Resolution Aerial Images Research Articles

Accuracy Enhancement of Orthoimage Generation for Urban Areas

This research addresses the problems of conventional orthoimages created from aerial imagery of urban areas, especially relief displacements, occlusions and information loss caused by man-made objects. An approach is presented to generate more accurate orthoimages based on elevation models that exactly describe the entire surface of the observed region. The approach utilizes the digital building model, in addition to the digital terrain model, in the orthorectification process. Occluded areas are identified and filled in the final orthoimage by merging data from conjugate images. The data used in the research consists of a small block of high resolution aerial images covering an urban area. The images are captured recently with the digital aerial camera UltraCam-D. The image pixel size is 9 m by 9 m yielding a nearly 10-cm ground sample distance. The results reached by applying the proposed approach on the test images have been promising. They have proven the validity of the approach in generating more proper orthoimages.

A High Spatial Resolution Aerial Image Dataset and an Efficient Scene Classification Model

A High Spatial Resolution Aerial Image Dataset and an Efficient Scene Classification Model

Self-Adaptive-Filling Deep Convolutional Neural Network Classification Method for Mountain Vegetation Type Based on High Spatial Resolution Aerial Images

The composition and structure of mountain vegetation are complex and changeable, and thus urgently require the integration of Object-Based Image Analysis (OBIA) and Deep Convolutional Neural Networks (DCNNs). However, while integration technology studies are continuing to increase, there have been few studies that have carried out the classification of mountain vegetation by combining OBIA and DCNNs, for it is difficult to obtain enough samples to trigger the potential of DCNNs for mountain vegetation type classification, especially using high-spatial-resolution remote sensing images. To address this issue, we propose a self-adaptive-filling method (SAF) to incorporate the OBIA method to improve the performance of DCNNs in mountain vegetation type classification using high-spatial-resolution aerial images. Using this method, SAF technology was employed to produce enough regular sample data for DCNNs by filling the irregular objects created by image segmenting using interior adaptive pixel blocks. Meanwhile, non-sample segmented image objects were shaped into different regular rectangular blocks via SAF. Then, the classification result was defined by voting combining the DCNN performance. Compared to traditional OBIA methods, SAF generates more samples for the DCNN and fully utilizes every single pixel of the DCNN input. We design experiments to compare them with traditional OBIA and semantic segmentation methods, such as U-net, MACU-net, and SegNeXt. The results show that our SAF-DCNN outperforms traditional OBIA in terms of accuracy and it is similar to the accuracy of the best performing method in semantic segmentation. However, it reduces the common pretzel phenomenon of semantic segmentation (black and white noise generated in classification). Overall, the SAF-based OBIA using DCNNs, which is proposed in this paper, is superior to other commonly used methods for vegetation classification in mountainous areas.

FUSION OF DIRECT GEOREFERENCED AERIAL DRONE WITH TERRESTRIAL LASER SCANNER DATA THE CASE OF THE ROMAN BATHS OF AMATHUS, CYPRUS

Abstract. The fusion of geomatic techniques with different accuracy and resolution has been used in recent years to applications of geometrical documentation for several archaeological sites. In this research article, the case of the Roman Baths of Amathus in Limassol, Cyprus was investigated.Aerial photogrammetry and Terrestrial Laser Scanning (TLS) techniques were used to produce the final product. The photogrammetric data were based on Post-Processed Kinematic (PPK) imagery while the TLS georeference was based on targets.The main research objective of this paper is to examine the reliability of PPK photogrammetric data without the use of Ground Control Points (GCPs) and how well they can be integrated with TLS data. Also, the two acquisition techniques were compared and indicated that 0.005 m Ground Sampling Distance (GSD) resolution aerial images and 0.0061/10 m resolution scans can be qualitatively fused.The research paper will present the entire methodology up to the generation of the final 3D photorealistic product.

Solving photogrammetric cold cases using AI-based image matching: New potential for monitoring the past with historical aerial images

With the ongoing digitization in archives, an increasing number of historical data becomes available for research. This includes historical aerial images which provide detailed information about the depicted area. Among the applications enabled by these images are change detection of land use, land cover, glaciers, and coastal environments as well as the observation of land degradation, and natural hazards. Studying the depicted areas and occurring 3D deformations requires the generation of a digital surface model (DSM) which is usually obtained via photogrammetric Structure-from-Motion (SfM). However, conventional SfM workflows often fail in registering historical aerial images due to their radiometric characteristics introduced by digitization, original image quality, or vast temporal changes between epochs. We demonstrate that the feature matching step in the Structure from Motion (SfM) pipeline is particularly crucial. To address this issue, we apply the two synergetic neural network methods SuperGlue and DISK, improving feature matching for historical aerial images. This requires several modifications to enable rotational invariance and leveraging the high resolution of aerial images. In contrast to other studies our workflow does not require any prior information such as DSMs, flight height, focal lengths, or scan resolution which are often no more extent in archives. It is shown that our methods using adapted parameter settings are even able to deal with quasi texture-less images. This enables the simultaneous processing of various kind of mono-temporal and multi-temporal data handled in a single workflow from data preparation over feature matching through to camera parameter estimation and the generation of a sparse point cloud. It outperforms conventional strategies in the number of correct feature matches, number of registered images and calculated 3D points and allows the generation of multi-temporal DSMs with high quality.With the flexibility of the method, it enables the automatic processing of formerly unusable or only to be interactively processed data, e.g. aerial images where the flight route is unknown, or with difficult radiometric properties. This makes it possible to go back even further in time, where the data quality usually decreases, and enables a holistic monitoring and comparison of environments of high interest. The code is made publicly available at https://github.com/tudipffmgt/HAI-SFM.

Improving the performance of learned descriptors in the matching of high spatial resolution aerial images by proposing a large-scale dataset of vertical images

Improving the performance of learned descriptors in the matching of high spatial resolution aerial images by proposing a large-scale dataset of vertical images

Spatiotemporal changes of coastal land use land cover and its drivers in Shanghai, China between 1989 and 2015

The coastal zone, an ecotone that provides vital diverse ecosystem services, is one of the most ecologically fragile and sensitive areas on the Earth. It has been strongly influenced by human activities and climate change. Thus, understanding the spatiotemporal changes of land use land cover in the coast is an essential prerequisite for the comprehensive evaluation of coastal ecosystems and the promotion of sustainable development. This study investigated the spatial and temporal changes of land use land cover in the coastal zone of mainland Shanghai by using high spatial resolution aerial images, and the associated driving factors obtained from statistical yearbooks between 1989 and 2015. Our results show that the total land area in the coastal zone exhibited an increasing trend at an annual rate of 7.6% on average. The coastal urban land use also experienced substantial increases, with the degree of urban expansion reaching 42.1% in 2015. The coastal urbanization was at the cost of natural and semi-natural lands. Nearly 64.4% of agricultural land, 24.4% of ocean area within the buffer, 84.9% of fresh water, and 92.8% of the tidal flat had been converted to urban land during 1989–2015. The gradient analysis of land use land cover change along the north-to-south coastal line revealed the spatiotemporal patterns of total land, urbanization degree, and natural and semi-natural lands. The majority of the socioeconomic factors influenced land use land cover change in the coastal zone, positively contributing to the increase of public facilities’ use of land, but negatively affecting the freshwater areas. These findings can provide insights for decision-making in the future for coastal land use land cover planning and management in Shanghai.

Comparing hydrologic impacts on recreational trails to remotely sensed data

Trails systems have impacts on the surrounding hydrology and vegetation health. Trails not only remove and disturb vegetation but also compact the soil. This may result in water pooling and flowing along the trail which may result in changes to the watershed. This paper explores whether readily available remotely sensed data can be used to detect hydrologic and geomorphic changes on the ground. We collected data about areas of deposition and paths of transportation along the trails. Two 3-m resolution aerial images were acquired from Planet Labs and Normalized Difference Vegetation Index (NDVI), and Soil Adjusted Vegetation Index (SAVI) band combinations were calculated. We also acquired the most recent lidar data from the United States Geological Survey (USGS). This lidar data was used to construct a Digital Elevation Model (DEM) of the trail system followed by a flow accumulation, slope, and curvature raster. Statistical analysis was used to determine a relationship between the intensity of on the ground observations of hydrologic change and the remote sensing raster using box plots and nominal logistic regression. Results varied depending on the raster layer evaluated and the inclusion of a buffer around the deposition areas and transportation paths.

Multi-Scale and Context-Aware Framework for Flood Segmentation in Post-Disaster High Resolution Aerial Images

Floods are the most frequent natural disasters, occurring almost every year around the globe. To mitigate the damage caused by a flood, it is important to timely assess the magnitude of the damage and efficiently conduct rescue operations, deploy security personnel and allocate resources to the affected areas. To efficiently respond to the natural disaster, it is very crucial to swiftly obtain accurate information, which is hard to obtain during a post-flood crisis. Generally, high resolution satellite images are predominantly used to obtain post-disaster information. Recently, deep learning models have achieved superior performance in extracting high-level semantic information from satellite images. However, due to the loss of multi-scale and global contextual features, existing deep learning models still face challenges in extracting complete and uninterrupted results. In this work, we proposed a novel deep learning semantic segmentation model that reduces the loss of multi-scale features and enhances global context awareness. Generally, the proposed framework consists of three modules, encoder, decoder and bridge, combined in a popular U-shaped scheme. The encoder and decoder modules of the framework introduce Res-inception units to obtain reliable multi-scale features and employ a bridge module (between the encoder and decoder) to capture global context. To demonstrate the effectiveness of the proposed framework, we perform an evaluation using a publicly available challenging dataset, FloodNet. Furthermore, we compare the performance of the proposed framework with other reference methods. We compare the proposed framework with recent reference models. Quantitative and qualitative results show that the proposed framework outperforms other reference models by an obvious margin.

Sci-Net: scale-invariant model for buildings segmentation from aerial imagery

Buildings’ segmentation is a fundamental task in the field of earth observation and aerial imagery analysis. Most existing deep learning-based methods in the literature can be applied to a fixed or narrow-range spatial resolution imagery. In practical scenarios, users deal with a broad spectrum of image resolutions. Thus, a given aerial image often needs to be re-sampled to match the spatial resolution of the dataset used to train the deep learning model, which results in a degradation in segmentation performance. To overcome this challenge, we propose, in this manuscript, scale-invariant neural network (Sci-Net) architecture that segments buildings from wide-range spatial resolution aerial images. Specifically, our approach leverages UNet hierarchical representation and dense atrous spatial pyramid pooling to extract fine-grained multi-scale representations. Sci-Net significantly outperforms state-of-the-art models on the open cities AI and the multi-scale building datasets with a steady improvement margin across different spatial resolutions.

Space-to-speed architecture supporting acceleration on VHR image processing

One of the major focuses in the remote sensing community is the rapid processing of deep neural networks (DNNs) on very high resolution (VHR) aerial images. Few studies have investigated the acceleration of training and prediction by optimizing the architecture of the DNN system rather than designing a lightweight DNN. Parallel processing using multiple graphics processing units (GPUs) increases VHR image processing performance. It drives extremely large and frequent data transfers (input/output(I/O)) from random access memory (RAM) to GPU memory. As a result, the system bus congestion causes the system to hang, resulting in long latency in training/predicting. In this paper, we evaluate the causes of long latency and propose a space-to-speed (S2S) DNN system to overcome the aforementioned challenges. A three-level memory system aiming to reduce data transfer during system operation is presented. Distribution optimization with parallel processing was used to accelerate the training. Training optimizations on VHR images (such as hot-zone searching and image/ground truth queues for data saving) were used to train the VHR images efficiently. Inference optimization was performed to speed up prediction in the release mode. To verify the efficiency of the proposed system, we used aerial image labeling from the Institut National de Recherche en Informatique et en Automatique (INRIA) and benchmarks from the Massachusetts Institute of Technology Aerial Imagery for Roof Segmentation (MITAIRS) to test the system performance and accuracy. Without the loss of accuracy, the S2S system improved prediction speed on the testing dataset by eight GPUs in a normal setting in both the INRIA dataset (from 534 to 72 s) and the MITAIRS dataset (818 to 120 s). With the prediction in half-float (using float-16 data), an 8-GPU parallel processing increased the speed to 38 s in the INRIA dataset and 83 s in the MITAIRS dataset. In a pressure test, our proposed system operated on 18,000 images with a size of 5000 × 5000 from 18.2 to 1.8 h with the prediction in full-float (using float-32 data) and 43 min with the prediction in half-float, increasing the speed by a factor of 9.78 and 25.3, respectively, when compared to system runs without optimization.

SWDet: Anchor-Based Object Detector for Solid Waste Detection in Aerial Images

As we all know, waste pollution is one of the most serious environmental issues in the world. Efficient detection of solid waste (SW) in aerial images can improve subsequent waste classification and automatic sorting on the ground. However, traditional methods have some problems, such as poor generalization and limited detection performance. This article presents an anchor-based object detector for solid waste in aerial images (SWDet). Specifically, we construct asymmetric deep aggregation (ADA) network with structurally reparameterized asymmetric blocks to extract waste features with inconspicuous appearance. Besides, considering the waste with blurred boundaries caused by the resolution of aerial images, this article constructs efficient attention fusion pyramid network (EAFPN) to obtain contextual information and multiscale geospatial information via attention fusion. And the model can capture the scattering features of irregular shape waste. In addition, we construct the dataset for solid waste aerial detection (SWAD) by collecting aerial images of SW in Henan Province, China, to validate the effectiveness of our method. Experimental results show that SWDet outperforms most of existing methods for SW detection in aerial images.

Analysis of superelevation and debris flow velocities at Illgraben, Switzerland

The forced vortex equation, based on the cross-stream inclination of a flow surface as it passes through a bend, is a common approach to estimating debris flow velocities. Here, we present the preliminary results of a study of superelevation and the correction factor k, used to adapt the forced vortex equation to debris flows, based on data from the Illgraben torrent in Switzerland. The definition of the radius of curvature, a factor in the calculation of superelevation velocities, is not found to exercise a large influence on the calculated velocities when using high resolution aerial images, with the choice of cross-section location and k-factor exercising a more significant influence. The k-factors found here fall within the range previously reported in the literature, ranging from approximately 1 to 7, and a previously suggested non-linear relationship with Froude numbers is evident in the dataset. Following the debris flow season of 2022, the study will be continued with additional debris flow events and the investigative methods will be extended to include high-resolution LiDAR sensors installed along the Illgraben torrent.

Towards Large-Scale Small Object Detection: Survey and Benchmarks.

With the rise of deep convolutional neural networks, object detection has achieved prominent advances in past years. However, such prosperity could not camouflage the unsatisfactory situation of Small Object Detection (SOD), one of the notoriously challenging tasks in computer vision, owing to the poor visual appearance and noisy representation caused by the intrinsic structure of small targets. In addition, large-scale dataset for benchmarking small object detection methods remains a bottleneck. In this paper, we first conduct a thorough review of small object detection. Then, to catalyze the development of SOD, we construct two large-scale Small Object Detection dAtasets (SODA), SODA-D and SODA-A, which focus on the Driving and Aerial scenarios respectively. SODA-D includes 24828 high-quality traffic images and 278433 instances of nine categories. For SODA-A, we harvest 2513 high resolution aerial images and annotate 872069 instances over nine classes. The proposed datasets, as we know, are the first-ever attempt to large-scale benchmarks with a vast collection of exhaustively annotated instances tailored for multi-category SOD. Finally, we evaluate the performance of mainstream methods on SODA. We expect the released benchmarks could facilitate the development of SOD and spawn more breakthroughs in this field.

Super-resolution with generative adversarial networks for improved object detection in aerial images

PurposeData quality and data resolution are essential for computer vision tasks like medical image processing, object detection, pattern recognition and so on. Super-resolution is a way to increase the image resolution, and super-resolved images contain more information compared to their low-resolution counterparts. The purpose of this study is analyzing the effects of the super resolution models trained before on object detection for aerial images.Design/methodology/approachTwo different models were trained using the Super-Resolution Generative Adversarial Network (SRGAN) architecture on two aerial image data sets, the xView and the Dataset for Object deTection in Aerial images (DOTA). This study uses these models to increase the resolution of aerial images for improving object detection performance. This study analyzes the effects of the model with the best perceptual index (PI) and the model with the best RMSE on object detection in detail.FindingsSuper-resolution increases the object detection quality as expected. But, the super-resolution model with better perceptual quality achieves lower mean average precision results compared to the model with better RMSE. It means that the model with a better PI is more meaningful to human perception but less meaningful to computer vision.Originality/valueThe contributions of the authors to the literature are threefold. First, they do a wide analysis of SRGAN results for aerial image super-resolution on the task of object detection. Second, they compare super-resolution models with best PI and best RMSE to showcase the differences on object detection performance as a downstream task first time in the literature. Finally, they use a transfer learning approach for super-resolution to improve the performance of object detection.

Effects of local land use on riparian vegetation, water quality, and in situ toxicity

The conversion of riparian forests into agricultural land results in the loss of water quality and aquatic biota health. The objectives of this study were therefore to determine the proportion of land use with emphasis on the type of vegetation cover; evaluate the limnological parameters and concentration of inorganic elements in the water of the São José stream in the Dourados River Basin, Mato Grosso do Sul, Brazil; correlate land use with the concentrations of inorganic elements in water; and evaluate the risk to preservation aquatic biota and in situ toxic effect on Astyanax lacustris. We collected samples from the São José Stream in 2020 and evaluated land use with high resolution aerial images. The inorganic elements in water samples were quantified using inductively coupled plasma optical emission spectrometry. In the surroundings of the São José stream, a reduction in riparian forest was observed with a proportion of only 16.32% of the area and the predominance of agricultural areas with 75.06%. The concentrations of dissolved oxygen (1.510 mg L-1) and P (> 0.235 mg L-1) in the water did not comply with the national legislation. In addition, Al and P indicated risks regarding the conservation of aquatic biota (risk quotient >1). The in situ evaluation of A. lacustris also revealed toxicity in the water. The results indicate environmental imbalance in the São José stream, requiring mitigation measures for its restoration and the sustainable use of its resources.
 Keywords: anthropic action, inorganic contaminants, risks for aquatic biota.

Advanced Landslide Prediction Utilising Unmanned Aerial Vehicle (UAV)

Slope stability involves developing a terrain slope profile and determining the geometry of the failure surface to compute the slope factor of safety. Terrain capture and reconstruction traditionally has been expensive, time consuming and manpower intensive. This innovative method utilizing unmanned aerial system technology alongside the advancement in graphics processing can be proven as more effective and cost efficient. This research aims to develop a method to forecast the occurrence of landslide by utilizing drone technology. The objectives are to obtain data on terrain slope, create 3D model of the land, then perform analysis on the slope stability. Drone technology equipped with high accuracy GPS system captures high resolution aerial images of a land area for mapping. The data obtained is uploaded into computer software to generate the 3D model of the land. Then, the critical details such as contours or the elevations can be extracted. This information is transferred into an alternative software such as GeoStudio to analyze the stability of slope. Thus, the results can be used to predict the level of safety of the terrain slope and taken for further safety measures involving the particular area.

Optimal and Fully Connected Deep Neural Networks Based Classification Model for Unmanned Aerial Vehicle Using Hyperspectral Remote Sensing Images

Unmanned Aerial Vehicle (UAV) is treated as an effective technique for gathering high resolution aerial images. The UAV based aerial image collection is highly preferred due to its inexpensive and effective nature. However, automatic classification of aerial images poses a major challenging issue in the design of UAV, which could be handled by the deep learning (DL) models. This study designs a novel UAV assisted DL based image classification model (UAVDL-ICM) for Industry 4.0 environment. The proposed UAVDL-ICM technique involves an ensemble of voting based three DL models, namely Residual network (ResNet), Inception with ResNetv2, and Densely Connected Networks (DenseNet). Also, the hyperparameter tuning of these DL models takes place using a genetic programming (GP) approach. Finally, Oppositional Water Wave Optimization (OWWO) with Fully Connected Deep Neural networks (FCDNN) is employed for the classification of aerial images. A wide range of simulations takes place and the results are examined in terms of different parameters. A detailed comparative study highlighted the betterment of the UAVDL-ICM technique compared to other recent approaches.

UAV-based classification of maritime Antarctic vegetation types using GEOBIA and random forest

Development of vegetation communities in areas of Antarctica without permanent ice cover emphasizes the need for effective remote sensing techniques for proper monitoring of local environmental changes. Detection and mapping of vegetation by image classification remains limited in the Antarctic environment due to the complexity of its surface cover, and the spatial heterogeneity and spectral homogeneity of cryptogamic vegetation. As ultra-high resolution aerial images allow a comprehensive analysis of vegetation, this study aims to identify different types of vegetation cover (i.e., algae, mosses, and lichens) in an ice-free area of Hope Bay, on the northern tip of the Antarctic Peninsula. Using the geographic object-based image analysis (GEOBIA) approach, remote sensing data sets are tested in the random forest classifier in order to distinguish vegetation classes within vegetated areas. Because species of algae, mosses, and lichens may have similar spectral characteristics, subclasses are established. The results show that when only the mean values of green, red, and NIR bands are considered, the subclasses have low separability. Variations in accuracy and visual changes are identified according to the set of features used in the classification. Accuracy improves when multilayer information is used. A combination of spectral and morphometric products and by-products provides the best result for the detection and delineation of different types of vegetation, with an overall accuracy of 0.966 and a Kappa coefficient of 0.946. The method allowed for the identification of units primarily composed of algae, mosses, and lichens as well as differences in communities. This study demonstrates that ultra-high spatial resolution data can provide the necessary properties for the classification of vegetation in Maritime Antarctica, even in images obtained by sensors with low spectral resolution.

Abrupt increase in thermokarst lakes on the central Tibetan Plateau over the last 50 years

Thermokarst lakes are an important ecosystem component in permafrost terrains; therefore, quantifying changes in these lakes is important for evaluating the water balance and carbon budget on the Qinghai-Tibet Plateau (QTP). In this study, we utilized high spatial resolution aerial and satellite images from 1969, 2010, and 2019 to quantify changes in thermokarst lakes > 0.1 ha across four regions on the central QTP. The results indicated an overall significant increase in the lake number (+158%) and surface area (+123%) for all study regions over the last five decades, despite variations in change in these trends among the different landform types. Changes in individual lake processes indicated that the above lake changes were mainly characterized by a significant increase in the number of small lakes and area enlargements of large lakes, whereas thermokarst lake drainage only occurred in some gentle slope areas. By analyzing the potential factors that drive changes in thermokarst lakes in the study region, we found that persistent climate warming and the increasing of precipitation were the most likely explanations for the observed results. With continued climate warming and permafrost degradation, we expect a persistent increase in the number and surface area of thermokarst lakes; however, the probability of lake drainage may also increase with lake expansion.