Remote sensing image mosaic technology based on SURF algorithm in agriculture

Abstract

The remote sensing technology of unmanned aerial vehicle (UAV) is a low altitude remote sensing technology. The technology has been widely used in military, agricultural, medical, geographical mapping, and other fields by virtue of the advantages of fast acquisition, high resolution, low cost, and good security. But limited by the flying height of UAV and the focal length of the digital camera, the single image obtained by the UAV is difficult to form the overall cognition of the ground farmland area. In order to further expand the field of view, it is necessary to mosaic multiple single images acquired by UAV into a complete panoramic image of the farmland. In this paper, aiming at the problem of UAV low-altitude remote sensing image splicing, an image mosaic technique based on Speed Up Robust Feature (SURF) is introduced to achieve rapid image splicing. One hundred fifty ground farmland remote sensing images collected by UAV are used as experimental splicing objects, and the image splicing is completed by the global stitching strategy optimized by Levenberg-Marquardt (L-M). Experiments show that the strategy can effectively reduce the influence of cumulative errors and achieve automatic panoramic mosaic of the survey area.

Fast Anchor Point Matching for Emergency UAV Image Stitching Using Position and Pose Information

“…In addition to the handmade feature points, deep learning methods, like LIFT (Learned Invariant Feature Transform) [14], are also applied in this field. These feature algorithms are widely used in various applications of UAV image stitching [3,5,[15][16][17]. For feature matching, some excellent algorithms are applied, such as RANSAC (random sample consensus) [18], GMS (grid-based motion statistics) [19,20].…”

“…It is similar to SIFT but faster because of it utilizes acceleration methods, box filter and Haar filter [5]. Therefore, SURF is usually used in UAV image stitching [3,5]. The parameters of SURF are set as follows: set the threshold for the hessian keypoint detector to 100.…”

“…Works in the literature have proposed various approaches to stitch UAV images, however, most of them address the improvement of precision. Some approaches [1][2][3] are presented to improve the stitching speed. However, the stitching time of these methods is still too long to meet the needs of emergency applications.…”

A Review of Keypoints’ Detection and Feature Description in Image Registration

“…As the critical and fundamental problem in computer vision, its direct task is to identify and align a wide range of visual information from multisensors, thereby yielding richer visual representation for subsequent research and application [1,2]. is technique is used for image fusion enhancing image quality [3], image mosaic creating a seamless panorama image from multiple images (which may be obtained from different time, different perspectives, or different sensors) [4], image segmentation dividing an image into several specific regions with unique properties [5], and object tracking constructing the complete motion trajectory of an object [4] as well as object detection finding out all interested targets in the image and determining their positions and categories [6].…”

IFRAD: A Fast Feature Descriptor for Remote Sensing Images

“…Recently, extensive literature has proposed some feature descriptors with improvements in affine invariance, computational efficiency and accuracy [1,2,[27][28][29]. Despite their robustness in affine-invariance, their heavy dependency on exploiting gradient changes and image pyramids results in the complexity of these algorithms, which limits the applications in hardware platforms, therefore many proposed methods for remote sensing applications have been used only in off-line or post-processing applications [2,[30][31][32]. In pursuing real-time applications, some GPU-accelerated algorithms were proposed to reduce the time consumption.…”