The paper titled “Applying Faster R-CNN in Extremely Low-Resolution Thermal Images for People Detection” by the authors Diego M. Jimenez-Bravo, Pierre Masala Mutombo, Bart Braem, Johann M. Marquez-Barja was accepted at the IEEE/ACM 24th International Symposium on Distributed Simulation and Real Time Applications (DS-RT20).
ABSTRACT
In today’s cities, it is increasingly normal to see different systems based on Artificial Intelligence (AI) that help citizens and government institutions in their daily lives. This is possible thanks to the Internet of Thing (IoT). In this paper, we present a solution using a low-resolution thermal sensor in combination of deep learning to detect people the images generated by those sensors. To verify whether the deep learning techniques are appropriate to this type of images of such low resolution, we have implemented a Faster Region-Convolutional Neural Network. The results obtained are hopeful and undoubtedly encourage to continue improving this research line. With a perception of 72,85% and given the complexity of the problem presented we consider the results obtained to be highly satisfactory and it encourages us to continue improving the work presented in this article.
Download and read the full paper here.
