Segmentation and visualization of obstacles for the enhanced vision system using generative adversarial networks

V.V. Kniaz; S.Yu. Danilov; A.N. Bordodymov

doi:10.26583/sv.10.4.01

Various Generative Adversarial Networks Model for Synthetic Prohibitory Sign Image Generation

Applied Sciences ◽

10.3390/app11072913 ◽

2021 ◽

Vol 11 (7) ◽

pp. 2913

Author(s):

Christine Dewi ◽

Rung-Ching Chen ◽

Yan-Ting Liu ◽

Hui Yu

Keyword(s):

Mean Squared Error ◽

Vision System ◽

Similarity Index ◽

Training Data ◽

Generative Adversarial Networks ◽

Synthetic Image ◽

Real Image ◽

Traffic Sign ◽

Research Issues ◽

Adversarial Networks

A synthetic image is a critical issue for computer vision. Traffic sign images synthesized from standard models are commonly used to build computer recognition algorithms for acquiring more knowledge on various and low-cost research issues. Convolutional Neural Network (CNN) achieves excellent detection and recognition of traffic signs with sufficient annotated training data. The consistency of the entire vision system is dependent on neural networks. However, locating traffic sign datasets from most countries in the world is complicated. This work uses various generative adversarial networks (GAN) models to construct intricate images, such as Least Squares Generative Adversarial Networks (LSGAN), Deep Convolutional Generative Adversarial Networks (DCGAN), and Wasserstein Generative Adversarial Networks (WGAN). This paper also discusses, in particular, the quality of the images produced by various GANs with different parameters. For processing, we use a picture with a specific number and scale. The Structural Similarity Index (SSIM) and Mean Squared Error (MSE) will be used to measure image consistency. Between the generated image and the corresponding real image, the SSIM values will be compared. As a result, the images display a strong similarity to the real image when using more training images. LSGAN outperformed other GAN models in the experiment with maximum SSIM values achieved using 200 images as inputs, 2000 epochs, and size 32 × 32.

Download Full-text

Tooth Segmentation of 3D Scan Data Using Generative Adversarial Networks

Applied Sciences ◽

10.3390/app10020490 ◽

2020 ◽

Vol 10 (2) ◽

pp. 490 ◽

Cited By ~ 1

Author(s):

Taeksoo Kim ◽

Youngmok Cho ◽

Doojun Kim ◽

Minho Chang ◽

Yoon-Ji Kim

Keyword(s):

Vision System ◽

Three Dimensional ◽

Dimensional Accuracy ◽

Generative Adversarial Networks ◽

Generative Adversarial Network ◽

Adversarial Network ◽

Adversarial Networks ◽

Average Improvement ◽

Scan Data ◽

Tooth Segmentation

The use of intraoral scanners in the field of dentistry is increasing. In orthodontics, the process of tooth segmentation and rearrangement provides the orthodontist with insights into the possibilities and limitations of treatment. Although, full-arch scan data, acquired using intraoral scanners, have high dimensional accuracy, they have some limitations. Intraoral scanners use a stereo-vision system, which has difficulties scanning narrow interdental spaces. These areas, with a lack of accurate scan data, are called areas of occlusion. Owing to such occlusions, intraoral scanners often fail to acquire data, making the tooth segmentation process challenging. To solve the above problem, this study proposes a method of reconstructing occluded areas using a generative adversarial network (GAN). First, areas of occlusion are eliminated, and the scanned data are sectioned along the horizontal plane. Next, images are trained using the GAN. Finally, the reconstructed two-dimensional (2D) images are stacked to a three-dimensional (3D) image and merged with the data where the occlusion areas have been removed. Using this method, we obtained an average improvement of 0.004 mm in the tooth segmentation, as verified by the experimental results.

Download Full-text

Virtual View Generation Based on 3D-Dense-Attentive GAN Networks

Sensors ◽

10.3390/s19020344 ◽

2019 ◽

Vol 19 (2) ◽

pp. 344 ◽

Cited By ~ 2

Author(s):

Junwei Fu ◽

Jun Liang

Keyword(s):

Binocular Vision ◽

Vision System ◽

Depth Map ◽

Image Features ◽

Generative Adversarial Networks ◽

Adversarial Networks ◽

Virtual View ◽

Proposed Model ◽

Image Edge ◽

3D Cnn

A binocular vision system is a common perception component of an intelligent vehicle. Benefiting from the biomimetic structure, the system is simple and effective. Which are extremely snesitive on external factors, especially missing vision signals. In this paper, a virtual view-generation algorithm based on generative adversarial networks (GAN) is proposed to enhance the robustness of binocular vision systems. The proposed model consists of two parts: generative network and discriminator network. To improve the quality of a virtual view, a generative network structure based on 3D convolutional neural networks (3D-CNN) and attentive mechanisms is introduced to extract the time-series features from image sequences. To avoid gradient vanish during training, the dense block structure is utilized to improve the discriminator network. Meanwhile, three kinds of image features, including image edge, depth map and optical flow are extracted to constrain the supervised training of model. The final results on KITTI and Cityscapes datasets demonstrate that our algorithm outperforms conventional methods, and the missing vision signal can be replaced by a generated virtual view.

Download Full-text

GAN-Based Image Super-Resolution with a Novel Quality Loss

Mathematical Problems in Engineering ◽

10.1155/2020/5217429 ◽

2020 ◽

Vol 2020 ◽

pp. 1-12

Author(s):

Xining Zhu ◽

Lin Zhang ◽

Lijun Zhang ◽

Xiao Liu ◽

Ying Shen ◽

...

Keyword(s):

Image Quality Assessment ◽

Vision System ◽

Super Resolution ◽

Human Vision ◽

Generative Adversarial Networks ◽

Quality Loss ◽

Adversarial Networks ◽

Image Super Resolution ◽

Single Image Super Resolution ◽

First Time

Single image super-resolution (SISR) has been a very attractive research topic in recent years. Breakthroughs in SISR have been achieved due to deep learning and generative adversarial networks (GANs). However, the generated image still suffers from undesired artifacts. In this paper, we propose a new method named GMGAN for SISR tasks. In this method, to generate images more in line with human vision system (HVS), we design a quality loss by integrating an image quality assessment (IQA) metric named gradient magnitude similarity deviation (GMSD). To our knowledge, it is the first time to truly integrate an IQA metric into SISR. Moreover, to overcome the instability of the original GAN, we use a variant of GANs named improved training of Wasserstein GANs (WGAN-GP). Besides GMGAN, we highlight the importance of training datasets. Experiments show that GMGAN with quality loss and WGAN-GP can generate visually appealing results and set a new state of the art. In addition, large quantity of high-quality training images with rich textures can benefit the results.

Download Full-text