Optimized AI Model Development for On-Board Image Classification in CubeSats Using Birds Satellite Imagery

Identifying vegetation from satellite images is very necessary for studies related to agricultural sector. Enhancing the quality and classification of satellite images is a challenge especially when study areas contain complex vegetation. The study aimed to enhance the image classification based on using extraction tool of the ArcGIS. In the present study, the classification of Landsat satellite images before and after extracting specific areas covering vegetation using the ArcGIS was compared. Two regions in Egypt, one with complex vegetation located at Siwa Oasis and the other one with simple vegetation located at Abu Simbel region, were used in this study. Then, several polygons were used to extract specific areas covering vegetation from the satellite images. Images were subsequently classified using Iso cluster unsupervised classification tool. The classification outcomes were compared between the original images before extraction with images after extraction. The results showed that extraction tool greatly enhanced the quality and classification of the image and it was possible to identify different types of vegetation.

Satellite image classification is an important and challenging task in the modern technological age. Satellites can capture images of danger-prone areas with very little effort. However, the size and number of satellite images are very high when they are rapidly captured from space, and they require a huge amount of memory to store the data. In addition, keeping the satellite images private is another important task for security purposes. On-board, instant, accurate classification of a smaller number of satellite images is a challenging task, which is important to determine the specific condition of an area for instant monitoring. In the proposed hybrid approach, the captured images are kept secure, while the required training of the classification is done separately. Finally, the trained module is encrypted for use by the satellite to perform the on-board classification task. The Brakerski–Fan–Vercauteren (BFV)-based homomorphic encryption of EuroSAT satellite images is applied to store images in a cloud storage, where the privacy of the images can be maintained. Then, the decrypted images are used for training four transfer learning models (YOLOv8, YOLOv12, ResNet34, ResNet101, and a vision transformer classification. The best-trained module is encoded and encrypted again by using homomorphic encryption to limit the module to authorized devices. The encrypted module is decrypted and decoded to recover the trained module, which is used for instant classification of test images. Finally, the performance of the transfer learning models is evaluated from the test results. The vision transformer classifier achieved the highest accuracy of 99.65 % .

The classification of images has attracted significant attention due to its applications in several computer vision tasks, including satellite imaging, image analysis, surveillance, object recognition, and image retrieval. The primary objective of image classification is to provide class labels to images based on their content. The applications of imagery classification and analysis in remote sensing are significant since they are utilized in many sectors, including military and civilian areas. In satellite imagery, the challenge of image classification is heightened due to the rotation of objects inside a view and the typically varied background. This review paper discusses satellite image classification through various deep learning approaches, including its historical background and current approaches. It finds the most appropriate classification techniques for different types of satellite images and discusses the impact of preprocessing methods on classification accuracy. Moreover, a comparative analysis of several studies is given based on different parameters such as research objectives, used datasets, methods/algorithms, limitations, etc. Specific case studies that have significantly contributed to the understanding of satellite image classification are also discussed; further, an overview of challenges and future research directions in this field is also provided.

Remote sensing techniques have been widely used for identification of land use and land cover features. Land information can be easily collected by classification of satellite images in the context of their use. In this paper study area has been classified into three classes i.e. settlement, trees and agricultural by classification of an image which has been enhanced using fusion of two images. The spatial and spectral resolutions of different satellite images provide better information with the aid of initial processing of image and fusion of both images. The satellite images fused together are multispectral IRS-P6 also called Resourcesat-1 satellite, on board LISS-III sensor provide image with spatial resolution of 23.5 m and an IRS-P5 also called Cartosat-1 satellite provides single band panchromatic image with spatial resolution of 2.5 m. Erdas Imagine 9.1 software has been used for image processing, fusion and supervised classification of the images. The Brovery, Multiplicative and Principal Component Analysis (PCA) method have been used for image fusion. The resultant images have been classified using the supervised classification with maximum likelihood parametric rule for information extraction and comparison between them in terms of their accuracy.

This paper discusses the contribution of AI and ML in the information systems of a smart city, particularly being concerned with enhancing the precision of weather forecasts and the effectiveness of emergency responses. Satellite imagery forms part of the complex data sets incorporated in the study, along with historical data regarding emergencies. The datasets were analyzed with the help of AI and ML models, such as LSTM and CNNs. Results show that the AI-based systems performed better than the traditional method, as it accounted for 92% of accuracy in short-range weather forecasting, while the legacy model only accounted for 78%. During extreme events such as heat waves and wildfires, AI models produced more timely and accurate warnings, cutting the response time for emergencies by as much as 25%. The paper also touches on broader implications of AI in relation to its potential and contribution toward the betterment of enhanced urban resilience, sustainability, and public safety. Although there are considerable merits with AI, the issues of data privacy and ethical concerns along with computational overheads pose challenges and drawbacks. Such a research effort is hoped to conclude in hybrid AI models and advanced IoT sensor networks as possibleF futures toward optimizing the smarts for smart city applications.

The robustness and speed of image classification is still a challenging task in satellite image processing. This paper introduces a novel image classification technique that uses the particle filter framework (PFF)-based optimisation technique for satellite image classification. The framework uses a template-matching algorithm, comprising fast marching algorithm (FMA) and level set method (LSM)-based segmentation which assists in creating the initial templates for comparison with other test images. The created templates are trained and used as inputs for the optimisation. The optimisation technique used in this proposed work is multikernel sparse representation (MKSR). The combined execution of FMA, LSM, PFF and MKSR approaches has resulted in a substantial reduction in processing time for various classes in a satellite image which is small when compared with Support Vector Machine (SVM) and Independent Component Discrimination Analysis (ICDA)based image classifications obtained for comparison purposes. This study aims to improve the robustness of image classification based on overall accuracy (OA) and kappa coefficient. The variation of OA with this technique, between different classes of a satellite image, is only10%, whereas that with the SVM and ICDA techniques is more than 50%.

A machine learning-based Support vector machine (SVM) and Extended Local Binary Patterns (ELBP) methods have been used for the classification of satellite images among a set of 24 different classes. This work does not only classify the satellite image class this work is also capable of classifying 24 different class however to identify the features of those other classes like the human face, football, dog, etc. is also simple because these other classes have some exclusive features which can be simply to differentiate hence easy classification. In the case of the satellite image, the major issue is that different satellite images may have different features that make satellite image classification hard. Another issue is that safelight images are normally noise corrupted. The noise patterns of the wireless image are estimated using SVM Classifier, and with those estimated noise patterns removed by SVM algorithm of signal classification. This work first performs segmentation on the input test image to be classified then finds out the local binary patterns using the proposed ELBP method. The Extended LBP is needed because to differentiate the patterns of different satellite images and different other class images cannot be estimated with LBP only. Once extended features obtained SVM classifies the class of the test image. The method used in this work is ELBP-SVM and the Satellite image correct recognition obtain is 94%. The experimental results obtained on MATLAB 2018b and the results found are better than other available work t. classify satellite images.

In this article, hardware and software tools is proposed to process image in satellite image processing systems so that the parameters can be calculated and make image viewable according to user requirements. This is a basic approach to solve real-time problems for water bodies like oceans. The extraction of Water bodies is difficult because of mountain and building shadow. There are three water indices for water bodies extraction namely, Normalized Difference Water Index (NDWI), Modified Normalized Difference Water Index (MNDWI) and Automated Water Extraction Index (AWEI) that extract water in real-time with onboard image processing system using FPGA. By selecting any input image there are given three options of NDWI, MNDWI and AWEI. When any one option is selected then the output is obtained according to selected indices. The proposed system of onboard real-time image processing using hardware software combination reduces total time to procure satellite image and extraction of water bodies.

Abstract. Now that the agricultural facilities are being increase owing to development of technology and diversification of agriculture and the ratio of garden crops that are imported a lot and the crops cultivated in facilities are raised in Korea, the number of vinyl greenhouses is tending upward. So, it is important to grasp the distribution of vinyl greenhouses as much as that of rice fields, dry fields and orchards, but it is difficult to collect the information of wide areas economically and correctly. Remote sensing using satellite imagery is able to obtain data of wide area at the same time, quickly and cost-effectively collect, monitor and analyze information from every object on earth. In this study, in order to analyze the utilization of satellite imagery at detection of agricultural facility, image classification was performed about the agricultural facility, vinyl greenhouse using Formosat-2 satellite imagery. The training set of sea, vegetation, building, bare ground and vinyl greenhouse was set to monitor the agricultural facilities of the object area and the training set for the vinyl greenhouses that are main monitoring object was classified and set again into 3 types according the spectral characteristics. The image classification using 4 kinds of supervise classification methods applied by the same training set were carried out to grasp the image classification method which is effective for monitoring agricultural facilities. And, in order to minimize the misclassification appeared in the classification using the spectral information, the accuracy of classification was intended to be raised by adding texture information. The results of classification were analyzed regarding the accuracy comparing with that of naked-eyed detection. As the results of classification, the method of Mahalanobis distance was shown as more efficient than other methods and the accuracy of classification was higher when adding texture information. Hence the more effective monitoring of agricultural facilities is expected to be available if the characteristics such as texture information including satellite images or spatial pattern are studied in detail.

Recent years witness a trend of applying large-scale distributed deep learning algorithms (HPC AI) in both business and scientific computing areas, whose goal is to speed up the training time to achieve a state-of-the-art quality. The HPC AI benchmarks accelerate the process. Unfortunately, benchmarking HPC AI systems at scale raises serious challenges. This paper presents a comprehensive HPC AI benchmarking methodology that achieves equivalence, representativeness, repeatability, and affordability. Among the nineteen AI workloads of AIBench Training–by far the most comprehensive AI benchmarks suite, we choose two representative and repeatable AI workloads in terms of both AI model and micro-architectural characteristics. The selected HPC AI benchmarks include both business and scientific computing: Image Classification and Extreme Weather Analytics. Finally, we propose three high levels of benchmarking and the corresponding rules to assure equivalence. To rank the performance of HPC AI systems, we present a new metric named Valid FLOPS, emphasizing both throughput performance and target quality. The evaluations show our methodology, benchmarks, and metrics can measure and rank the HPC AI systems in a simple, affordable and repeatable way. The specification, source code, datasets, and HPC AI500 ranking numbers are publicly available from https://www.benchcouncil.org/aibench/hpcai500/index.html.

Deep learning methods have been successfully applied to remote-sensing problems for several years. Among these methods, CNN-based models have high accuracy in solving the land classification problem using satellite or aerial images. Although these models have high accuracy, this generally comes with large memory size requirements. However, it is desirable to have small-sized models for applications, such as the ones implemented on unmanned aerial vehicles, with low memory space. Unfortunately, small-sized CNN models do not provide as high accuracy as with their large-sized versions. In this study, we propose a novel method to improve the accuracy of CNN models, especially the ones with small size, by injecting traditional features into them. To test the effectiveness of the proposed method, we applied it to the CNN models SqueezeNet, MobileNetV2, ShuffleNetV2, VGG16 and ResNet50V2 having size 0.5 MB to 528 MB. We used the sample mean, grey-level co-occurrence matrix features, Hu moments, local binary patterns, histogram of oriented gradients and colour invariants as traditional features for injection. We tested the proposed method on the EuroSAT dataset to perform land classification. Our experimental results show that the proposed method significantly improves the land classification accuracy especially when applied to small-sized CNN models.

Remote sensing technology has rendered lots of information in agriculture. It has usually been used to monitor paddy growing ecosystems in the past few decades. However, there are uncertainties in data fusion techniques which can be resolved in image classification on paddy rice. In this study, a series of learning concepts integrated by a probability progress Fuzzy Dempster-Shafer (FDS) analysis is presented to upgrade various models and different types of image data which is the goal of this study. More specifically, the study utilized the FDS to generate a series of probability models in the classification of the system. In addition, Logistic Regression (LR), Support Vector Machine (SVM), and Neural Network (NN) approaches are employed into the developed FDS system. Furthermore, two different image types are Satellite Image and Aerial Photo used as the analysis material. The overall classification accuracy has been improved to 97.27%, and the kappa value is 0.93. The overall accuracy of the paddy field image classification for a multi-period of mid-scale satellite images is between 85% and 90%. The overall accuracy of the classification using multi-spectral numerical aerial photos can be between 91% and 95%. The FDS improves the accuracy of the above image classification results.

Remote sensing is one of the very important parts in the advance image processing which is used to acquiring satellite image to know about geo-spatial information. Remote sensing is widely used to monitor different resources available on earth surface, out of which the land used area monitoring is one of very important part. There are many techniques and methods are proposed for satellite image classification based on different theme. Here, in this paper theme of classification is land used and land area cover mapping using LISS-III satellite image. LISS-III satellite image have been classified in different area covered by water, forest, mangroves and developments by selecting the pixel based classification. Here multiple linear regressions is used on initial training data set, after evaluation the new features data set is applied to artificial neural network to check the impact of best training data set on the classification accuracy. The accuracy of classification algorithm is calculated using confusion matrix and Kappa coefficient. It is observed with help of confusion matrix and Kappa coefficient that the accuracy of ANN classifier without evaluated training data set is 90.19% and Kappa Coefficient is 0.8533 and when training data set evaluated with the help of multiple Linear regression then ANN accuracy is 98.74% and the Kappa Coefficient is 0.9766 which is improved and very good. So with the proposed method classification accuracy of ANN classifier is improvement for classification of LISS-III satellite image.

Deep learning (DL) has shown outstanding performances in many fields, including remote sensing (RS). DL is turning into an essential tool for the RS research community. Recently, many cloud platforms have been developed to provide access to large-scale computing capacity, consequently permitting the usage of DL architectures as a service. However, this opened the door to new challenges associated with the privacy and security of data. The RS data used to train the DL algorithms have several privacy requirements. Some of them need a high level of confidentiality, such as satellite images related to public security with high spatial resolutions. Moreover, satellite images are usually protected by copyright, and the owner may strictly refuse to share them. Therefore, privacy-preserving deep learning (PPDL) techniques are a possible solution to this problem. PPDL enables training DL on encrypted data without revealing the original plaintext. This study proposes a hybrid PPDL approach for object classification for very-high-resolution satellite images. The proposed encryption scheme combines Paillier homomorphic encryption (PHE) and somewhat homomorphic encryption (SHE). This combination aims to enhance the encryption of satellite images while ensuring a good runtime and high object classification accuracy. The method proposed to encrypt images is maintained through the public keys of PHE and SHE. Experiments were conducted on real-world high-resolution satellite images acquired using the SPOT6 and SPOT7 satellites. Four different CNN architectures were considered, namely ResNet50, InceptionV3, DenseNet169, and MobileNetV2. The results showed that the loss in classification accuracy after applying the proposed encryption algorithm ranges from 2% to 3.5%, with the best validation accuracy on the encrypted dataset reaching 92%.

Abstract: Satellite image analysis plays a crucial role in fields such as environmental monitoring, urban planning, agriculture, and disaster management. This project presents a machine learning-based methodology for the automated segmentation and classification of objects in satellite images. The proposed system employs a two-step algorithm: (1) K-Means clustering for unsupervised segmentation of satellite images into meaningful clusters, and (2) Support Vector Machine (SVM) for supervised classification of the segmented regions into predefined categories such as land, water, and vegetation. A Flask-based web application is developed to provide a userfriendly interface for uploading satellite images and visualizing classified results. The backend is supported by a structured SQL database to manage image metadata and classification outputs efficiently. The system is designed to handle large datasets, ensuring robustness and scalability. Experimental results on benchmark datasets demonstrate high accuracy in object detection and classification, highlighting the system's potential to support real-world decision-making in environmental and infrastructural domains.