Restoring Raindrops Using Attentive Generative Adversarial Networks
| Autor: | Hee-Deok Yang |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
0209 industrial biotechnology
Technology Computer science QH301-705.5 QC1-999 02 engineering and technology 020901 industrial engineering & automation convolutional neural networks 0202 electrical engineering electronic engineering information engineering General Materials Science Biology (General) Instrumentation QD1-999 Fluid Flow and Transfer Processes business.industry Process Chemistry and Technology Physics General Engineering attentive generative adversarial network Engineering (General). Civil engineering (General) Computer Science Applications Chemistry 020201 artificial intelligence & image processing Artificial intelligence TA1-2040 business raindrops |
| Zdroj: | Applied Sciences, Vol 11, Iss 7034, p 7034 (2021) Applied Sciences Volume 11 Issue 15 |
| ISSN: | 2076-3417 |
| Popis: | Artificial intelligence technologies and vision systems are used in various devices, such as automotive navigation systems, object-tracking systems, and intelligent closed-circuit televisions. In particular, outdoor vision systems have been applied across numerous fields of analysis. Despite their widespread use, current systems work well under good weather conditions. They cannot account for inclement conditions, such as rain, fog, mist, and snow. Images captured under inclement conditions degrade the performance of vision systems. Vision systems need to detect, recognize, and remove noise because of rain, snow, and mist to boost the performance of the algorithms employed in image processing. Several studies have targeted the removal of noise resulting from inclement conditions. We focused on eliminating the effects of raindrops on images captured with outdoor vision systems in which the camera was exposed to rain. An attentive generative adversarial network (ATTGAN) was used to remove raindrops from the images. This network was composed of two parts: an attentive-recurrent network and a contextual autoencoder. The ATTGAN generated an attention map to detect rain droplets. A de-rained image was generated by increasing the number of attentive-recurrent network layers. We increased the number of visual attentive-recurrent network layers in order to prevent gradient sparsity so that the entire generation was more stable against the network without preventing the network from converging. The experimental results confirmed that the extended ATTGAN could effectively remove various types of raindrops from images. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|