Paper “Deep Learning Based SWIR Object Detection in Long-Range Surveillance Systems: An Automated Cross-Spectral Approach“, by Pavlović, M.S.; Milanović, P.D.; Stanković, M.S.; Perić, D.B.; Popadić, I.V.; Perić, M.V., has been published in Sensors!
By using a multi-spectral imaging setting, the paper proposes a new cross-spectral automatic data annotation methodology for SWIR channel training dataset creation, in which the visible-light channel provides a source for detecting object types and bounding boxes which are then transformed to the SWIR channel. With the proposed cross-spectral methodology, the goal of the paper is to improve object detection in SWIR images captured in challenging outdoor scenes. Experimental tests using a state-of-the-art deep neural network-based YOLOX model demonstrate that retraining with the created SWIR image dataset significantly improves average detection precision.