This letter proposes a multiresolution technique to address the high computational cost in remote sensing image registration. The scale-invariant feature transform is applied to detect keypoints and descriptors, and then, global information combined with descriptors is utilized to establish keypoint mappings. Keypoints are first classified according to their octaves. Then, in the lowest resolution, the keypoints of the largest octave are mapped with descriptors and the global information, giving an initial affine transformation $T_0$ . In the next octave, the keypoints of the second largest octave are mapped by employing $T_0$ to narrow the space of matching keypoints. By this means, the process of establishing keypoint correspondences is conducted from one resolution (octave) to the next as the obtained transformation gets finer until we get to the highest resolution. Due to the high computational expense of computing global information, the proposed technique is important for aligning large-size remote sensing imagery. Experimental results show that the proposed method can achieve a comparable registration accuracy but with a less computational cost than directly building keypoint mappings on images of large size.

The authors wish to update the Acknowledgments in their paper published in Sensors [1],

Inspired by the boosting technique for detecting objects, this paper proposes a cascade structure with a resurrection mechanism to establish keypoint mappings on multispectral images. The cascade structure is composed of four steps by utilizing best bin first (BBF), color and intensity distribution of segment (CIDS), global information and the RANSAC process to remove outlier keypoint matchings. Initial keypoint mappings are built with the descriptors associated with keypoints; then, at each step, only a small number of keypoint mappings of a high confidence are classified to be incorrect. The unclassified keypoint mappings will be passed on to subsequent steps for determining whether they are correct. Due to the drawback of a classification rule, some correct keypoint mappings may be misclassified as incorrect at a step. Observing this, we design a resurrection mechanism, so that they will be reconsidered and evaluated by the rules utilized in subsequent steps. Experimental results show that the proposed cascade structure combined with the resurrection mechanism can effectively build more reliable keypoint mappings on multispectral images than existing methods.

In this paper, for infrared images, the image enhancement technique based on wavelet transform is studied, which is a process that automatically apply different filtering coefficient toward different directions. The algorithm, including the application of nonlinear anisotropic diffusion, is experienced to the enhancement of infrared images. For directional filtering, the structural feature at each pixel is analyzed by the eigen-analysis. If the analysis shows that the pixel belongs to the edge region, we then perform directional smoothing along the tangential direction of the edge to improve its continuity, while directional sharpening along the normal direction to enhance the contrast. Meanwhile, the noise in the homogeneous region has been reduced notably by applying the appropriate wavelet coefficient. The algorithm is so effective that it reduces the noise while enhancing the edge sharpness at the same time. The quantitative measurements along with the visual inspection were also compared and results showed the algorithm based on wavelet transform has the ability in enhancing the infrared image. The proposed algorithm is compared to the other regular noise-reducing algorithms. The experimental results show that the proposed algorithm considerably improves the infrared image quality without causing any noticeable artifacts. Out of the algorithms compared, our algorithm demonstrated the best performance.