In recent years, there has been a growing demand for 3D reconstructions of tunnel pits, underground pipe networks, and building interiors. For such scenarios, weak textures, repeated textures, or even no textures are common. To reconstruct these scenes, we propose covering the lighting sources with films of spark patterns to “add” textures to the scenes. We use a calibrated camera to take pictures from multiple views and then utilize structure from motion (SFM) and multi-view stereo (MVS) algorithms to carry out a high-precision 3D reconstruction. To improve the effectiveness of our reconstruction, we combine deep learning algorithms with traditional methods to extract and match feature points. Our experiments have verified the feasibility and efficiency of the proposed method. Full article

Commercial microwave link (MWL) used by mobile telecom operators for data transmission can provide hydro-meteorologically valid rainfall estimates according to studies in the past decade. For the first time, this study investigated a new method, the MSG technique, that uses Meteosat Second Generation (MSG) satellite data to improve MWL rainfall estimates. The investigation, conducted during daytime, used MSG optical (VIS0.6) and near IR (NIR1.6) data to estimate rain areas along a 15 GHz, 9.88 km MWL for classifying the MWL signal into wet–dry periods and estimate the baseline level. Additionally, the MSG technique estimated a new parameter, wet path length, representing the length of the MWL that was wet during wet periods. Finally, MWL rainfall intensity estimates from this new MSG and conventional techniques were compared to rain gauge estimates. The results show that the MSG technique is robust and can estimate gauge comparable rainfall estimates. The evaluation scores every three hours of RMSD, relative bias, and r² based on the entire evaluation period results of the MSG technique were 2.61 mm h⁻¹, 0.47, and 0.81, compared to 2.09 mm h⁻¹, 0.04, and 0.84 of the conventional technique, respectively. For convective rain events with high intensity spatially varying rainfall, the results show that the MSG technique may approximate the actual mean rainfall estimates better than the conventional technique. Full article

A relevant indicator for the eutrophication status in the Baltic Sea is the Chlorophyll-a concentration (Chl-a). Alas, ocean color remote sensing applications to estimate Chl-a in this brackish basin, characterized by large gradients in salinity and dissolved organic matter, are hampered by its optical complexity and atmospheric correction limits. This study presents Chl-a retrieval improvements for a fully reprocessed multi-sensor time series of remote-sensing reflectances (R_rs) at ~1 km spatial resolution for the Baltic Sea. A new ensemble scheme based on multilayer perceptron neural net (MLP) bio-optical algorithms has been implemented to this end. The study documents that this approach outperforms band-ratio algorithms when compared to in situ datasets, reducing the gross overestimates of Chl-a observed in the literature for this basin. The R_rs and Chl-a time series were then exploited for eutrophication monitoring, providing a quantitative description of spring and summer phytoplankton blooms in the Baltic Sea over 1998–2019. The analysis of the phytoplankton dynamics enabled the identification of the latitudinal variations in the spring bloom phenology across the basin, the early blooming in spring in the last two decades, and the description of the spatiotemporal coverage of summer cyanobacterial blooms in the central and southern Baltic Sea. Full article

Small mammals, and particularly rodents, are common inhabitants of farmlands, where they play key roles in the ecosystem, but when overabundant, they can be major pests, able to reduce crop production and farmers’ incomes, with tangible effects on the achievement of Sustainable Development Goals no 2 (SDG2, Zero Hunger) of the United Nations. Farmers do not currently have a standardized, accurate method of detecting the presence, abundance, and locations of rodents in their fields, and hence do not have environmentally efficient methods of rodent control able to promote sustainable agriculture oriented to reduce the environmental impacts of cultivation. New developments in unmanned aerial system (UAS) platforms and sensor technology facilitate cost-effective data collection through simultaneous multimodal data collection approaches at very high spatial resolutions in environmental and agricultural contexts. Object detection from remote-sensing images has been an active research topic over the last decade. With recent increases in computational resources and data availability, deep learning-based object detection methods are beginning to play an important role in advancing remote-sensing commercial and scientific applications. However, the performance of current detectors on various UAS-based datasets, including multimodal spatial and physical datasets, remains limited in terms of small object detection. In particular, the ability to quickly detect small objects from a large observed scene (at field scale) is still an open question. In this paper, we compare the efficiencies of applying one- and two-stage detector models to a single UAS-based image and a processed (via Pix4D mapper photogrammetric program) UAS-based orthophoto product to detect rodent burrows, for agriculture/environmental applications as to support farmer activities in the achievements of SDG2. Our results indicate that the use of multimodal data from low-cost UASs within a self-training YOLOv3 model can provide relatively accurate and robust detection for small objects (mAP of 0.86 and an F1-score of 93.39%), and can deliver valuable insights for field management with high spatial precision able to reduce the environmental costs of crop production in the direction of precision agriculture management. Full article

An outbreak of Ulva prolifera poses a massive threat to coastal ecology in the Southern Yellow Sea, China (SYS). It is a necessity to extract its area and monitor its development accurately. At present, Ulva prolifera monitoring by remote sensing imagery is mostly based on a fixed threshold or artificial visual interpretation for threshold selection, which has large errors. In this paper, an adaptive threshold model based on Google Earth Engine (GEE) is proposed and applied to extract U. prolifera in the SYS. The model first applies the Floating Algae Index (FAI) or Normalized Difference Vegetation Index (NDVI) algorithm on the preprocessed remote sensing images and then uses the Canny Edge Filter and Otsu threshold segmentation algorithm to extract the threshold automatically. The model is applied to Landsat8/OLI and Sentinel-2/MSI images, and the confusion matrix and cross-sensor comparison are used to evaluate the accuracy and applicability of the model. The verification results show that the model extraction of U. prolifera based on the FAI algorithm has higher accuracy (R² = 0.99, RMSE = 5.64) and better robustness. However, when the average cloud cover is more than 70% in the image (based on the statistical results of multi-year cloud cover information), the model based on the NDVI algorithm has better applicability and can extract the algae distributed at the edge of the cloud. When the model uses the FAI algorithm, it is named FAI-COM (model based on FAI, the Canny Edge Filter, and Otsu thresholding). And when the model uses the NDVI algorithm, it is named NDVI-COM (model based on NDVI, the Canny Edge Filter, and Otsu thresholding). Therefore, the final extraction results are generated by supplementing NDVI-COM results on the basis of FAI-COM extraction results in this paper. The F1-score of U. prolifera extracted results is above 0.85. The spatiotemporal distribution of U. prolifera in the South Yellow Sea from 2016 to 2020 is obtained through the model calculation. Overall, the coverage area of U. prolifera shows a decreasing trend over the five years. It is found that the delay in recovery time of Porphyra yezoensis culture facilities in the Northern Jiangsu Shoal and the manual salvage and cleaning-up of U. prolifera in May are among the reasons for the smaller interannual scale of algae in 2017 and 2018. Full article

Detecting animals to estimate abundance can be difficult, particularly when the habitat is dense or the target animals are fossorial. The recent surge in the use of thermal imagers in ecology and their use in animal detections can increase the accuracy of population estimates and improve the subsequent implementation of management programs. However, the use of thermal imagers results in many hours of captured flight videos which require manual review for confirmation of species detection and identification. Therefore, the perceived cost and efficiency trade-off often restricts the use of these systems. Additionally, for many off-the-shelf systems, the exported imagery can be quite low resolution (<9 Hz), increasing the difficulty of using automated detections algorithms to streamline the review process. This paper presents an animal species detection system that utilises the cost-effectiveness of these lower resolution thermal imagers while harnessing the power of transfer learning and an enhanced small object detection algorithm. We have proposed a distant object detection algorithm named Distant-YOLO (D-YOLO) that utilises YOLO (You Only Look Once) and improves its training and structure for the automated detection of target objects in thermal imagery. We trained our system on thermal imaging data of rabbits, their active warrens, feral pigs, and kangaroos collected by thermal imaging researchers in New South Wales and Western Australia. This work will enhance the visual analysis of animal species while performing well on low, medium and high-resolution thermal imagery. Full article

Coastal marine ecosystems are under stress, yet actionable information about the cumulative effects of human impacts has eluded ecologists. Habitat-forming seaweeds in temperate regions provide myriad irreplaceable ecosystem services, but they are increasingly at risk of local and regional extinction from extreme climatic events and the cumulative impacts of land-use change and extractive activities. Informing appropriate management strategies to reduce the impacts of stressors requires comprehensive knowledge of species diversity, abundance and distributions. Remote sensing undoubtedly provides answers, but collecting imagery at appropriate resolution and spatial extent, and then accurately and precisely validating these datasets is not straightforward. Comprehensive and long-running monitoring of rocky reefs exist globally but are often limited to a small subset of reef platforms readily accessible to in-situ studies. Key vulnerable habitat-forming seaweeds are often not well-assessed by traditional in-situ methods, nor are they well-captured by passive remote sensing by satellites. Here we describe the utility of drone-based methods for monitoring and detecting key rocky intertidal habitat types, the limitations and caveats of these methods, and suggest a standardised workflow for achieving consistent results that will fulfil the needs of managers for conservation efforts. Full article

With a wide range of satellite-derived vegetation bio-geophysical products now available to users, validation efforts are required to assess their accuracy and fitness for purpose. Substantial progress in the validation of such products has been made over the last two decades, but quantification of the uncertainties associated with in situ reference measurements is rarely performed, and the incorporation of uncertainties within upscaling procedures is cursory at best. Since current validation practices assume that reference data represent the truth, our ability to reliably demonstrate compliance with product uncertainty requirements through conformity testing is limited. The Fiducial Reference Measurements for Vegetation (FRM4VEG) project, initiated by the European Space Agency, is aiming to address this challenge by applying metrological principles to vegetation and surface reflectance product validation. Following FRM principles, and in accordance with the International Standards Organisation’s (ISO) Guide to the Expression of Uncertainty in Measurement (GUM), for the first time, we describe an end-to-end uncertainty evaluation framework for reference data of two key vegetation bio-geophysical variables: the fraction of absorbed photosynthetically active radiation (FAPAR) and canopy chlorophyll content (CCC). The process involves quantifying the uncertainties associated with individual in situ reference measurements and incorporating these uncertainties within the upscaling procedure (as well as those associated with the high-spatial-resolution imagery used for upscaling). The framework was demonstrated in two field campaigns covering agricultural crops (Las Tiesas–Barrax, Spain) and deciduous broadleaf forest (Wytham Woods, UK). Providing high-spatial-resolution reference maps with per-pixel uncertainty estimates, the framework is applicable to a range of other bio-geophysical variables including leaf area index (LAI), the fraction of vegetation cover (FCOVER), and canopy water content (CWC). The proposed procedures will facilitate conformity testing of moderate spatial resolution vegetation bio-geophysical products in future validation exercises. Full article

The classification of land use and land cover (LULC) is a well-studied task within the domain of remote sensing and geographic information science. It traditionally relies on remotely sensed imagery and therefore models land cover classes with respect to their electromagnetic reflectances, aggregated in pixels. This paper introduces a methodology which enables the inclusion of geographical object semantics (from vector data) into the LULC classification procedure. As such, information on the types of geographic objects (e.g., Shop, Church, Peak, etc.) can improve LULC classification accuracy. In this paper, we demonstrate how semantics can be fused with imagery to classify LULC. Three experiments were performed to explore and highlight the impact and potential of semantics for this task. In each experiment CORINE LULC data was used as a ground truth and predicted using imagery from Sentinel-2 and semantics from LinkedGeoData using deep learning. Our results reveal that LULC can be classified from semantics only and that fusing semantics with imagery—Semantic Boosting—improved the classification with significantly higher LULC accuracies. The results show that some LULC classes are better predicted using only semantics, others with just imagery, and importantly much of the improvement was due to the ability to separate similar land use classes. A number of key considerations are discussed. Full article

Soil salinization is a significant factor affecting corn growth in coastal areas. How to use multi-source remote sensing data to achieve the target of rapid, efficient and accurate soil salinity monitoring in a large area is worth further study. In this research, using Kenli District of the Yellow River Delta as study area, the inversion of soil salinity in a corn planting area was carried out based on the integration of ground imaging hyperspectral, unmanned aerial vehicles (UAV) multispectral and Sentinel-2A satellite multispectral images. The UAV and ground images were fused, and the partial least squares inversion model was constructed by the fused UAV image. Then, inversion model was scaled up to the satellite by the TsHARP method, and finally, the accuracy of the satellite-UAV-ground inversion model and results was verified. The results show that the band fusion of UAV and ground images effectively enrich the spectral information of the UAV image. The accuracy of the inversion model constructed based on the fused UAV images was improved. The inversion results of soil salinity based on the integration of satellite-UAV-ground were highly consistent with the measured soil salinity (R² = 0.716 and RMSE = 0.727), and the inversion model had excellent universal applicability. This research integrated the advantages of multi-source data to establish a unified satellite-UAV-ground model, which improved the ability of large-scale remote sensing data to finely indicate soil salinity. Full article

As coral reefs continue to degrade globally due to climate change, considerable effort and investment is being put into coral restoration. The production of coral offspring via asexual and sexual reproduction are some of the proposed tools for restoring coral populations and will need to be delivered at scale. Simple, inexpensive, and high-throughput methods are therefore needed for rapid analysis of thousands of coral offspring. Here we develop a machine learning pipeline to rapidly and accurately measure three key indicators of coral juvenile fitness: survival, size, and color. Using machine learning, we classify pixels through an open-source, user-friendly interface to quickly identify and measure coral juveniles on two substrates (field deployed terracotta tiles and experimental, laboratory PVC plastic slides). The method’s ease of use and ability to be trained quickly and accurately using small training sets make it suitable for application with images of species of sexually produced corals without existing datasets. Our results show higher accuracy of survival for slides (94.6% accuracy with five training images) compared to field tiles measured over multiple months (March: 77.5%, June: 91.3%, October: 97.9% accuracy with 100 training images). When using fewer training images, accuracy of area measurements was also higher on slides (7.7% average size difference) compared to tiles (24.2% average size difference for October images). The pipeline was 36× faster than manual measurements. The slide images required fewer training images compared to tiles and we provided cut-off guidelines for training for both substrates. These results highlight the importance and power of incorporating high-throughput methods, substrate choice, image quality, and number of training images for measurement accuracy. This study demonstrates the utility of machine learning tools for scalable ecological studies and conservation practices to facilitate rapid management decisions for reef protection. Full article

Surface subsidence caused by coal mining has a great impact on the geological and ecological environments and causes damage to houses, roads, and industrial buildings. In order to understand the subsidence pattern in the mountainous mining regions, three mining faces of the Zhangjiamao mining area in the north of Shaanxi province, northwestern China are taken as case study. Firstly, the small baseline subset (SBAS) technology is used to process 12 images obtained in the mining area to investigate the subsidence data from December 2019 to April 2020. The boundary of surface deformation of the mining area interpreted by the SBAS-InSAR technology is inconsistent with the theoretical boundary suggested by coal mine subsidence theories. Especially, there are some areas in which the real subsidence are larger than estimated area. This discrepancy must be corrected as steep slopes near the theoretical boundary may increase the likelihood of landslides. Our research indicates that: (1) The accumulated displacement and the maximum deformation rate reached −120.759 mm and −270.012 mm/yr in the study area, and the subsidence boundary of the three mining faces is revealed; (2) the combination of the predicted boundary and slope stability analysis can effectively identify the landslide region at the edge of subsidence boundary; (3) the field surveys have proved the effectiveness of this method. The mining area subsidence revealed by our research helps to further understand the impact of land subsidence caused by mining in the mountainous areas and provides a practical method to predict subsidence boundaries and the likelihood for landslides. Full article

The existence of several NDVI products in Qinghai-Tibetan Plateau (QTP) makes it challenging to identify the ideal sensor for vegetation monitoring as an important factor for landslide detection studies. A pixel-based analysis of the NDVI time series was carried out to compare the performances of five NDVI products, including ETM+, OLI, MODIS Series, and AVHRR sensors in QTP. Harmonic analysis of time series and wavelet threshold denoising were used for reconstruction and denoising of the five NDVI datasets. Each sensor performance was assessed based on the behavioral similarity between the original and denoised NDVI time series, considering the preservation of the original shape and time series values by computing correlation coefficient (CC), mean absolute error (MAE), root mean square error (RMSE), and signal to noise ratio (SNR). Results indicated that the OLI slightly outperformed the other sensors in all performance metrics, especially in mosaic natural vegetation, grassland, and cropland, providing 0.973, 0.015, 0.022, and 27.220 in CC, MAE, RMSE, and SNR, respectively. AVHRR showed similar results to OLI, with the best results in the predominant type of land covers (needle-leaved, evergreen, closed to open). The MODIS series performs lower across all vegetation classes than the other sensors, which might be related to the higher number of artifacts observed in the original data. In addition to the satellite sensor comparison, the proposed analysis demonstrated the effectiveness and reliability of the implemented methodology for reconstructing and denoising different NDVI time series, indicating its suitability for long-term trend analysis of different natural land cover classes, vegetation monitoring, and change detection. Full article

Object tracking is an essential aspect of environmental perception technology for autonomous vehicles. The existing object tracking algorithms can only be applied well to simple scenes. When the scenes become complex, the algorithms have poor tracking performance and insufficient robustness, and the problems of tracking drift and object loss are prone to occur. Therefore, a robust object tracking algorithm for autonomous vehicles in complex scenes is proposed. Firstly, we study the Siam-FC network and related algorithms, and analyze the problems that need to be addressed in object tracking. Secondly, the construction of a double-template Siamese network model based on multi-feature fusion is described, as is the use of the improved MobileNet V2 as the feature extraction backbone network, and the attention mechanism and template online update mechanism are introduced. Finally, relevant experiments were carried out based on public datasets and actual driving videos, with the aim of fully testing the tracking performance of the proposed algorithm on different objects in a variety of complex scenes. The results showed that, compared with other algorithms, the proposed algorithm had high tracking accuracy and speed, demonstrated stronger robustness and anti-interference abilities, and could still accurately track the object in real time without the introduction of complex structures. This algorithm can be effectively applied in intelligent vehicle driving assistance, and it will help to promote the further development and improvement of computer vision technology in the field of environmental perception. Full article

Real-time precise point positioning (RT-PPP) has become a powerful technique for the determination of the zenith tropospheric delay (ZTD) over a GPS (global positioning system) or GNSS (global navigation satellite systems) station of interest, and the follow-on high-precision retrieval of precipitable water vapor (PWV). The a priori zenith hydrostatic delay (ZHD) and the mapping function used in the PPP approach are the two factors that could affect the accuracy of the PPP-based ZTD significantly. If the in situ atmospheric pressure is available, the Saastamoinen model can be used to determine ZHD values, and the model-predicted ZHD results are of high accuracy. However, not all GPS/GNSS are equipped with an in situ meteorological sensor. In this research, the daily forecasting ZHD and mapping function values from VMF1 forecasting (VMF1_FC) and VMF3 forecasting (VMF3_FC) products were used for the determination of the GPS-derived PWV. The a priori ZHDs derived from VMF1_FC and VMF3_FC were first evaluated by comparing against the reference ZHDs from globally distributed radiosonde stations. GPS observations from 41 IGS stations that have co-located radiosonde stations during the period of the first half of 2020 were used to test the quality of GPS-ZTD and GPS-PWV. Three sets of ZTDs estimated from RT-PPP solutions using the a priori ZHD and mapping function from the following three VMF products were evaluated: (1) VMF1_FC; (2) VMF3_FC (resolution 5° × 5°); (3) VMF3_FC (resolution 1° × 1°). The results showed that, when the ZHDs from 443 globally distributed radiosonde stations from 1 July 2018 to 30 June 2021 were used as the reference, the mean RMSEs of the ZHDs from the three VMF products were 5.9, 5.4, and 4.3 mm, respectively. The ZTDs estimated from RT-PPP at 41 selected IGS stations were compared with those from IGS, and the results showed that the mean RMSEs of the ZTDs of the 41 stations from the three PPP solutions were 8.6, 9.0, and 8.6 mm, respectively, and the mean RMSEs of the PWV converted from their corresponding ZWDs were 1.9, 2.4, and 1.7 mm, respectively, in comparison with the reference PWV from co-located radiosonde stations. The results suggest that the a priori ZHD and mapping function from VMF1_FC and VMF3_FC can be used for the precise determination of real-time GPS/GNSS-PWV in most regions, especially the VMF3_FC (resolution 1° × 1°) product. Full article