Unmanned aerial vehicle (UAV) remote sensing platforms allow for normalized difference vegetation index (NDVI) values to be mapped with a relatively high resolution, therefore enabling an unforeseeable ability to evaluate the influence of the operation parameters on the quality of the thus acquired data. In order to better understand the effects of these parameters, we made a comprehensive evaluation on the effects of the solar zenith angle (SZA), the time of day (TOD), the flight altitude (FA) and the growth level of paddy rice at a pixel-scale on UAV-acquired NDVI values. Our results show that: (1) there was an inverse relationship between the FA (≤100 m) and the mean NDVI values, (2) TOD and SZA had a greater impact on UAV–NDVIs than the FA and the growth level; (3) Better growth levels of rice—measured using the NDVI—could reduce the effects of the FA, TOD and SZA. We expect that our results could be used to better plan flight campaigns that aim to collect NDVI values over paddy rice fields.

Cross-domain few-shot learning (FSL) often employs adversarial domain adaptation techniques to address the issue of data distribution discrepancies between the source and target domains. However, forcing the alignment of two distinct domains may lead to distortions in class distribution alignment and result in a decrease in classification performance in hyperspectral image analysis. Moreover, existing cross-domain methods are often applied to satellite/airborne hyperspectral image as both the source and target domain. It is rarely explored whether the same cross-domain methods can be applied for cross applications where the source domain and target domain data could be both satellite/airborne hyperspectral image with lower spatial resolution and unmanned aerial vehicle (UAV) hyperspectral image with higher spatial resolution. To address these issues, this paper proposes a novel domain-adaptive FSL network with dual branches respectively aiming at domain fusion and domain separation. The domain fusion branch uses a conditional adversarial network to align the global distributions of the two domains, while the domain separation branch introduces gate mechanism for discriminative feature learning in each domain to achieve independent category distributions. During the experiment, the proposed method is evaluated by performing cross-transfer learning under the condition that low spatial resolution hyperspectral data and high spatial resolution hyperspectral data are used as source and target data alternately. The experimental results suggest that the proposed method not only mitigates the negative effects of forced alignment in domain fusion but also holds potential for cross-domain transfer learning between low and high spatial resolution hyperspectral images.

Unmanned air vehicle (UAV) based imaging has been an attractive technology to be used for wind turbine blades (WTBs) monitoring. In such applications, image motion blur is a challenging problem which means that motion deblurring is of great significance in the monitoring of running WTBs. However, an embarrassing fact for these applications is the lack of sufficient WTB images, which should include better pairs of sharp images and blurred images captured under the same conditions for network model training. To overcome the challenge of image pair acquisition, a training sample synthesis method is proposed. Sharp images of static WTBs were first captured, and then video sequences were prepared by running WTBs at different speeds. The blurred images were identified from the video sequences and matched to the sharp images using image difference. To expand the sample dataset, rotational motion blurs were simulated on different WTBs. Synthetic image pairs were then produced by fusing sharp images and images of simulated blurs. Finally, a total of 4000 image pairs were obtained. To conduct motion deblurring, a hybrid deblurring network integrated with DeblurGAN and DeblurGANv2 was deployed. The results show that the integration of DeblurGANv2 and Inception-ResNet-v2 provides better deblurred images, in terms of both metrics of signal-to-noise ratio (80.138) and structural similarity (0.950) than those obtained from the comparable networks of DeblurGAN and MobileNet-DeblurGANv2.

Monitoring plant growth is essential in modern agriculture to guarantee productivity. Since manual measurement of plant characteristics is laborious and expensive, automatic measures are desirable. This can be accomplished by methods such as vision-based structure from motion (SFM) to obtain the 3-D information of a plant. An SFM method based on binocular vision is here developed to acquire the physical parameters of plants. In this method, image sequences are captured by a binocular camera from multiple views of the target plant to improve the effectiveness and simplify the implementation. The spatial relationships between adjacent images are estimated through image feature extraction and matching. A disparity map is then built and the 3-D coordinate of each image pixel is obtained by applying stereo-vision. The connected coordinates then constitute the 3-D model of the plant. By doing so, plant structure parameters, such as height, canopy size, and trunk diameter, can be derived from the 3-D model. Experimental results show that the measured plant height, the canopy width, and the trunk diameter of the target plant are within an acceptable accuracy at the millimeter level, and the mean errors of the measured sizes are all less than 2%. This demonstrates the potential value of the proposed method for online growth monitoring of agricultural plants.

Accurate estimation of the degree of regeneration in tropical dry forest (TDF) is critical for conservation policymaking and evaluation. Hyperspectral remote sensing and light detection and ranging (LiDAR) have been used to characterize the deterministic successional stages in a TDF. These successional stages, classified as early, intermediate, and late, are considered a proxy for mapping the age since the abandonment of a given forest area. Expanding on the need for more accurate successional forest mapping, our study considers the age attributes of a TDF study area as a continuous expression of relative attribute scores/levels that vary along the process of ecological succession. Specifically, two remote-sensing data sets: HyMap (hyperspectral) and LVIS (waveform LiDAR), were acquired at the Santa Rosa National Park Environmental Monitoring Super Site (SRNP-EMSS) in Costa Rica, were used to generate age-attribute metrics. These metrics were then used as entry-level variables on a randomized nonlinear archetypal analysis (RNAA) model to select the most informative metrics from both data sets. Next, a relative attribute learning (RAL) algorithm was adapted for both independent and fused metrics to comparatively learn the relative attribute levels of the forest ages of the study area. In this study, four HyMap indices and five LVIS metrics were found to have the potential to map the forest ages of the study area, and compared with these results, a significant improvement was found through the fusion of the metrics on the accuracy of the generated forest age maps. By linking the age group mapping and the relative attribute mapping results, a dynamic gradient of the age-attribute transition patterns emerged.

Hyperspectral images (HSIs) often contain pixels with mixed spectra, which makes it difficult to accurately separate the background signal from the anomaly target signal. To mitigate this problem, we present a method that applies spectral unmixing and structure sparse representation to accurately extract the pure background features and to establish a structured sparse representation model at a sub-pixel level by using the Archetypal Analysis (AA) scheme. Specifically, spectral unmixing with AA is used to unmix the spectral data to obtain representative background endmember signatures. Moreover the unmixing reconstruction error is utilized for the identification of the target. Structured sparse representation is also adopted for anomaly target detection by using the background endmember features from AA unmixing. Moreover, both the AA unmixing reconstruction error and the structured sparse representation reconstruction error are integrated together to enhance the anomaly target detection performance. The proposed method exploits background features at a sub-pixel level to improve the accuracy of anomaly target detection. Comparative experiments and analysis on public hyperspectral datasets show that the proposed algorithm potentially surpasses all the counterpart methods in anomaly target detection.