verified in a wide range of tasks, such as binary classification [39], multi-class classification [40,41], and fault detection [42]. Additionally, we considered the efficiency of the algorithm since a mobile device is used to run the model.…”

SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems

“…System Hardware Modeling Given a sampled network, its hardware performance is modeled through a hardware simulator. In this work, we use a hardware simulator customized for a realistic HMD system [40,61] with smart sen-Figure 6. Hardware model for the target system.…”

“…Virtual Reality (VR) and Augmented Reality (AR) are becoming increasingly prevailing as one of the nextgeneration computing platforms [3]. Head mounted devices (HMD) for AR/VR feature multiple cameras to support various computer vision (CV) / machine learning (ML) powered human-computer interaction functions, such as object classification [40,61], hand-tracking [19] and SLAM [38].…”

Virtual Reality Software and Data Processing Algorithms Packaged Online for Videos

“…However, the projected 360-degree video of virtual reality shows characteristics significantly different from traditional video sequences, which need to be optimized according to these characteristics [7]. By analyzing the texture characteristics of the polar and equatorial regions, we can judge whether to terminate the CU partition in advance from the texture complexity and texture direction, so as to reduce the number of unnecessary traversals [8]. e basic idea of the data processing algorithm is to search the region with the most dense sample in the feature space through repeated iteration, which is called the modal of the sample.…”