Matching As Color Imaging: Thermal Feature Detection
Bhavesh Deshpande · RIT Scholar Works (Rochester Institute of Technology) · 2021
Feature detection and extraction is considered to be one of the most important aspects when it comes to any computer vision application, especially the autonomous driving field that is highly dependent on it. Thermal imaging is less explored in the field of autonomous driving mainly due to the high cost of the cameras and inferior techniques available for detection. Due to advances in technology the former is not a major limitation and there lies tremendous scope for improvement in the latter. Autonomous driving relies heavily on multiple and sometimes redundant sensors, for which thermal sensors are a preferred addition. Thermal sensors being completely dependent on the infrared radiation emitted are able to frame and recognize objects even in the complete absence of light. However, detecting features persistently through subsequent frames is a difficult task due to the lack of textures in thermal images. Motivated by this challenge, we propose a Triplet based Siamese Convolutional Neural Network for feature detection and extraction for any given thermal image. Our architecture is able to detect larger number of good feature points on thermal images than other best performed feature detection algorithms with superb matching performance based on our extracted descriptors. To demonstrate our aforementioned claim, we compare the performance of the proposed CNN scheme with traditional as well as state-of-the-art feature detection and extraction schemes. Future work involves extending the pipeline for motion tracking, SLAM, SFM and many other applications.