Abstract
Abstract. The active development of neural network technologies and optoelectronic systems has led to the introduction of computer vision technologies in various fields of science and technology. Deep learning made it possible to solve complex problems that a person had not been able to solve before. The use of multi-spectral optical systems has significantly expanded the field of application of video systems. Tasks such as image recognition, object re-identification, video surveillance require high accuracy, speed and reliability. These qualities are provided by algorithms based on deep convolutional neural networks. However, they require to have large databases of multi-spectral images of various objects to achieve state-of-the-art results. While large and various databases of color images of different objects are widely available in public domain, then similar databases of thermal images are either not available, or they represent a small number of types of objects. The quality of three-dimensional modeling for the thermal imaging spectral range remains at an insufficient level for solving a number of important tasks, which require high precision and reliability. The realistic synthesis of thermal images is especially important due to the complexity and high cost of obtaining real data. This paper is focused on the development of a method for synthesizing thermal imaging images based on generative adversarial neural networks. We developed an algorithm for a multi-spectral image-to-image translation. We have changed to the original GAN architecture and converted the loss function. We presented a new learning approach. For this, we prepared a special training dataset including about 2000 image tensors. The evaluation of the results obtained showed that the proposed method can be used to expand the available databases of thermal images.
Highlights
Nowadays, the use of computer vision is widespread
In (Limmer, Lensch, 2016) a methods was proposed for translation of a near-infrared image to a color image.In our previous work, the deep generativeadversarial neural network to automatically convert thermal images to semantically similar color images of the visible range was presented (Kniaz V.V., 2019)
In our previous works (Kniaz et al, 2016),(Kniaz et al, 2017) we presented the method for transformation of visible range images to infrared images
Summary
The use of computer vision is widespread. In different tasks (image recognition, video surveillance, military applications), intelligent systems replace and surpass the results of humans. Modern computer vision systems are equipped with sensors of various spectra (visible, infrared, radio range). This allows you to significantly expand the scope of their application. Methods based on deep convolutional neural networks occupy a leading position in solving problems of human re-identification, image recognition and object detection. Such algorithms are well trained on multi-spectral and fusion data. Modern deep learning algorithms show excellent results in solving various problems of image-to-image translation Their use (both with 3D modeling methods and independently) can significantly improve the quality of synthesized thermal images.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
