When sufficient time-series images and training data are unavailable for crop classification, features extracted from convolutional neural network (CNN)-based representative learning may not provide useful information to discriminate crops with similar spectral characteristics, leading to poor classification accuracy. In particular, limited input data are the main obstacles to obtain reliable classification results for early crop mapping. This study investigates the potential of a hybrid classification approach, i.e., CNN-random forest (CNN-RF), in the context of early crop mapping, that combines the automatic feature extraction capability of CNN with the superior discrimination capability of an RF classifier. Two experiments on incremental crop classification with unmanned aerial vehicle images were conducted to compare the performance of CNN-RF with that of CNN and RF with respect to the length of the time-series and training data sizes. When sufficient time-series images and training data were used for the classification, the accuracy of CNN-RF was slightly higher or comparable with that of CNN. In contrast, when fewer images and the smallest training data were used at the early crop growth stage, CNN-RF was substantially beneficial and the overall accuracy increased by maximum 6.7%p and 4.6%p in the two study areas, respectively, compared to CNN. This is attributed to its ability to discriminate crops from features with insufficient information using a more sophisticated classifier. The experimental results demonstrate that CNN-RF is an effective classifier for early crop mapping when only limited input images and training samples are available.

As the use of unmanned aerial vehicle (UAV) images rapidly increases so does the need for precise radiometric calibration. For UAV images, relative radiometric calibration is required in addition to the traditional vicarious radiometric calibration due to the small field of view. For relative radiometric calibration, some UAVs install irradiance sensors, but most do not. For UAVs without them, an intelligent scheme for relative radiometric calibration must be applied. In this study, a relative radiometric calibration method is proposed to improve the quality of a reflectance map without irradiance measurements. The proposed method, termed relative calibration by the optimal path (RCOP), uses tie points acquired during geometric calibration to define the optimal paths. A calibrated image from RCOP was compared to validation data calibrated with irradiance measurements. As a result, the RCOP method produces seamless mosaicked images with uniform brightness and reflectance patterns. Therefore, the proposed method can be used as a precise relative radiometric calibration method for UAV images.

In recent years, Korea has sustained consistent access to remote sensed data by launching Korea Multi-Purpose Satellite-3A (KOMPSAT-3A, K3A)—an updated version of the high-resolution KOMPSAT series. This KOMPSAT-3A required calibration and validation (Cal/Val) before and after its launch to enable proper functional characterization and to maintain the veracity of data collected. The Korea Aerospace Research Institute (KARI) executed the initial prelaunch calibration in the laboratory and we performed the Cal/Val of KOMPSAT-3A during the Launch and Early Operation Phase (LEOP) in the field. Two suitable sites in Korea and Mongolia with stable weather, almost uniform terrain, and near Lambertian diffusion, provided the necessary tarp reflectance to calculate the absolute radiometric calibration coefficients. The surface reflectance was determined using 12 and four well-calibrated reference reflectance tarps employing the FieldSpec^® 3(Analytical Spectral Devices Inc., Boulder, CO, USA) Spectroradiometer. Subsequently, the top of atmosphere (TOA) radiance was estimated using radiative transfer code (RTC) software based on the Atmospheric and Topographic Correction (ATCOR). In addition, cross calibration was simultaneously performed at the Libya-4 pseudo invariant calibration site (PICS) for KOMPSAT-3A TOA radiance, using the spectral band adjustment factor (SBAF) compensated Landsat 8 reflectance and the Second Simulation of Satellite Signal in the Solar Spectrum (6S) to compute cross calibration coefficients. The results of the KOMPSAT-3A absolute calibration coefficient show that the R² values were over 0.99, implying a significant correlation for almost all bands between the TOA radiance and the KOMPSAT-3A spectral band response at both campaign sites. However, this study reveals a difference of less than 5% calibration gains for all bands compared to the prelaunch values, while the cross calibration gain is below 5% in visible bands and above 5% in the near infrared band. An effort to optimize the reliability of the absolute calibration coefficients resorted to the rigorous quantification of uncertainties amongst atmospheric conditions, the digital number (DN), the reflectance tarp, the bidirectional reflectance distribution function (BRDF), and ozone levels. Therefore, we presumed that the total uncertainty was 4.27%, which conforms to some published results.

Jae-Hyun Ryu, Hyun-Dong Moon, Kyung-Do Lee, Jaeil Cho, Ho-yong Ahn. Korean J. Remote Sens. 2024;40:657-73. https://doi.org/10.7780/kjrs.2024.40.5.1.19

Unmanned aerial vehicle (UAV) imaging provides the ability to obtain high-resolution images at a lower cost than satellite imagery and aerial photography. However, multiple UAV images need to be mosaicked to obtain images of large areas, and the resulting UAV multispectral image mosaics typically contain seam lines. To address this problem, we applied irradiance, vignette, and bidirectional reflectance distribution function (BRDF) filters and performed field work using a DJI Mavic 3 Multispectral (M3M) camera to collect data. We installed a calibrated reference tarp (CRT) in the center of the collection area and conducted three types of flights (BRDF, vignette, and validation) to measure the irradiance, radiance, and reflectance—which are essential for irradiance correction—using a custom reflectance box (ROX). A vignette filter was generated from the vignette parameter, and the anisotropy factor (ANIF) was calculated by measuring the radiance at the nadir, following which the BRDF model parameters were calculated. The calibration approaches were divided into the following categories: a vignette-only process, which solely applied vignette and irradiance corrections, and the full process, which included irradiance, vignette, and BRDF. The accuracy was verified through a validation flight. The radiance uncertainty at the seam line ranged from 3.00 to 5.26% in the 80% lap mode when using nine images around the CRT, and from 4.06 to 6.93% in the 50% lap mode when using all images with the CRT. The term ‘lap’ in ‘lap mode’ refers to both overlap and sidelap. The images that were subjected to the vignette-only process had a radiance difference of 4.48–6.98%, while that of the full process images was 1.44–2.40%, indicating that the seam lines were difficult to find with the naked eye and that the process was successful.

Jae-Hyun Ryu, Hyejin Lee, Hyun-Dong Moon, Kyung-Do Lee, Chan-won Park, Jaeil Cho, Seon-Woong Jang, Ho-yong Ahn. Korean J. Remote Sens. 2024;40:539-49. https://doi.org/10.7780/kjrs.2024.40.5.1.10