Transmission of 3D Holographic Information via Conventional Communication Channels and the Possibility of Multiplexing in the Implementation of 3D Hyperspectral Images

This paper shows the possibility of transmitting 3D holographic information in real time with a TV frame rate over conventional radio channels by transmitting two two-dimensional signals in two image modes: depth map and surface texture of the object (mask + texture). The authors point out that it is similar to compression through eliminating the carrier and it is inherently similar to SSB (single-sideband modulation) but has higher resolution ability in reconstructing 3D images. It is also shown that such technology for transmitting 3D holographic information is in good agreement with the tasks of both aggregating and multiplexing 3D images when they are transferred from one part of the electromagnetic spectrum of radiation to another and the creation of hyperspectral 3D images.

Implementation of Modified Mask RCNN

Detecting camouflage moving object from the video sequence is the big challenge in computer vision. To detect moving object from dynamic background is also very difficult as the background is also detected as moving object. Mask RCNN is a deep neural network which solves the problem of separation of instances of same object in machine learning or computer vision. Thus, it separates different objects in video. It is the extension of faster RCNN in which an extra branch is added to create an object mask simultaneously along with bounding box and classifier. After giving input, Mask RCNN gives the rectangle around the object, class to which object belong and object mask. This article introduces Mask RCNN algorithm along with some modifications for target detection from dynamic background and also for camouflage handling. After target object detection, contrast limited adaptive histogram equalization is applied. Morphological operations are used to improve results. For both challenges quantitative and qualitative measures were obtained and compared with the existing algorithms. Our method efficiently detects the moving object from input sequence and gives best results in both situations.

Symmetry Encoder-Decoder Network with Attention Mechanism for Fast Video Object Segmentation

Semi-supervised video object segmentation (VOS) has obtained significant progress in recent years. The general purpose of VOS methods is to segment objects in video sequences provided with a single annotation in the first frame. However, many of the recent successful methods heavily fine-tune the object mask in the first frame, which decreases their efficiency. In this work, to address this issue, we propose a symmetry encoder-decoder network with the attention mechanism for video object segmentation (SAVOS) requiring only one forward pass to segment the target object in a video. Specifically, the encoder generates a low-resolution mask with smoothed boundaries, while the decoder further refines the details of the segmentation mask and integrates lower level features progressively. Besides, to obtain accurate segmentation results, we sequentially apply the attention module on multi-scale feature maps for refinement. We conduct several experiments on three challenging datasets (i.e., DAVIS 2016, DAVIS 2017, and SegTrack v2) to show that SAVOS achieves competitive performance against the state-of-the-art.

An Efficient Saliency Detection Model Based on Wavelet Generalized Lifting

Saliency detection refers to the segmentation of all visually conspicuous objects from various backgrounds. The purpose is to produce an object-mask that overlaps the salient regions annotated by human vision. In this paper, we propose an efficient bottom-up saliency detection model based on wavelet generalized lifting. It requires no kernels with implicit assumptions and prior knowledge. Multiscale wavelet analysis is performed on broadly tuned color feature channels to include a wide range of spatial-frequency information. A nonlinear wavelet filter bank is designed to emphasize the wavelet coefficients, and then a saliency map is obtained through linear combination of the enhanced wavelet coefficients. This full-resolution saliency map uniformly highlights multiple salient objects of different sizes and shapes. An object-mask is constructed by the adaptive thresholding scheme on the saliency maps. Experimental results show that the proposed model outperforms the existing state-of-the-art competitors on two benchmark datasets.

A Motion Vehicle Detection Method Based on Self-Adaptive Background Subtraction with Cumulative Inter-Frame Difference

Against the poor accuracy of the vehicle counters extracted by existing vehicle detection technology, a motion vehicle detection method based on self-adaptive background subtraction with cumulative inter-frame difference is proposed in this paper. Cumulative inter-frame difference is used to subtract binary object mask. According to the binary object mask, in the area of moving objects the pixels of last background are used to modify the current background, otherwise the pixels of current image are used. The result of this operation is the current background. Then the background difference method is used to detect moving vehicles.