We present a live video streaming system using a low cost 3D sensor camera like the Microsoft Kinect. The huge amount of raw point data that Kinect creates has to be stored and transmitted by efficient compact means. Noise and redundancy, however, make the process more difficult to achieve. To overcome these difficulties we propose a live streaming system that streams a 3D video to an Android Mobile phone and to Linux Desktop systems. For Android mobile phone client, the 3D video is filtered before streaming. Filtering stage contains 3 types of filters, Voxel Grid, Statistical Outlier Removal and Histogram-based conditional filters. The video is captured by the Kinect and a 3D point cloud is created. Voxel Grid filter is used since the generated 3D video will have millions of points; a downsampling procedure is applied to minimize the number of points. To reduce outliers and color information, statistical outlier removal and histogram-based conditional filters are used respectively. Conditional filter is customized by the scene histogram for each channel of RGB color to preserve the dominant color information for each scene. For Linux desktop client, the video is filtered by the histogram-based conditional filter and is compressed using an Octree structure that reduces spatial redundancies across the streamed video

A popular technique for retrieving images from huge and unlabeled image databases are content-based-image-retrieval (CBIR). However, the traditional information retrieval techniques do not satisfy users in terms of time consumption and accuracy. Additionally, the number of images accessible to users are growing due to web development and transmission networks. As the result, huge digital image creation occurs in many places. Therefore, quick access to these huge image databases and retrieving images like a query image from these huge image collections provides significant challenges and the need for an effective technique. Feature extraction and similarity measurement are important for the performance of a CBIR technique. This work proposes a simple but efficient deep-learning framework based on convolutional-neural networks (CNN) for the feature extraction phase in CBIR. The proposed CNN aims to reduce the semantic gap between low-level and high-level features. The similarity measurements are used to compute the distance between the query and database image features. When retrieving the first 10 pictures, an experiment on the Corel-1K dataset showed that the average precision was 0.88 with Euclidean distance, which was a big step up from the state-of-the-art approaches.

In this paper, an authenticate live 3D point cloud video streaming system is presented, using a low cost 3D sensor camera, the Microsoft Kinect. The proposed system is implemented on a client-server network infrastructure. The live 3D video is captured from the Kinect RGB-D sensor, then a 3D point cloud is generated and processed. Filtering and compression are used to handle the spatial and temporal redundancies. A color histogram based conditional filter is designed to reduce the color information for each frame based on the mean and standard deviation. In addition to the designed filter, a statistical outlier removal filter is used. A certificate-based authentication is used where the client will verify the identity of the server during the handshake process. The processed 3D point cloud video is live streamed over a TCP/IP protocol to the client. The system is evaluated in terms of: compression ratio, total bytes per points, peak signal to noise ratio (PSNR), and Structural Similarity (SSIM) index. The experimental results demonstrate that the proposed video streaming system have a best case with SSIM 0.859, PSNR of 26.6 dB and with average compression ratio of 8.42 while the best average compression ratio case is about 15.43 with PSNR 18.5128 dB of and SSIM 0.7936.

The performance and the quality of 3D video streaming over WLAN networks is influenced by different parameters such as network transmission and the encoding of the 3D video stream. In this paper, we analyze a proposed live 3D video streaming system that transmits a 3D live video through a wireless LAN network (WLAN). The live 3D video is captured from the Kinect RGB-D sensor, then a 3D point cloud is being generated and processed. Several filters are applied during preprocessing stage which handles the spatial redundancy, then before streaming an Octree compression is used to further reduces the temporal redundancy. In this paper a color based conditional filter is designed to reduce color information for each frame. The filter condition is defined using the mean and the standard deviation of the occurrences in the color histogram. The quality of the whole system which includes filtering, compression and streaming is evaluated using several measurements: compression ratio, total bytes per points, peak signal to noise ratio (PSNR) and Similarity Structure index (SSIM). The experimental results shows that the proposed system have a best PSNR of 14dB and SSIM 81% with compression ratio of 10.69% while the best compression ratio is about 12% with PSNR 12.05dB of and SSIM 78.64%.