Automatic Detection of Individual Trees from VHR Satellite Images Using Scale-Space Methods

Superpixels, as a state-of-the-art segmentation paradigm, have recently been widely used in computer vision and pattern recognition. Despite the effectiveness of these algorithms, there are still many limitations and challenges dealing with Very High-Resolution (VHR) satellite images especially in complex urban scenes. In this paper, we develop a superpixel algorithm as a modified edge-based version of Simple Linear Iterative Clustering (SLIC), which is here called ESLIC, compatible with VHR satellite images. Then, based on the modified properties of generated superpixels, a heuristic multi-scale approach for building extraction is proposed, based on the stereo satellite imagery along with the corresponding Digital Surface Model (DSM). First, to generate the modified superpixels, an edge-preserving term is applied to retain the main building boundaries and edges. The resulting superpixels are then used to initially refine the stereo-extracted DSM. After shadow and vegetation removal, a rough building mask is obtained from the normalized DSM, which highlights the appropriate regions in the image, to be used as the input of a multi-scale superpixel segmentation of the proper areas to determine the superpixels inside the building. Finally, these building superpixels with different scales are integrated and the output is a unified building mask. We have tested our methods on building samples from a WorldView-2 dataset. The results are promising, and the experiments show that superpixels generated with the proposed ESLIC algorithm are more adherent to the building boundaries, and the resulting building mask retains urban object shape better than those generated with the original SLIC algorithm.

As the acquisition of very high resolution (VHR) satellite images becomes easier owing to technological advancements, ever more stringent requirements are being imposed on automatic image interpretation. Moreover, per-pixel classification has become the focus of research interests in this regard. However, the efficient and effective processing and the interpretation of VHR satellite images remain a critical task. Convolutional neural networks (CNNs) have recently been applied to VHR satellite images with considerable success. However, the prevalent CNN models accept input data of fixed sizes and train the classifier using features extracted directly from the convolutional stages or the fully connected layers, which cannot yield pixel-to-pixel classifications. Moreover, training a CNN model requires large amounts of labeled reference data. These are challenging to obtain because per-pixel labeled VHR satellite images are not open access. In this paper, we propose a framework called the unsupervised-restricted deconvolutional neural network (URDNN). It can solve these problems by learning an end-to-end and pixel-to-pixel classification and handling a VHR classification using a fully convolutional network and a small number of labeled pixels. In URDNN, supervised learning is always under the restriction of unsupervised learning, which serves to constrain and aid supervised training in learning more generalized and abstract feature. To some degree, it will try to reduce the problems of overfitting and undertraining, which arise from the scarcity of labeled training data, and to gain better classification results using fewer training samples. It improves the generality of the classification model. We tested the proposed URDNN on images from the Geoeye and Quickbird sensors and obtained satisfactory results with the highest overall accuracy (OA) achieved as 0.977 and 0.989, respectively. Experiments showed that the combined effects of additional kernels and stages may have produced better results, and two-stage URDNN consistently produced a more stable result. We compared URDNN with four methods and found that with a small ratio of selected labeled data items, it yielded the highest and most stable results, whereas the accuracy values of the other methods quickly decreased. For some categories with fewer training pixels, accuracy for categories from other methods was considerably worse than that in URDNN, with the largest difference reaching almost 10%. Hence, the proposed URDNN can successfully handle the VHR image classification using a small number of labeled pixels. Furthermore, it is more effective than state-of-the-art methods.

In this article, we develop a novel method for the detection of vineyard parcels in agricultural landscapes based on very high resolution (VHR) optical remote sensing images. Our objective is to perform texture-based image retrieval and supervised classification algorithms. To do that, the local textural and structural features inside each image are taken into account to measure its similarity to other images. In fact, VHR images usually involve a variety of local textures and structures that may verify a weak stationarity hypothesis. Hence, an approach only based on characteristic points, not on all pixels of the image, is supposed to be relevant. This work proposes to construct the local extrema-based descriptor (LED) by using the local maximum and local minimum pixels extracted from the image. The LED descriptor is formed based on the radiometric, geometric and gradient features from these local extrema. We first exploit the proposed LED descriptor for the retrieval task to evaluate its performance on texture discrimination. Then, it is embedded into a supervised classification framework to detect vine parcels using VHR satellite images. Experiments performed on VHR panchromatic PLEIADES image data prove the effectiveness of the proposed strategy. Compared to state-of-the-art methods, an enhancement of about 7% in retrieval rate is achieved. For the detection task, about 90% of vineyards are correctly detected.

Satellite imagery has been used to improve scientific research worldwide. In this study, the southern right whale (Eubalaena australis) was chosen to test the use of medium, high, and very high resolution (VHR) satellite images, on the Brazilian breeding ground. These images were used to identify the whales and were compared to aerial survey data collected in the same area. The VHR satellite images from the Pleiades‐1A satellite, available on Google Earth, displayed the best results when compared to those from Sentinel 2, Landsat 8, Rapid Eye, and Planet Scope. No significant differences were observed (Mann‐Whitney U test) between the possible whales recorded in the satellite images and of real whales recorded in situ by aerial surveys, while considering either the number of groups (p = .841, n = 5) or the total number of animals (p = .222, n = 5). Further, when using VHR images, the geographical positions of the whales recorded in situ had a positive correlation with the positions generated from the satellite images (Mantel test: r = 0.52, p = .001, n = 13). This technique may represent an important tool for detecting right whales, especially in countries where research funding is scarce.

Case instance segmentation of small farmland based on Mask R-CNN of feature pyramid network with double attention mechanism in high resolution satellite images

Road extraction from very high-resolution (VHR) satellite images plays an important role in the remote-sensing applications. Although tracing road features in satellite images has received much attention over the years, fully automated methods appear to be in their infancy. To tackle these limitations to some extent, this paper presents a novel object-based automatic road extraction method. The proposed method consists of five main steps. First, satellite images are segmented to generate objects. Then, two object-based filters are applied to compute object features to select road candidates. After that, the road class is extracted using the support vector machine (SVM) based on the extracted feature set. Finally, tensor voting (TV), active contour, and the geometrical information are integrated to eliminate road gaps and improve road smoothness. Experiments are conducted on nine test sites. It is experimentally demonstrated that the proposed method produces an excellent accuracy for the automatic road extraction from VHR satellite images.

Reliable building delineation in very high resolution (VHR) satellite imagery can be achieved by precise disparity information extracted from stereo pairs. However, off-nadir VHR images over urban areas contain many occlusions due to building leaning that creates gaps in the extracted disparity maps. The typical approach to fill these gaps is by interpolation. However, it inevitably degrades the quality of the disparity map and reduces the accuracy of building detection. Thus, this research proposes a registration-based technique for mapping the disparity of off-terrain objects to avoid the need for disparity interpolation and normalization. The generated disparity by the proposed technique is then used to support building detection in off-nadir VHR satellite images. Experiments in a high-rise building area confirmed that 75 percent of the detected building roofs overlap precisely the reference data, with almost 100 percent correct detection. These accuracies are substantially higher than those achieved by other published research.

Abstract. The Very High Resolution (VHR) satellite imageries such us Pleiades, WorldView-2, GeoEye-1 used for precise mapping purpose must be corrected from any distortion to achieve the expected accuracy. Orthorectification is performed to eliminate geometric errors of the VHR satellite imageries. Orthorectification requires main input data such as Digital Elevation Model (DEM) and Ground Control Point (GCP). The VHR systematic-ortho imageries were generated using SRTM 30m DEM without using any GCP data. The accuracy value differences of VHR systematic-ortho imageries and VHR orthorectified imageries using GCP currently is not exactly defined. This study aimed to identified the accuracy comparison of VHR systematic-ortho imageries against orthorectified imageries using GCP. Orthorectified imageries using GCP created by using Rigorous model. Accuracy evaluation is calculated by using several independent check points.

Oil palm trees detection and counting on Microsoft Bing Maps Very High Resolution (VHR) satellite imagery and Unmanned Aerial Vehicles (UAV) data using image processing thresholding approach

This paper presents a two-level Active Learning (AL) classification method for the interactive detection of earthquake-induced debris via the synergetic use of post-disaster Very High Resolution (VHR) satellite and local decimeter-resolution aerial images. The proposed method is performed by interactively guiding the human expert in the collection of labeled training samples from aerial images and optimally planning further aerial surveys. A label propagation mechanism is adopted to reliably propagate the labeled pixels annotated by the user on the aerial image by visual photointerpretation to the (lower resolution) satellite image. The experimental analysis is carried out using post-disaster images of the 2010 Yushu earthquake in China. The obtained results confirm that the proposed method can significantly reduce the user annotation effort and the cost for acquiring additional aerial images leading to more accurate and timely debris detection maps.

ABSTRACTOil palm trees are important economic crops in tropical areas. Accurate knowledge of the number of oil palm trees in a plantation area is important to predict the yield of palm oil, manage the growing situation of the palm trees and maximise their productivity. In this study, we propose a novel automatic method for detection and enumeration of individual oil palm trees using images from unmanned aerial vehicles (UAVs). This method required three major steps. First, images from UAVs were classified as vegetation or non-vegetation by the support vector machine (SVM) classifier. Second, a feature descriptor based on the histogram of oriented gradient (HOG) was designed for palm trees and used to extract features for machine learning. Finally, a SVM classifier was trained and optimised using the HOG features from positive (i.e., oil palm trees) and negative samples (i.e., objects other than oil palm trees). The trained classifier was then applied to detect individual oil palm trees using adaptive moving windows that allowed it to also return the crown size of each oil palm tree. The method was trained at one site and validated independently at four other sites with different situations. The overall accuracy of palm tree detection was 99.21% at the training site and 99.39%, 99.06%, 99.90% and 94.63% at the four validation sites; the last one was for the most challenging site, in which palm trees were mixed with other trees. These tests confirm the effectiveness of the proposed method. The simplicity and great efficiency of the proposed method allow it to support oil palm tree counting for large areas using imagery from UAVs.

Third-dimension information is of a great importance for several remote sensing applications, such as building detection. The main data-source for these applications is very high resolution (VHR) satellite images which allow detailed mapping of complex environments. Stereo VHR satellite images allow the extraction of two correlated types of third-dimension information: disparity and elevation information. While the disparity is measured directly, the elevation information is derived computationally. To measure the disparity information, two overlapped images are matched. However, for the backward and forward off-nadir VHR stereo images, building facades occlude areas and hence create many data gaps. When the disparity is required to represent only the off-terrain objects, interpolation and normalization techniques are typically used. However, in dense urban environments, these techniques destroy the quality of the generated data. Therefore, this paper proposes a registration-based technique to measure the disparity of the above-ground objects. The technique includes constructing epipolar images and registering them using common terrain- level features to allow direct disparity mapping for the off-terrain objects. After the implementation, the negative effects of occlusion in the off-nadir VHR stereo images are mitigated through direct disparity mapping of the above-ground objects and bypassing the interpolation and normalization steps.

The latest breed of very high resolution (VHR) commercial satellites opens new possibilities for cartographic and remote-sensing applications. In fact, one of the most common applications of remote-sensing images is the extraction of land-cover information for digital image base maps by means of classification techniques. The aim of the study was to compare the potential classification accuracy provided by pan-sharpened orthoimages from both GeoEye-1 and WorldView-2 (WV2) VHR satellites over urban environments. The influence on the supervised classification accuracy was evaluated by means of an object-based statistical analysis regarding three main factors: (i) sensor used; (ii) sets of image object (IO) features used for classification considering spectral, geometry, texture, and elevation features; and (iii) size of training samples to feed the classifier (nearest neighbour (NN)). The new spectral bands of WV2 (Coastal, Yellow, Red Edge, and Near Infrared-2) did not improve the benchmark established from GeoEye-1. The best overall accuracy for GeoEye-1 (close to 89%) was attained by using together spectral and elevation features, whereas the highest overall accuracy for WV2 (83%) was achieved by adding textural features to the previous ones. In the case of buildings classification, the normalized digital surface model computed from light detection and ranging data was the most valuable feature, achieving producer's and user's accuracies close to 95% and 91% for GeoEye-1 and VW2, respectively. Last but not least and regarding the size of the training samples, the rule of ‘the larger the better' was true but, based on statistical analysis, the ideal choice would be variable depending on both each satellite and target class. In short, 20 training IOs per class would be enough if the NN classifier was applied on pan-sharpened orthoimages from both GeoEye-1 and WV2.

The demand for tree height derivation is increasing year by year, especially for large plantation and forest area. The conventional method needs a long time to complete tree measurement for large forest area, especially when using a pole, measuring tape, rangefinder, clinometer, and tree climbing. This study aims to evaluate the height of oil palm tree based on crown diameter by using a multi-rotor Unmanned Aerial Vehicle (UAV). Digital Elevation Model (DEM) and orthophoto were generated by using Agisoft software, while oil palm tree crown diameter was delineated by using seed generation with Quantum Geographic Information System (QGIS) and Seeded Region Growing (SRG) segmentation methods in the System for Automated Geoscientific Analysis (SAGA). The study validates the results between the actual tree height and tree height estimated from UAV. The results showed that the orthophoto was successfully generated with a Ground Sampling Distance (GSD) of 2.95 cm and 129 tree crowns were successfully analyzed. The accuracy of the tree height as compared to the actual measurement was 57.7 cm. In conclusion, UAV images are capable of determining the tree height after going through the correct procedure to help foresters in their daily task.

Raw remotely sensed images contain geometric distortions and cannot be used directly for map-based applications, accurate locational information extraction or geospatial data integration. A geometric correction process must be conducted to minimize the errors related to distortions and achieve the desired location accuracy before further analysis. A considerable number of images might be needed when working over large areas or in temporal domains in which manual geometric correction requires more labor and time. To overcome these problems, new algorithms have been developed to make the geometric correction process autonomous. The Scale Invariant Feature Transform (SIFT) algorithm is an image matching algorithm used in remote sensing applications that has received attention in recent years. In this study, the effects of the incidence angle, surface topography and land cover (LC) characteristics on SIFT-based automated orthorectification were investigated at three different study sites with different topographic conditions and LC characteristics using Pleiades very high resolution (VHR) images acquired at different incidence angles. The results showed that the location accuracy of the orthorectified images increased with lower incidence angle images. More importantly, the topographic characteristics had no observable impacts on the location accuracy of SIFT-based automated orthorectification, and the results showed that Ground Control Points (GCPs) are mainly concentrated in the “Forest” and “Semi Natural Area” LC classes. A multi-thread code was designed to reduce the automated processing time, and the results showed that the process performed 7 to 16 times faster using an automated approach. Analyses performed on various spectral modes of multispectral data showed that the arithmetic data derived from pan-sharpened multispectral images can be used in automated SIFT-based RPC orthorectification.