Due to the advancements in digital image processing and multimedia devices, the digital image can be easily tampered and presented as evidence in judicial courts, print media, social media, and for ...insurance claims. The most commonly used image tampering technique is the copy-move forgery (CMF) technique, where the region from the original image is copied and pasted in some other part of the same image to manipulate the original image content. The CMFD techniques may not provide robust performance after various post-processing attacks and multiple forged regions within the images. This article introduces a robust CMF detection technique to mitigate the aforementioned problems. The proposed CMF detection technique utilizes a fusion of speeded up robust features (SURF) and binary robust invariant scalable keypoints (BRISK) descriptors for CMF detection. The SURF features are robust against different post-processing attacks such as rotation, blurring, and additive noise. However, the BRISK features are considered as robust in the detection of the scale-invariant forged regions as well as poorly localized keypoints of the objects within the forged image. The fused features are matched using hamming distance and second nearest neighbor. The matched features grouped into clusters by applying density-based spatial clustering of applications with noise clustering algorithm. The random sample consensus technique is applied to the clusters to remove the remaining false matches. After some post-processing, the forged regions are detected and localized. The performance of the proposed CMFD technique is assessed using three standard datasets (i.e., CoMoFoD, MICC-F220, and MICC-F2000). The proposed technique surpasses the state-of-the-art techniques used for CMF detection in terms of true and false detection rates.
InSAR (Interferometric Synthetic Aperture Radar) is widely recognized as a crucial remote sensing tool for monitoring various geological disasters because it provides all-day and all-weather ...monitoring. Nevertheless, the current interpretation methods for InSAR heavily depend on the interpreter’s experience, which hinders efficiency and fails to meet the requirements for the timely detection of geologic hazards. Furthermore, the results obtained through current InSAR processing carry inherent noise interference, further complicating the interpretation process. To address those issues, this paper proposes an approach that enables automatic and rapid identification of deformation zones. The proposed method leverages IPTA (Interferometric Point Target Analysis) technology for SAR data processing. It combines the power of HNSW (Hierarchical Navigable Small Word) and DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithms to cluster deformation results. Compared with traditional methods, the computational efficiency of the proposed method is improved by 11.26 times, and spatial noise is suppressed. Additionally, the clustering results are fused with slope units determined using DEM (Digital Elevation Model), which facilitates the automatic identification of slopes experiencing deformation. The experimental verification in the western mountainous area of Beijing has identified 716 hidden danger areas, and this method is superior to the traditional technology in speed and automation.
A density-based spatial clustering of applications with noise (DBSCAN) and three distances (TD) integrated Wi-Fi positioning algorithm was proposed, aiming to enhance the positioning accuracy and ...stability of fingerprinting by the dynamic selection of signal-domain distance to obtain reliable nearest reference points (RPs). Two stages were included in this algorithm. One was the offline stage, where the offline fingerprint database was constructed and the other was the online positioning stage. Three distances (Euclidean distance, Manhattan distance, and cosine distance), DBSCAN, and high-resolution distance selection principle were combined to obtain more reliable nearest RPs and optimal signal-domain distance in the online stage. Fused distance, the fusion of position-domain and signal-domain distances, was applied for DBSCAN to generate the clustering results, considering both the spatial structure and signal strength of RPs. Based on the principle that the higher resolution the distance, the more clusters will be obtained, the high-resolution distance was used to compute positioning results. The weighted K-nearest neighbor (WKNN) considering signal-domain distance selection was used to estimate positions. Two scenarios were selected as test areas; a complex-layout room (Scenario A) for post-graduates and a typical large indoor environment (Scenario B) covering 3200 m2. In both Scenarios A and B, compared with support vector machine (SVM), Gaussian process regression (GPR) and rank algorithms, the improvement rates of positioning accuracy and stability of the proposed algorithm were up to 60.44 and 60.93%, respectively. Experimental results show that the proposed algorithm has a better positioning performance in complex and large indoor environments.
Global navigation satellite system (GNSS) vehicle trajectory data play an important role in obtaining timely urban road information. However, most models cannot effectively extract road information ...from low-frequency trajectory data. In this study, we aimed to accurately extract urban road network intersections and central locations from low-frequency GNSS trajectory data, and we developed a method for accurate road intersection identification based on filtered trajectory sequences and multiple clustering algorithms. Our approach was founded on the following principles. (1) We put in place a rigorous filtering rule to account for the offset characteristics of low-frequency trajectory data. (2) To overcome the low density and weak connection features of vehicle turning points, we adopted the CDC clustering algorithm. (3) By combining the projection features of orientation values in 2D coordinates, a mean solving method based on the DBSCAN algorithm was devised to obtain intersection center coordinates with greater accuracy. Our method could effectively identify urban road intersections and determine the center position and more effectively apply low-frequency trajectory data. Compared with remote sensing images, the intersection identification accuracy was 96.4%, the recall rate was 89.6%, and the F-value was 92.88% for our method; the intersection center position’s root mean square error (RMSE) was 10.39 m, which was 14.9% higher than that of the mean value method.
The traditional annotation-based medical image retrieval faces a problem with competence and precision with the extensive medical image databases. Broad research has been undertaken on Medical image ...retrieval (MIR) using local, global features of each image, and machine learning algorithms with reliable descriptors have shown the significant improvement of these systems. The proposed method is implemented with a novel approach to address the semantic gap and form efficient texture and shape features clusters. The texture and shape feature vectors are constructed using a novel Relative directional edge binary patterns (RDEBP) and complex Zernike moments. RDEBPs are used to extract the texture features of an image. For every defined square matrix of size 5 × 5, 4 RDEBP patterns are extracted, rich in providing the texture information of an object in the image. The binary patterns are calculated by considering the center pixel’s neighbourhood and relations between neighbour pixels. The complex Zernike moments (ZM) give the shape properties of the object involved in the image. Combining these two features is effectively clustered using the Density-based spatial clustering of applications with noise (DBSCAN) algorithm. Finally, images are retrieved from the closest cluster using the d1-similarity metric concerning the query image. Therefore, the searching time for a query image from the specified cluster is reduced compared to the traditional Content-based image retrieval (CBIR), reflecting excellent response time and retrieval accuracy. Experiments on two databases were performed and confirmed the effectiveness of the proposed work over other state-of-the-art methods. The outcomes of the suggested method are more than 2 to 5% better when compared to the average values produced by other methods.
Perimeter intrusion detection systems (PIDS) play a crucial role in safeguarding critical infrastructures from unauthorized access and potential security breaches. Security is the main concern ...everywhere in the world. There are already many PIDS available, but the PID systems are still lacking in terms of probability of detection, false intrusion, and the activity recognition of intrusion. To solve the above problem, we designed a prototype for PIDS using a DHT22 temperature and humidity sensor, vibration sensor SW- 420 Module Pinout, Mini PIR motion sensor, and Arduino UNO. After collecting the data from above mentioned sensors we applied machine learning algorithms DBSCAN to cluster the data points and K-NN classification to classify those clusters in one-dimensional data, but the results were not much satisfying. From there we got the motivation to improve the algorithm and applied it to two-dimensional data. The existing DBSCAN is not efficient due to its high complexity and the varying densities. To overcome these issues in this algorithm, we have improved the existing DBSCAN to ST-DBSCAN where we have used the estimation for the epsilon value and used the Manatton distance formula to find out the distance between points which produces 94.9853% accuracy on our dataset. Another contribution of the proposed work is that we have developed our own dataset named STPID-dataset, captured from security cameras installed in various locations which can be used by future researchers.
To address the energy crisis and the challenge of global climate change, it has become a consensus among countries to vigorously develop renewable energy sources, and wind energy, as a clean, ...efficient, and nonpolluting renewable energy source, is being promoted and generated in an increasing number of offshore wind turbine (OWT) arrays worldwide. However, accurate and complete offshore wind turbine datasets are crucial for ensuring the safety of marine navigation, marine ecological, and environmental protection, and the effective evaluation and optimization of offshore wind farms. However, most previous studies focused on OWT information extraction using a single multispectral or SAR image dataset, failing to combine the respective advantages of multispectral and SAR imagery. Moreover, accurate land boundary data are needed to mask the land before extracting OWTs, which is inconvenient to perform. In view of the shortcomings of previous studies, the advantages of multispectral and radar satellite image data are fully exploited, and offshore China is selected as the study area. According to the spatial location characteristics of OWTs, a new extraction algorithm for OWTs, the double-loop cooperative detection algorithm, is designed. At the end of 2022, a total of 5986 OWTs were detected in Chinese waters, with an extraction precision of 99.93%, a recall rate of 99.38%, and a comprehensive evaluation index value of 99.65%. The advantages of this algorithm are that it is fast, concise, and effective, thus providing a new approach for extracting OWTs.
In metagenomics, the separation of nucleotide sequences belonging to an individual or closely matched populations is termed binning. Binning helps the evaluation of underlying microbial population ...structure as well as the recovery of individual genomes from a sample of uncultivable microbial organisms. Both supervised and unsupervised learning methods have been employed in binning; however, characterizing a metagenomic sample containing multiple strains remains a significant challenge. In this study, we designed and implemented a new workflow, Coverage and composition based binning of Metagenomes (CoMet), for binning contigs in a single metagenomic sample. CoMet utilizes coverage values and the compositional features of metagenomic contigs. The binning strategy in CoMet includes the initial grouping of contigs in guanine-cytosine (GC) content-coverage space and refinement of bins in tetranucleotide frequencies space in a purely unsupervised manner. With CoMet, the clustering algorithm DBSCAN is employed for binning contigs. The performances of CoMet were compared against four existing approaches for binning a single metagenomic sample, including MaxBin, Metawatt, MyCC (default) and MyCC (coverage) using multiple datasets including a sample comprised of multiple strains.
Binning methods based on both compositional features and coverages of contigs had higher performances than the method which is based only on compositional features of contigs. CoMet yielded higher or comparable precision in comparison to the existing binning methods on benchmark datasets of varying complexities. MyCC (coverage) had the highest ranking score in F1-score. However, the performances of CoMet were higher than MyCC (coverage) on the dataset containing multiple strains. Furthermore, CoMet recovered contigs of more species and was 18 - 39% higher in precision than the compared existing methods in discriminating species from the sample of multiple strains. CoMet resulted in higher precision than MyCC (default) and MyCC (coverage) on a real metagenome.
The approach proposed with CoMet for binning contigs, improves the precision of binning while characterizing more species in a single metagenomic sample and in a sample containing multiple strains. The F1-scores obtained from different binning strategies vary with different datasets; however, CoMet yields the highest F1-score with a sample comprised of multiple strains.
In this paper, a parking slot detection algorithm based on a bird's eye view is proposed. A density-based spatial clustering of applications with noise (DBSCAN) clustering algorithm and template ...matching algorithm are fused to detect parking slots in a bird's eye view. Progressive probabilistic Hough line detection and an improved DBSCAN clustering algorithm is developed to locate the sidelines of parking slots. Then, template matching is provided to locate and classify the "T shape" and "L shape" marking points more accurately. Finally, the marking points and sidelines of parking slots are integrated to complete the parking slot detection. The recall rate and precision rate of experimental results are 74.4% and 92.0%.