Research on the Application of Visual Sensing Technology in Art Education

It is essential to have a new understanding of the development of visual sensing technology in digital image art at this stage, in order to make traditional art education have new professional ability teaching. Based on the current research results in related fields, a three-dimensional (3D) image visual communication system based on digital image automatic reconstruction is proposed with two schemes as the premise. In scheme 1, the hardware part is divided into two modules. The hardware used by the analysis of the 3D image layer module is the HUJ-23 3D image processor. The acquisition of a 3D image layer module uses the hardware of a realistic infrared camera. The software of the system consists of two parts: a 3D image computer expression module and a 3D image reconstruction module. A simulation platform is established. The test data of 3D image reconstruction accuracy and visual communication integrity of the designed system show that both of them show a good trend. In scheme 2, regarding digital image processing, the 3D image visual perception reconstruction is affected by the modeling conditions, and some images are incomplete and damaged. The depth camera and image processor that can be used in the visual communication technology are selected, and their internal parameters are modified to borrow them in the original system hardware. Gaussian filtering model combined with scale-invariant feature transform (SIFT) feature point extraction algorithm is adopted to select image feature points. Previous system reconstruction technology is used to upgrade the 3D digital image, and the feature point detection equation is adopted to detect the accuracy of the upgraded results. Based on the above hardware and software research, the 3D digital image system based on visual communication is successfully upgraded. The test platform is established, and the test samples are selected. Unlike the previous systems, the 3D image reconstruction accuracy of the designed visual communication system can be as high as 98%; the upgraded system has better image integrity and stronger performance than the previous systems and achieves higher visual sensing technology. In art education, it can provide a new content perspective for digital image art teaching.

Separate in Latent Space: Unsupervised Single Image Layer Separation

Many real world vision tasks, such as reflection removal from a transparent surface and intrinsic image decomposition, can be modeled as single image layer separation. However, this problem is highly ill-posed, requiring accurately aligned and hard to collect triplet data to train the CNN models. To address this problem, this paper proposes an unsupervised method that requires no ground truth data triplet in training. At the core of the method are two assumptions about data distributions in the latent spaces of different layers, based on which a novel unsupervised layer separation pipeline can be derived. Then the method can be constructed based on the GANs framework with self-supervision and cycle consistency constraints, etc. Experimental results demonstrate its successfulness in outperforming existing unsupervised methods in both synthetic and real world tasks. The method also shows its ability to solve a more challenging multi-layer separation task.

OBJECT BOUNDARIES REGULARIZATION USING THE DYNAMIC POLYLINE COMPRESSION ALGORITHM

<p><strong>Abstract.</strong> This study presents a regularization approach to refine object boundaries for the purpose of buildings 3D modelling and reconstruction. Specifically, the derivative Normalized Digital Surface model (nDSM) image layer is firstly segmented using the classical multi-resolution segmentation followed by spectral difference segmentation. As the segmentation results can contain quite a number of boundary artefacts in the form geometrical distortions, the Dynamic Polyline Compression algorithm (DCPA) is applied as a regularization step in order to refine the outer boundaries, which removes the distortions. This results in higher quality image objects for the purpose of 3D models reconstruction. Experimental results after comparing between automatically extracted buildings and manually digitized aerial photographs indicate high completeness scores of 94%&amp;ndash;97% and correctness of 93%&amp;ndash;96%. Overall average error is minimized with very low Root Mean Square (RMS) and Overlay errors.</p>