Search results

Extracting suitable features to represent an image based on its content is a very tedious task. Especially in remote sensing we have high-resolution images with a variety of objects on the Earth's surface. Mahalanobis distance metric is used to measure the similarity between query and database images. The low distance obtained image is indexed at the top as high relevant information to the query.

This paper aims to develop an automatic feature extraction system for remote sensing image data. Haralick texture features based on Contourlet transform are fused with statistical features extracted from the QuadTree (QT) decomposition are developed as feature set to represent the input data. The extracted features will retrieve similar images from the large image datasets using an image-based query through the web-based user interface.

The developed retrieval system performance has been analyzed using precision and recall and F1 score. The proposed feature vector gives better performance with 0.69 precision for the top 50 relevant retrieved results over other existing multiscale-based feature extraction methods.

The main contribution of this paper is developing a texture feature vector in a multiscale domain by combining the Haralick texture properties in the Contourlet domain and Statistical features using QT decomposition. The features required to represent the image is 207 which is very less dimension compare to other texture methods. The performance shows superior than the other state of art methods.

Technology acceptance is a measure of that technology’s usefulness. Oil palm is one of the biggest contributors to Indonesia’s revenues, thus fueling its economy. Using remote sensing would allow a plantation to monitor and forecast its production and the amount of fertilizer used. This review aims to provide a policy recommendation in the form of a strategy to improve the added value of Indonesia’s oil palm and support the government in increasing oil palm production. This recommendation needs to be formulated by determining the users’ acceptance of remote sensing technology (state-owned plantations, private plantation companies and smallholder plantations).

This review’s methodology used sentiment analysis through text mining (bag of words model). The study’s primary data were from focus group discussions (FGDs), questionnaires, observations on participants, audio-visual documentation and focused discussions based on group category. The results of interviews and FGDs were transcribed into text and analyzed to 1) find words that can represent the content of the document; 2) classify and determine the frequency (word cloud); and finally 3) analyze the sentiment.

The result showed that private plantation companies and state-owned plantations had extremely high positive sentiments toward using remote sensing in their oil palm plantations, whereas smallholders had a 60% resistance. However, there is still a possibility for this technology’s adoption by smallholders, provided it is free and easily applied.

Basically, technology is applied to make work easier. However, not everyone is tech-savvy, especially the older generations. One dimension of technology acceptance is user/customer retention. New technology would not be immediately accepted, but there would be user perceptions about its uses and ease. At first, people might be reluctant to accept a new technology due to the perception that it is useless and difficult. Technology acceptance is the gauge of how useful technology is in making work easier compared to conventional ways.

Therefore, technology acceptance needs to be improved among smallholders by intensively socializing the policies, and through dissemination and dedication by academics and the government.

The social implications of using technology are reducing the workforce, but the company will be more profitable and efficient.

Remote sensing is one of the topics that people have not taken up in a large way, especially sentiment analysis. Acceptance of technology that utilizes remote sensing for plantations is very useful and efficient. In the end, company profits can be allocated more toward empowering the community and the environment.

The purpose of this paper is to acquaint a wide audience of readers with some of the unique remote sensing and navigation capabilities of animals.

Biomimetic comparison of remote sensors evolved by animals and sensors designed by man. The study and comparison includes thermal infrared sensors used by snakes, echolocation used by bats and dolphins, and navigation methods used by birds. Countermeasures used by prey to avoid capture are also considered.

Some animals have remote sensing and navigation capabilities that are considerably more efficient than those provided by the human body or designed by man.

Sensor designers may be encouraged to use the biometic approach in the design of new sensors.

The paper provides a better understanding of animal behaviour, especially their unique abilities to remotely sense, echolocate and navigate with high accuracy over considerable distances.

The paper presents a comparison of remote sensors used by animals with those developed by humans. Remote sensor designers can learn to improve their sensor designs by studying animal sensors within a biomimetic framework.

The purpose of this paper is to analyze the characteristics of spatio-temporal dynamics and the evolution of land use change is essential for understanding and assessing the status and transition of ecosystems. Such analysis, when applied to Horqin sandy land, can also provide basic information for appropriate decision-making.

By integrating long time series Landsat imageries and geographic information system (GIS) technology, this paper explored the spatio-temporal dynamics and evolution-induced land use change of the largest sandy land in China from 1983 to 2016. Accurate and consistent land use information and land use change information was first extracted by using the maximum likelihood classifier and the post-classification change detection method, respectively. The spatio-temporal dynamics and evolution were then analyzed using three kinds of index models: the dynamic degree model to analyze the change of regional land resources, the dynamic change transfer matrix and flow direction rate to analyze the change direction, and the barycenter transfer model to analyze the spatial pattern of land use change.

The results indicated that land use in Horqin sandy land during the study period changed dramatically. Vegetation and sandy land showed fluctuating changes, cropland and construction land steadily increased, water body decreased continuously, and the spatial distribution patterns of land use were generally unbalanced. Vegetation, sandy land and cropland were transferred frequently. The amount of vegetation loss was the largest. Water body loss was 473.6 km², which accounted for 41.7 per cent of the total water body. The loss amount of construction land was only 1.0 km². Considerable differences were noted in the rate of gravity center migration among the land use types in different periods, and the overall rate of construction land migration was the smallest. Moreover, the gravity center migration rates of the water body and sandy land were relatively high and were related to the fragile ecological environment of Horqin sandy land.

The results not only confirmed the applicability and effectiveness of the combined method of remote sensing and GIS technology but also revealed notable spatio-temporal dynamics and evolution-induced land use change throughout the different time periods (1983-1990, 1990-2000, 2000-2010, 2010-2014, 2014-2016 and 1983-2016).

The paper aims to tackle the classification of Remote Sensing Images (RSIs), which presents a significant challenge for computer algorithms due to the inherent characteristics of clustered ground objects and noisy backgrounds. Recent research typically leverages larger volume models to achieve advanced performance. However, the operating environments of remote sensing commonly cannot provide unconstrained computational and storage resources. It requires lightweight algorithms with exceptional generalization capabilities.

This study introduces an efficient knowledge distillation (KD) method to build a lightweight yet precise convolutional neural network (CNN) classifier. This method also aims to substantially decrease the training time expenses commonly linked with traditional KD techniques. This approach entails extensive alterations to both the model training framework and the distillation process, each tailored to the unique characteristics of RSIs. In particular, this study establishes a robust ensemble teacher by independently training two CNN models using a customized, efficient training algorithm. Following this, this study modifies a KD loss function to mitigate the suppression of non-target category predictions, which are essential for capturing the inter- and intra-similarity of RSIs.

This study validated the student model, termed KD-enhanced network (KDE-Net), obtained through the KD process on three benchmark RSI data sets. The KDE-Net surpasses 42 other state-of-the-art methods in the literature published from 2020 to 2023. Compared to the top-ranked method’s performance on the challenging NWPU45 data set, KDE-Net demonstrated a noticeable 0.4% increase in overall accuracy with a significant 88% reduction in parameters. Meanwhile, this study’s reformed KD framework significantly enhances the knowledge transfer speed by at least three times.

This study illustrates that the logit-based KD technique can effectively develop lightweight CNN classifiers for RSI classification without substantial sacrifices in computation and storage costs. Compared to neural architecture search or other methods aiming to provide lightweight solutions, this study’s KDE-Net, based on the inherent characteristics of RSIs, is currently more efficient in constructing accurate yet lightweight classifiers for RSI classification.

It is in the interest of any gas company to maintain the value of its pipelines and to protect them effectively against damage caused by third parties. Aims to address this issue.

As a result of global progress in high‐resolution remote sensing and image processing technology, it is now possible to design natural gas pipeline monitoring systems with remote sensors and context‐oriented image processing software.

Recent developments in UAV technology show that UAVs provide the appropriate platforms for a remote sensing‐based inspection system: appropriate small and medium size UAV have been developed, their operation is technically feasible in an controlled as well as in uncontrolled airspace.

The data and information processing system still has to be developed to an operational standard. A total operational system consisting of UAV platform, sensors, data processing and alarm detection has to be demonstrated in a complete mission. The certification and operation standards for a safe and efficient operation of UAVs do not yet exist.

Two different scenarios for a UAV‐based gas pipeline monitoring system are discussed.

Satellite and airborne images are increasingly used at different stages of disaster management, especially in the detection of infrastructure damage. Although semi- or full automatic techniques to detect damage have been proposed, they have not been used in emergency situations. Damage maps produced by international organisations are still based on visual interpretation of images, which is time- and labour-consuming. The purpose of this paper is to investigate how an automatic mapping of damage can be helpful for a first and rapid assessment of building damage.

The study area is located in Port-au-Prince (Haiti) stricken by an earthquake in January 2010. To detect building damage, the paper uses optical images (15 cm of spatial resolution) coupled with height data (LiDAR, 1 m of spatial resolution). By undertaking an automatic object-oriented classification, the paper identifies three categories of building damages: intact buildings, collapsed buildings and debris.

Data processing for the study area covering 11 km2 took about 15 hours. The accuracy of the classification varies from 70 to 79 per cent depending to the methods of assessment. Causes of errors are numerous: limited spectral information of the optical images, resolution difference between the two data, high density of buildings but most importantly, certain types of building collapses could not be detected by vertically taken images (the case of data in this study).

The automatic damage mapping developed in this paper proves to be reliable and could be used in emergency situations. It could also be combined with manual visual interpretation to accelerate the planning of humanitarian rescues and reconstruction.

The purpose of this paper is to show that satellite data applicability for landslides studies is given concentration in tropical regions, which have two limitations; regular cloud cover and thick vegetation.

Landslide studies have three categories: mapping, zonation, and monitoring. High spatial resolution images are convenient for mapping. Since the slope and slope materials are the dominant parameters for slide potential, a high resolution DEM produced from the above data with classification of multispectral data will be vital for zonation. Weather‐free and penetration are advantages that make radar images essential for monitoring.

A composition of satellite data with support of aerial photography, with its high spatial resolution, will give an excellent spatial database for these studies.

Satellite remote sensing data are applicable for landslides studies in non‐accessible mountainous tropical regions.

The purpose of this paper is to present a Differential Immune Clone Clustering Algorithm (DICCA) to solve image segmentation.

DICCA combines immune clone selection and differential evolution, and two populations are used in the evolutionary process. Clone reproduction and selection, differential mutation, crossover and selection are adopted to evolve two populations, which can increase population diversity and avoid local optimum. After extracting the texture features of an image and encoding them with real numbers, DICCA is used to partition these features, and the final segmentation result is obtained.

This approach is applied to segment all sorts of images into homogeneous regions, including artificial synthetic texture images, natural images and remote sensing images, and the experimental results show the effectiveness of the proposed algorithm.

The method presented in this paper represents a new approach to solving clustering problems. The novel method applies the idea two populations are used in the evolutionary process. The proposed clustering algorithm is shown to be effective in solving image segmentation.

The purpose of this paper is to improve the retrieval results of hyperspectral image by integrating both spectral and textural features. For this purpose, an improved multiscale opponent representation for hyperspectral texture is proposed to represent the spatial information of the hyperspectral scene.

In the presented approach, end-member signatures are extracted as spectral features by means of the widely used end-member induction algorithm N-FINDR, and the improved multiscale opponent representation is extracted from the first three principal components of the hyperspectral data based on Gabor filters. Then, the combination similarity between query image and other images in the database is calculated, and the first k more similar images are returned in descending order of the combination similarity.

Some experiments are calculated using the airborne hyperspectral data of Washington DC Mall. According to the experimental results, the proposed method improves the retrieval results, especially for image categories that have regular textural structures.

The paper presents an effective retrieval method for hyperspectral images.