Lightweight Integrated Solution for a UAV-Borne Hyperspectral Imaging System

Abstract

The rapid development of unmanned aerial vehicles (UAVs), miniature hyperspectral imagers, and relevant instruments has facilitated the transition of UAV-borne hyperspectral imaging systems from concept to reality. Given the merits and demerits of existing similar UAV hyperspectral systems, we presented a lightweight, integrated solution for hyperspectral imaging systems including a data acquisition and processing unit. A pushbroom hyperspectral imager was selected owing to its superior radiometric performance. The imager was combined with a stabilizing gimbal and global-positioning system combined with an inertial measurement unit (GPS/IMU) system to form the image acquisition system. The postprocessing software included the radiance transform, surface reflectance computation, geometric referencing, and mosaic functions. The geometric distortion of the image was further significantly decreased by a postgeometric referencing software unit; this used an improved method suitable for UAV pushbroom images and showed more robust performance when compared with current methods. Two typical experiments, one of which included the case in which the stabilizing gimbal failed to function, demonstrated the stable performance of the acquisition system and data processing system. The result shows that the relative georectification accuracy of images between the adjacent flight lines was on the order of 0.7–1.5 m and 2.7–13.1 m for cases with spatial resolutions of 5.5 cm and 32.4 cm, respectively.

UAV-Borne Hyperspectral Imaging Remote Sensing System Based on Acousto-Optic Tunable Filter for Water Quality Monitoring

“…Rapid developments of light unmanned aerial vehicles (UAVs), small hyperspectral imagers, and related instruments have facilitated the translation of UAV hyperspectral imaging system concepts into reality [1]. Hyperspectral imaging remote sensing technologies based on light UAVs are a combination of UAV, imaging spectrum, and remote sensing technologies, which possess unique advantages with regard to temporal, spatial, and spectral resolution [2].…”

The distribution of climbing chalk on climbed boulders and its impact on rock‐dwelling fern and moss species

“…Furthermore, it is worthwhile to continue with an experimental approach by applying climbing chalk on unclimbed rock and study its in situ impact on rock‐dwelling species (besides bryophytes and ferns, also including lichens and flowering plants) on different rock types. Finally, recent advances in drone and imaging technology may allow for mapping and analyzing visible climbing chalk traces and vegetation health along climbing routes with hyperspectral imaging by means of unmanned aerial vehicles (Peng et al., 2020; Strumia, Buonanno, Aronne, Santo, & Santangelo, 2020; Zhang, Zhang, Wei, Wang, & Huang, 2020).…”

Aerial image object detection method based on improved YOLOv5

“…In the Split stage, For any given feature mapping , two transformations and are first performed when the kernel size is 3 and 5, respectively. In the fusion phase, the results of multiple branches are first fused by elementwise summation: (6) The global average pooling is followed by the use of a low-dimensional fully connected layer to reduce the size of the feature output: (7) In the selection stage, the softmax activation function is used to obtain the following two weights:…”

“…Wang et al [6] proposed an improved small object detection algorithm EMT-ECoTNet based on YOLOv7-w6 to solve the problem of low detection accuracy due to complex backgrounds and small object features in UAV aerial images, which improved the convergence speed and accuracy. rate; Zhang et al [7] proposed a lightweight object detection algorithm LUSS-YOLO based on YOLOv5 to adapt to the problem of high false detection rate and missed detection rate of small objects in UAV remote sensing images. Remote sensing object detection.…”