Roberts Treize. Depth-Aware RGB and IR Image Alignment Using ToF-Based Homography Interpolation. 2025 International Conference on Networking, Sensing and Control (ICNSC), IEEE, 2025.
Bibtex citation:
Bibtex citation:
@inproceedings{20635_2025,
author = {Roberts Treize},
title = {Depth-Aware RGB and IR Image Alignment Using ToF-Based Homography Interpolation},
journal = {2025 International Conference on Networking, Sensing and Control (ICNSC)},
publisher = {IEEE},
year = {2025}
}
author = {Roberts Treize},
title = {Depth-Aware RGB and IR Image Alignment Using ToF-Based Homography Interpolation},
journal = {2025 International Conference on Networking, Sensing and Control (ICNSC)},
publisher = {IEEE},
year = {2025}
}
Abstract: This paper presents a depth-aware method for pixelwise registration of RGB and infrared (IR) images using Time-of-Flight (ToF) sensing. Unlike fixed homography models that fail under varying scene depths, our approach dynamically adapts the transformation matrix based on per-pixel depth information. We perform a two-depth calibration using a 6×7 checkerboard target, obtaining homographies between the ToF and both RGB and IR image planes. These matrices are linearly interpolated to generate a continuous, depth-dependent transformation model. Each pixel's depth is retrieved from the ToF camera and used to evaluate a tailored homography, which maps coordinates between modalities. To handle missing or uncertain depth data, we apply percentile-based outlier removal and edge-aware interpolation. Final alignment is performed via bilinear resampling. The method is scalable to high-resolution input, and achieves precise multimodal overlay even under non-uniform depth conditions.