scholarly journals Agricultural Greenhouses Detection in High-Resolution Satellite Images Based on Convolutional Neural Networks: Comparison of Faster R-CNN, YOLO v3 and SSD

Sensors ◽  
2020 ◽  
Vol 20 (17) ◽  
pp. 4938
Author(s):  
Min Li ◽  
Zhijie Zhang ◽  
Liping Lei ◽  
Xiaofan Wang ◽  
Xudong Guo
Keyword(s):  
High Resolution ◽  
Visual Inspection ◽  
Satellite Images ◽  
High Spatial Resolution ◽  
Fine Tuning ◽  
Single Shot ◽  
Modern Agriculture ◽  
High Resolution Satellite Images ◽  
Independent Test ◽  
Test Sets

Agricultural greenhouses (AGs) are an important facility for the development of modern agriculture. Accurately and effectively detecting AGs is a necessity for the strategic planning of modern agriculture. With the advent of deep learning algorithms, various convolutional neural network (CNN)-based models have been proposed for object detection with high spatial resolution images. In this paper, we conducted a comparative assessment of the three well-established CNN-based models, which are Faster R-CNN, You Look Only Once-v3 (YOLO v3), and Single Shot Multi-Box Detector (SSD) for detecting AGs. The transfer learning and fine-tuning approaches were implemented to train models. Accuracy and efficiency evaluation results show that YOLO v3 achieved the best performance according to the average precision (mAP), frames per second (FPS) metrics and visual inspection. The SSD demonstrated an advantage in detection speed with an FPS twice higher than Faster R-CNN, although their mAP is close on the test set. The trained models were also applied to two independent test sets, which proved that these models have a certain transability and the higher resolution images are significant for accuracy improvement. Our study suggests YOLO v3 with superiorities in both accuracy and computational efficiency can be applied to detect AGs using high-resolution satellite images operationally.

scholarly journals Comparative Research on Deep Learning Approaches for Airplane Detection from Very High-Resolution Satellite Images

2020 ◽  
Vol 12 (3) ◽  
pp. 458 ◽  
Author(s):  
Ugur Alganci ◽  
Mehmet Soydas ◽  
Elif Sertel
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
Object Detection ◽  
Satellite Images ◽  
Training Data ◽  
Object Localization ◽  
Detection Accuracy ◽  
Single Shot ◽  
High Resolution Satellite Images ◽  
Very High

Object detection from satellite images has been a challenging problem for many years. With the development of effective deep learning algorithms and advancement in hardware systems, higher accuracies have been achieved in the detection of various objects from very high-resolution (VHR) satellite images. This article provides a comparative evaluation of the state-of-the-art convolutional neural network (CNN)-based object detection models, which are Faster R-CNN, Single Shot Multi-box Detector (SSD), and You Look Only Once-v3 (YOLO-v3), to cope with the limited number of labeled data and to automatically detect airplanes in VHR satellite images. Data augmentation with rotation, rescaling, and cropping was applied on the test images to artificially increase the number of training data from satellite images. Moreover, a non-maximum suppression algorithm (NMS) was introduced at the end of the SSD and YOLO-v3 flows to get rid of the multiple detection occurrences near each detected object in the overlapping areas. The trained networks were applied to five independent VHR test images that cover airports and their surroundings to evaluate their performance objectively. Accuracy assessment results of the test regions proved that Faster R-CNN architecture provided the highest accuracy according to the F1 scores, average precision (AP) metrics, and visual inspection of the results. The YOLO-v3 ranked as second, with a slightly lower performance but providing a balanced trade-off between accuracy and speed. The SSD provided the lowest detection performance, but it was better in object localization. The results were also evaluated in terms of the object size and detection accuracy manner, which proved that large- and medium-sized airplanes were detected with higher accuracy.

scholarly journals Deep Hybrid Network for Land Cover Semantic Segmentation in High-Spatial Resolution Satellite Images

Information ◽  
2021 ◽  
Vol 12 (6) ◽  
pp. 230
Author(s):  
Sultan Daud Khan ◽  
Louai Alarabi ◽  
Saleh Basalamah
Keyword(s):  
High Resolution ◽  
Land Cover ◽  
Spatial Resolution ◽  
Satellite Images ◽  
High Spatial Resolution ◽  
Multiple Scales ◽  
Semantic Segmentation ◽  
Vital Role ◽  
Hybrid Network ◽  
High Resolution Satellite Images

Land cover semantic segmentation in high-spatial resolution satellite images plays a vital role in efficient management of land resources, smart agriculture, yield estimation and urban planning. With the recent advancement in remote sensing technologies, such as satellites, drones, UAVs, and airborne vehicles, a large number of high-resolution satellite images are readily available. However, these high-resolution satellite images are complex due to increased spatial resolution and data disruption caused by different factors involved in the acquisition process. Due to these challenges, an efficient land-cover semantic segmentation model is difficult to design and develop. In this paper, we develop a hybrid deep learning model that combines the benefits of two deep models, i.e., DenseNet and U-Net. This is carried out to obtain a pixel-wise classification of land cover. The contraction path of U-Net is replaced with DenseNet to extract features of multiple scales, while long-range connections of U-Net concatenate encoder and decoder paths are used to preserve low-level features. We evaluate the proposed hybrid network on a challenging, publicly available benchmark dataset. From the experimental results, we demonstrate that the proposed hybrid network exhibits a state-of-the-art performance and beats other existing models by a considerable margin.

scholarly journals AUTOMATED PANSHARPENING INFORMATION TECHNOLOGY OF SATELLITE IMAGES

2021 ◽  
pp. 123-132
Author(s):  
V. V. Hnatushenko ◽  
V. Yu. Kashtan
Keyword(s):  
Image Processing ◽  
Information Technology ◽  
High Resolution ◽  
Spatial Resolution ◽  
Satellite Images ◽  
High Spatial Resolution ◽  
Image Resolution ◽  
Resolution Image ◽  
Ndvi Index ◽  
High Resolution Satellite Images

Context. Nowadays, information technologies are widely used in digital image processing. The task of joint processing of satellite image obtained by different space systems that have different spatial differences is important. The already known pansharpening methods to improve the quality of the resulting image, there are new scientific problems associated with increasing the requirements for high-resolution image processing and the development of automated technology for processing the satellite data for further thematic analysis. Most spatial resolution techniques result in artifacts. Our work explores the major remote sensing data fusion techniques at pixel level and reviews the concept, principals, limitations and advantages for each technique with the program implementation of research. Objective. The goal of the work is analyze the effectiveness of the traditional pan-sharpening methods like the Brovey, the wavelet-transform, the GIHS, the HCT and the combined pansharpening method for satellite images of high-spatial resolution. Method. In this paper we propose the information technology for pansharpening high spatial resolution images with automation of choosing the best method based on the analysis of quantitative and qualitative evolutions. The method involves the scaling multispectral image to the size of the panchromatic image; using histogram equalization to adjust the primary images by aligning the integral areas of the sections with different brightness; conversion of primary images after the spectral correction on traditional pansharpening methods; analyze the effectiveness of the results obtained for conducts their detailed comparative visual and quantitative evaluation. The technology allows determining the best method of pansharpening by analyzing quantitative metrics: the NDVI index, the RMSE and the ERGAS. The NDVI index for the methods Brovey and HPF indicate color distortion in comparison with the reference data. This is due to the fact that the Brovey and HPF methods are based on the fusion of three channel images and do not include the information contained in the near infrared range. The RMSE and the ERGAS show the superiority of the combined HSVHCT-Wavelet method over the conventional and state-of-art image resolution enhancement techniques of high resolution satellite images. This is achieved, in particular, by preliminary processing of primary images, data processing localized spectral bases, optimized performance information, and the information contained in the infrared image. Results. The software implementing proposed method is developed. The experiments to study the properties of the proposed algorithm are conducted. Experimental evaluation performed on eight-primary satellite images of high spatial resolution obtained WorldView-2 satellite. The experimental results show that a synthesized high spatial resolution image with high information content is achieved with the complex use of fusion methods, which makes it possible to increase the spatial resolution of the original multichannel image without color distortions. Conclusions. The experiments confirmed the effectiveness of the proposed automated information technology for pansharpening high-resolution satellite images with the development of a graphical interface to obtain a new synthesized image. In addition, the proposed technology will effectively carry out further recognition and real-time monitoring infrastructure.

scholarly journals SVA-SSD: saliency visual attention single shot detector for building detection in low contrast high-resolution satellite images

2021 ◽  
Vol 7 ◽  
pp. e772
Author(s):  
Ahmed I. Shahin ◽  
Sultan Almotairi
Keyword(s):  
Deep Learning ◽  
High Resolution ◽  
Visual Attention ◽  
Satellite Images ◽  
Boundary Detection ◽  
Single Shot ◽  
Building Detection ◽  
Desert Environment ◽  
Low Contrast ◽  
High Resolution Satellite Images

Building detection in high-resolution satellite images has received great attention, as it is important to increase the accuracy of urban planning. The building boundary detection in the desert environment is a real challenge due to the nature of low contrast images in the desert environment. The traditional computer vision algorithms for building boundary detection lack scalability, robustness, and accuracy. On the other hand, deep learning detection algorithms have not been applied to such low contrast satellite images. So, there is a real need to employ deep learning algorithms for building detection tasks in low contrast high-resolution images. In this paper, we propose a novel building detection method based on a single-shot multi-box (SSD) detector. We develop the state-of-the-art SSD detection algorithm based on three approaches. First, we propose data-augmentation techniques to overcome the low contrast images’ appearance. Second, we develop the SSD backbone using a novel saliency visual attention mechanism. Moreover, we investigate several pre-trained networks performance and several fusion functions to increase the performance of the SSD backbone. The third approach is based on optimizing the anchor-boxes sizes which are used in the detection stage to increase the performance of the SSD head. During our experiments, we have prepared a new dataset for buildings inside Riyadh City, Saudi Arabia that consists of 3878 buildings. We have compared our proposed approach vs other approaches in the literature. The proposed system has achieved the highest average precision, recall, F1-score, and IOU performance. Our proposed method has achieved a fast average prediction time with the lowest variance for our testing set. Our experimental results are very promising and can be generalized to other object detection tasks in low contrast images.

scholarly journals Remote Sensing Methods for the Retrieval of Inventory and Bioproductivity Parameters of Forests Using High Resolution Satellite Images

2019 ◽  
Vol 75 ◽  
pp. 01003 ◽  
Author(s):  
Egor Dmitriev ◽  
Vladimir Kozoderov ◽  
Sergey Donskoy ◽  
Petr Melnik ◽  
Anton Sokolov
Keyword(s):  
Satellite Images ◽  
High Spatial Resolution ◽  
Texture Features ◽  
Forest Species ◽  
Effective Learning ◽  
Estimated Parameters ◽  
High Resolution Satellite Images ◽  
Automated Processing ◽  
Tver Region ◽  
Remote Sensing Methods

A method for automated processing high spatial resolution satellite images is proposed to retrieve inventory and bioproductivity parameters of forest stands. The method includes effective learning classifiers, inverse modeling, and regression modeling of the estimated parameters. Spectral and texture features are used to classify forest species. The results of test experiments for the selected area of Savvatievskoe forestry (Russia, Tver region) are presented. Accuracy estimates obtained using ground-based measurements demonstrate the effectiveness of using the proposed techniques to automate the process of updating information for the State Forest Inventory program of Russia.

An Approach for Building Rooftop Border Extraction from Very High-Resolution Satellite Images

2021 ◽  
pp. 1-11
Author(s):  
Yasser Mostafa ◽  
Mahmoud Nokrashy O. Ali ◽  
Faten Mostafa ◽  
Mohamed Yousef
Keyword(s):  
High Resolution ◽  
Satellite Images ◽  
High Resolution Satellite Images ◽  
Very High
Sign in / Sign up

Export Citation Format

Share Document