Visible to Thermal image Translation for improving visual task in low light conditions
This work addresses low-light visual tasks for security and surveillance, but it is incremental as it applies existing GAN methods to a new dataset.
The paper tackles the challenge of performing visual tasks like pedestrian detection in low light conditions by proposing an end-to-end framework that translates RGB images to thermal images using a GAN. The results show it is feasible to generate thermal data more quickly and affordably, benefiting security and surveillance applications.
Several visual tasks, such as pedestrian detection and image-to-image translation, are challenging to accomplish in low light using RGB images. Heat variation of objects in thermal images can be used to overcome this. In this work, an end-to-end framework, which consists of a generative network and a detector network, is proposed to translate RGB image into Thermal ones and compare generated thermal images with real data. We have collected images from two different locations using the Parrot Anafi Thermal drone. After that, we created a two-stream network, preprocessed, augmented, the image data, and trained the generator and discriminator models from scratch. The findings demonstrate that it is feasible to translate RGB training data to thermal data using GAN. As a result, thermal data can now be produced more quickly and affordably, which is useful for security and surveillance applications.