An image recognition method for the deformation area of open-pit rock slopes under variable rainfall

A review of the thermal conductivity of silver-epoxy nanocomposites as encapsulation material for packaging applications

Automatic recognition of erosion area on the slope of tailings dam using region growing segmentation algorithm

Every data and kind of data need a physical drive to store it. There has been an explosion in the volume of images, video, and other similar data types circulated over the internet. Users using the internet expect intelligible data, even under the pressure of multiple resource constraints such as bandwidth bottleneck and noisy channels. Therefore, data compression is becoming a fundamental problem in wider engineering communities. There has been some related work on data compression using neural networks. Various machine learning approaches are currently applied in data compression techniques and tested to obtain better lossy and lossless compression results. A very efficient and variety of research is already available for image compression. However, this is not the case for video compression. Because of the explosion of big data and the excess use of cameras in various places globally, around 82% of the data generated involve videos. Proposed approaches have used Deep Neural Networks (DNNs), Recurrent Neural Networks (RNNs), and Generative Adversarial Networks (GANs), and various variants of Autoencoders (AEs) are used in their approaches. All newly proposed methods aim to increase performance (reducing bitrate up to 50% at the same data quality and complexity). This paper presents a bibliometric analysis and literature survey of all Deep Learning (DL) methods used in video compression in recent years. Scopus and Web of Science are well-known research databases. The results retrieved from them are used for this analytical study. Two types of analysis are performed on the extracted documents. They include quantitative and qualitative results. In quantitative analysis, records are analyzed based on their citations, keywords, source of publication, and country of publication. The qualitative analysis provides information on DL-based approaches for video compression, as well as the advantages, disadvantages, and challenges of using them.

/pdf/deep-learning-approaches-for-video-compression-a-3ehtrdw6.pdf

Deep Learning Approaches for Video Compression: A Bibliometric Analysis

Holographic-type communication (HTC) permits new levels of engagement between remote users. It is anticipated that it will give a very immersive experience while enhancing the sense of spatial co-presence. In addition to the newly revealed advantages, however, stringent system requirements are imposed, such as multi-sensory and multi-dimensional data capture and reproduction, ultra-lightweight processing, ultra-low-latency transmission, realistic avatar embodiment conveying gestures and facial expressions, support for an arbitrary number of participants, etc. In this paper, we review the current limitations to the HTC system implementation and systemize the main challenges into a few major groups. Furthermore, we propose a conceptual framework for the realization of an HTC system that will guarantee the desired low-latency transmission, lightweight processing, and ease of scalability, all accompanied with a higher level of realism in human body appearance and dynamics.

/pdf/challenges-in-implementing-low-latency-holographic-type-2i2uxbnk.pdf

Challenges in Implementing Low-Latency Holographic-Type Communication Systems

As a kind of information-intensive 3D representation, point cloud rapidly develops in immersive applications, which has also sparked new attention in point cloud compression. The most popular dynamic methods ignore the characteristics of point clouds and use an exhaustive neighborhood search, which seriously impacts the encoder’s runtime. Therefore, we propose an improved compression means for dynamic point cloud based on curvature estimation and hierarchical strategy to meet the demands in real-world scenarios. This method includes initial segmentation derived from the similarity between normals, curvature-based hierarchical refining process for iterating, and image generation and video compression technology based on de-redundancy without performance loss. The curvature-based hierarchical refining module divides the voxel point cloud into high-curvature points and low-curvature points and optimizes the initial clusters hierarchically. The experimental results show that our method achieved improved compression performance and faster runtime than traditional video-based dynamic point cloud compression.

/pdf/a-method-based-on-curvature-and-hierarchical-strategy-for-bddrb7uv.pdf

A Method Based on Curvature and Hierarchical Strategy for Dynamic Point Cloud Compression in Augmented and Virtual Reality System

Efficient and quick extraction of unknown objects in cluttered 3D scenes plays a significant role in robotics tasks such as object search, grasping, and manipulation. This paper describes a geometric-based unsupervised approach for the segmentation of cluttered scenes into objects. The proposed method first over-segments the raw point clouds into supervoxels to provide a more natural representation of 3D point clouds and reduce the computational cost with a minimal loss of geometric information. Then the fully connected local area linkage graph is used to distinguish between planar and nonplanar adjacent patches. Then the initial segmentation is completed utilizing the geometric features and local surface convexities. After the initial segmentation, many subgraphs are generated, each of which represents an individual object or part of it. Finally, we use the plane extracted from the scene to refine the initial segmentation result under the framework of global energy optimization. Experiments on the Object Cluttered Indoor Dataset dataset indicate that the proposed method can outperform the representative segmentation algorithms in terms of weighted overlap and accuracy, while our method has good robustness and real-time performance.

Efficient point cloud segmentation approach using energy optimization with geometric features for 3D scene understanding.

Contour detection and salient feature line regularization for printed circuit board in point clouds based on geometric primitives

The invention discloses a printed circuit board point cloud key contour feature extraction method, and aims to provide a method for extracting point cloud key contour feature points with low total time consumption and high extraction efficiency. The method is realized through the following scheme: defining boundary points by utilizing included angles of connecting lines of query points and neighbor points on a projection plane, preprocessing PCB point cloud data by adopting a straight-through filtering method, establishing a kd-tree topological structure and storing a point cloud index vectorof a clustering result; secondly, detecting the maximum plane area of the printed circuit board by using a random sampling consistency algorithm, calculating the Euclidean distance between each neighbor point and the seed point, comparing the normal vector included angle between the two points, converting the flanging point into a boundary point, and extracting a point cloud data feature boundary1; key features are separated in space, and a point cloud data feature boundary 2 is extracted; and merging the boundary points 1 and 2 of the two parts, and extracting point cloud key contour features to obtain a result of the PCB key contour.

Printed circuit board point cloud key contour feature extraction method

This paper introduces a robust normal estimation method for point cloud data that can handle both smooth and sharp features. Our method is based on the inclusion of neighborhood recognition into the normal mollification process in the neighborhood of the current point: First, the point cloud surfaces are assigned normals via a normal estimator of robust location (NERL), which guarantees the reliability of the smooth region normals, and then a robust feature point recognition method is proposed to identify points around sharp features accurately. Furthermore, Gaussian maps and clustering are adopted for feature points to seek a rough isotropic neighborhood for the first-stage normal mollification. In order to further deal with non-uniform sampling or various complex scenes efficiently, the second-stage normal mollification based on residual is proposed. The proposed method was experimentally validated on synthetic and real-world datasets and compared to state-of-the-art methods.

/pdf/robust-and-fast-normal-mollification-via-consistent-1mspcwm6.pdf

Si Sun

Papers

A Method Based on Curvature and Hierarchical Strategy for Dynamic Point Cloud Compression in Augmented and Virtual Reality System

Efficient point cloud segmentation approach using energy optimization with geometric features for 3D scene understanding.

Contour detection and salient feature line regularization for printed circuit board in point clouds based on geometric primitives

Printed circuit board point cloud key contour feature extraction method

Robust and Fast Normal Mollification via Consistent Neighborhood Reconstruction for Unorganized Point Clouds