Abstract
The original multispectral (MS) images obtained from multi-lens multispectral cameras (MSCs) have significant misregistration errors, which require image registration for precise spectral measurement. However, due to the nonlinearity intensity differences among MS images, performing image matching is difficult to find sufficient correct matches (CMs) for image registration, and results in a complex coarse-to-fine solution. Based on the modification of speed-up robust feature (SURF), we proposed a normalized SURF (N-SURF) that can significantly increase the amount of CMs among different pairs of MS images and make one-step image registration possible. In this study, we first introduce N-SURF and adopt different MS datasets acquired from three representative MSCs (MCA-12, Altum, and Sequoia) to evaluate its matching ability. Meanwhile, we utilized three image transformation models—affine transform (AT), projective transform (PT), and an extended projective transform (EPT) to correct the misregistration errors of MSCs and evaluate their co-registration correctness. The results show that N-SURF can obtain 6–20 times more CMs than SURF and can successfully match all pairs of MS images, while SURF failed in the cases of significant spectral differences. Moreover, visual comparison, accuracy assessment, and residual analysis show that EPT can more accurately correct the viewpoint and lens distortion differences of MSCs than AT and PT, and it can obtain co-registration accuracy of 0.2–0.4 pixels. Subsequently, using the successful N-SURF matching and EPT model, we developed an automatic MS image registration tool that is suitable for various multilens MSCs.
Highlights
M ULTISPECTRAL (MS) images can be acquired using a multilens multispectral camera (MSC) that records visible [red (RED), green (GRE), and blue (BLU)] and invisible [red edge (REG) and near-infrared (NIR)] spectral information
The differences between different pairs can be clearly observed. It shows that speed-up robust feature (SURF)-10 leads to different amounts of features on different MS images, in which only a few features are detected on the BLU image and is not possible to conduct image registration
In this article, based on the modification of SURF feature extraction, we present novel normalized SURF (N-SURF) matching for MSCs image registration
Summary
M ULTISPECTRAL (MS) images can be acquired using a multilens multispectral camera (MSC) that records visible [red (RED), green (GRE), and blue (BLU)] and invisible [red edge (REG) and near-infrared (NIR)] spectral information. The light weight and small size of MSCs make them suitable for mounting on various unmanned aerial vehicle (UAV) platforms to obtain high-spatial-resolution images, and the diversity of the MS band combinations can derive various vegetation indexes [1]. Since MSCs adopt a multi-lens structure to record distinct spectral information, the viewpoint and lens distortion differences among each lens lead to significant ghost effects in original images. To recover one-sensor geometry for precise spectral analysis, performing automatic MS image registration is an important task to reduce the band misregistration errors of MSCs [4]–[6]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
