Monocular Camera Based Real-Time Dense Mapping Using Generative Adversarial Network

2018 ◽  
Author(s):  
Xin Yang ◽  
Jinyu Chen ◽  
Zhiwei Wang ◽  
Qiaozhe Zhang ◽  
Wenyu Liu ◽  
...  
Keyword(s):  
Real Time ◽  
Generative Adversarial Network ◽  
Monocular Camera ◽  
Adversarial Network

scholarly journals floodGAN: Using Deep Adversarial Learning to Predict Pluvial Flooding in Real Time

Water ◽  
2021 ◽  
Vol 13 (16) ◽  
pp. 2255
Author(s):  
Julian Hofmann ◽  
Holger Schüttrumpf
Keyword(s):  
Real Time ◽  
Hydrodynamic Model ◽  
Early Warning Systems ◽  
Training Data ◽  
Generative Adversarial Network ◽  
Flood Prediction ◽  
Adversarial Network ◽  
Pluvial Flooding ◽  
Physically Based ◽  
Fully Connected

Using machine learning for pluvial flood prediction tasks has gained growing attention in the past years. In particular, data-driven models using artificial neuronal networks show promising results, shortening the computation times of physically based simulations. However, recent approaches have used mainly conventional fully connected neural networks which were (a) restricted to spatially uniform precipitation events and (b) limited to a small amount of input data. In this work, a deep convolutional generative adversarial network has been developed to predict pluvial flooding caused by nonlinear spatial heterogeny rainfall events. The model developed, floodGAN, is based on an image-to-image translation approach whereby the model learns to generate 2D inundation predictions conditioned by heterogenous rainfall distributions—through the minimax game of two adversarial networks. The training data for the floodGAN model was generated using a physically based hydrodynamic model. To evaluate the performance and accuracy of the floodGAN, model multiple tests were conducted using both synthetic events and a historic rainfall event. The results demonstrate that the proposed floodGAN model is up to 106 times faster than the hydrodynamic model and promising in terms of accuracy and generalizability. Therefore, it bridges the gap between detailed flood modelling and real-time applications such as end-to-end early warning systems.

scholarly journals Upsampling Real-Time, Low-Resolution CCTV Videos Using Generative Adversarial Networks

Electronics ◽  
2020 ◽  
Vol 9 (8) ◽  
pp. 1312
Author(s):  
Debapriya Hazra ◽  
Yung-Cheol Byun
Keyword(s):  
High Resolution ◽  
Real Time ◽  
Super Resolution ◽  
Poor Quality ◽  
Generative Adversarial Networks ◽  
Temporal Consistency ◽  
Low Resolution ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Benchmark Datasets

Video super-resolution has become an emerging topic in the field of machine learning. The generative adversarial network is a framework that is widely used to develop solutions for low-resolution videos. Video surveillance using closed-circuit television (CCTV) is significant in every field, all over the world. A common problem with CCTV videos is sudden video loss or poor quality. In this paper, we propose a generative adversarial network that implements spatio-temporal generators and discriminators to enhance real-time low-resolution CCTV videos to high-resolution. The proposed model considers both foreground and background motion of a CCTV video and effectively models the spatial and temporal consistency from low-resolution video frames to generate high-resolution videos. Quantitative and qualitative experiments on benchmark datasets, including Kinetics-700, UCF101, HMDB51 and IITH_Helmet2, showed that our model outperforms the existing GAN models for video super-resolution.

scholarly journals Suggestive GAN for supporting Dysgraphic drawing skills

2019 ◽  
Vol 8 (2) ◽  
pp. 132
Author(s):  
Smita Pallavi
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Network System ◽  
Image Generation ◽  
Generative Adversarial Network ◽  
Learning Skills ◽  
Human Tutor ◽  
Adversarial Network ◽  
Drawing Skills

<span lang="EN-US">The squat competence of dysgraphia affected students in drawing graphics on paper may deter the normal pace of learning skills of children. Convolutional neural network may tend to extract and stabilize the action-motion disorder by reconstructing features and inferences on natural drawings. The work in this context is to devise a scalable Generative Adversarial Network system that allows training and compilation of image generation using real time generated images and  Google QuickDraw dataset to use quick and accurate modalities to provide feedback to empower the guiding software as an apt substitute for human tutor. The training loss accuracy of both discriminator and generator networks is also compared for the SGAN optimizer.</span>

Sign in / Sign up

Export Citation Format

Share Document