Oriented FAST And Rotated BRIEF Research Articles

Multi-channel and multi-featured extended orb with gabor filter and non-maximum suppression

This research paper presents an enhanced approach to feature extraction using the Oriented FAST and Rotated BRIEF (ORB) algorithm (Rublee et al., 2014). The proposed method leverages the power of Gabor filters (Mehrotra et al., 1992) in combination with Non-Maximum Suppression (Neuback and Van Gool, 2006) to improve the robustness and efficiency of feature detection in computer vision applications. The process begins with the acquisition of an RGB image, which is then transformed into seven single-channel images representing different color and intensity aspects: red, green, blue, hue, saturation, value, and grayscale. Each single-channel image is independently subjected to Gabor filtering, resulting in seven Gabor-filtered images. These images capture distinct texture and frequency information, enhancing the discriminative power of subsequent feature extraction. Subsequently, the Oriented FAST and Rotated BRIEF (ORB) algorithm is applied to each of the seven Gabor-filtered images to extract key points and descriptors. This step yields a comprehensive set of keypoints (Mallick et al., 2015) and descriptors, capturing rich local feature information across multiple image channels. To further refine the extracted features and eliminate redundant keypoints, Non-Maximum Suppression is employed independently on each single-channel image. This process effectively filters out overlapped and false keypoints, ensuring the selection of only the most salient features for downstream tasks. Experimental results demonstrate the efficacy of the proposed approach in improving feature detection performance compared to traditional methods. The combination of Gabor filtering and Non-Maximum Suppression enhances feature discriminability, robustness to noise, and resistance to image transformations, making it well-suited for various computer vision applications, including object recognition, image matching, and scene understanding.

Matching UAV-Based Simulated High-Resolution SAR and Real SAR Images

Abstract. Our experiment focuses on generating simulated high-resolution (HR) Synthetic Aperture Radar (SAR) images from the photogrammetric 3D model derived from Unmanned Aerial Vehicle (UAV) imagery. The goal is to match these simulated images with real SAR data of complex scenes containing vegetation, buildings, roads, and the construction of receiving antennas. Simulated SAR reflectivity map was based on ray tracing techniques.Two feature matching algorithms, namely Scale-Invariant Feature Transform (SIFT) and Oriented FAST and Rotated BRIEF (ORB) were employed for co-registration of the simulated to the real SAR images. The effectiveness of these algorithms is evaluated by their matching rates. The experiment results of the matching process highlight the superior performance of ORB over SIFT, attributed to its robustness against rotation variations and noise. ORB emerges as a versatile choice for high-resolution real and simulated SAR registration tasks.

Image quality evaluation: evaluation of the image quality of actual images by using machine learning models

Evaluating image features is a significant step in image processing in applications like number plate detection, vehicle tracking and many image processing-based applications. Image processing-based applications need accurate parts to get the best outcomes. Feature detection is done based on various feature detection techniques. The proposed system aims to get the best feature detector based on the input images by evaluating the image features. For assessing the image features, the proposed system worked on various descriptors like oriented FAST and rotated brief (ORB), learned arrangements of three patch codes (LATCH), binary robust independent elementary features (BRIEF), and binary robust invariant scalable keypoints (BRISK) to extract and evaluate the features using K-nearest neighbor (KNN)-matching and retrieve the inliers of the matching. Each descriptor produces different matching features and inliers; with the matchings and inliers, the inlier ratio calculates to show the analysis. To increase performance, we also examine adding depth information to descriptors.

Visual Odometry Based on Improved Oriented Features from Accelerated Segment Test and Rotated Binary Robust Independent Elementary Features

To address the problem of system instability during vehicle low-speed driving, we propose improving the visual odometer using ORB (Oriented FAST and Rotated BRIEF) features. The homogeneity of ORB features leads to poor corner point properties of some feature points. When the environmental texture lacks richness, it leads to poor matching performance and low matching accuracy of the feature points. We solve the problem of the corner point properties of feature points using weight calculation for regions with different textures. When the vehicle speed is too low, the continuous frames captured by the camera will overlap significantly, causing large fluctuations in the system error. We use motion model estimation to solve this problem. Meanwhile, experimental validation using the KITTI dataset achieves good results.

Combining bag of visual words-based features with CNN in image classification

Abstract Although traditional image classification techniques are often used in authentic ways, they have several drawbacks, such as unsatisfactory results, poor classification accuracy, and a lack of flexibility. In this study, we introduce a combination of convolutional neural network (CNN) and support vector machine (SVM), along with a modified bag of visual words (BoVW)-based image classification model. BoVW uses scale-invariant feature transform (SIFT) and Oriented Fast and Rotated BRIEF (ORB) descriptors; as a consequence, the SIFT–ORB–BoVW model developed contains highly discriminating features, which enhance the performance of the classifier. To identify appropriate images and overcome challenges, we have also explored the possibility of utilizing a fuzzy Bag of Visual Words (BoVW) approach. This study also discusses using CNNs/SVM to improve the proposed feature extractor’s ability to learn more relevant visual vocabulary from the image. The proposed technique was compared with classic BoVW. The experimental results proved the significant enhancement of the proposed technique in terms of performance and accuracy over state-of-the-art models of BoVW.

Comparison of feature extraction and auto-preprocessing for chili pepper (Capsicum Frutescens) quality classification using machine learning

The low-cost camera for machine vision, such as a webcam, still has a problem with resolution noise. Therefore, it is important to learn strategies to reduce noise from low-cost camera images so that they can be widely used for grading machines in the future. This paper aims to compare three feature extraction methods with auto-preprocessing to classify chili pepper <em>(Capsicum Frutescens)</em> quality using a machine learning algorithm. Three extraction methods were used, including the color feature, oriented FAST and rotated BRIEF (ORB), and the combination color feature and ORB. A total of 525 image data for quality chili pepper were collected using the webcam. The auto-preprocessing strategy to classify chili peppers can improve the performance of machine-learning algorithms for all data generated by the feature extractor. The performance of the chili paper quality classification model with auto-preprocessing of the variable color feature can improve the performance of machine learning algorithms by up to 64.21%. The performance improvement of the classification model using the ORB feature variable and the auto-preprocessing of up to 4.41%. The performance improvement of the classification model using machine learning algorithms is 11.27% when using the combination color feature and ORB feature and autopreprocessing.

Detection of Coastal Erosion and Progradation in the Colombian ‘Atrato River’ Delta by Using Sentinel-1 Synthetic Aperture Radar Data

This paper presents a methodology to detect the coastal erosion and progradation effects in the ‘Atrato River’ delta, located in the Gulf of Urabá in Colombia, using SAR (Synthetic Aperture Radar) images. Erosion is the physical–mechanical loss of the soil that affects its functions and ecosystem services while producing a reduction in its productive capacity. Progradation is the deposition of layers in the basinward direction while moving coastward. Other studies have investigated these two phenomena using optical images, encountering difficulties due to the persistent presence of clouds in this region. In order to avoid the cloud effects, in this study, we used 16 Sentinel 1 SAR images with two different polarizations between 2016 and 2023. First, each image was rescaled from 0 to 255, then the image was despeckled by a deep learning (DL) model. Afterwards, a single RGB image was composed with the filtered polarizations. Next, a classifier with 99% accuracy based on Otsu’s method was used to determine whether each pixel was water or not. Then, the classified image was registered to a reference one using Oriented FAST and Rotated BRIEF (ORB) descriptor. Finally, a multitemporal analysis was performed by comparing every image to the previous one to identify the studied phenomena, calculating areas. Also, all images were integrated to obtain a heatmap that showed the overall changes across eight years (2016–2023) in a single image. The multitemporal analysis performed found that the newly created mouth is the most active area for these processes, coinciding with other studies. In addition, a comparison of these findings with the Oceanic Niño Index (ONI) showed a relative delayed coupling to the erosion process and a coupling of progradation with dry and wet seasons.

Advanced framework for epilepsy detection through image-based EEG signal analysis.

Recurrent and unpredictable seizures characterize epilepsy, a neurological disorder affecting millions worldwide. Epilepsy diagnosis is crucial for timely treatment and better outcomes. Electroencephalography (EEG) time-series data analysis is essential for epilepsy diagnosis and surveillance. Complex signal processing methods used in traditional EEG analysis are computationally demanding and difficult to generalize across patients. Researchers are using machine learning to improve epilepsy detection, particularly visual feature extraction from EEG time-series data. This study examines the application of a Gramian Angular Summation Field (GASF) approach for the analysis of EEG signals. Additionally, it explores the utilization of image features, specifically the Scale-Invariant Feature Transform (SIFT) and Oriented FAST and Rotated BRIEF (ORB) techniques, for the purpose of epilepsy detection in EEG data. The proposed methodology encompasses the transformation of EEG signals into images based on GASF, followed by the extraction of features utilizing SIFT and ORB techniques, and ultimately, the selection of relevant features. A state-of-the-art machine learning classifier is employed to classify GASF images into two categories: normal EEG patterns and focal EEG patterns. Bern-Barcelona EEG recordings were used to test the proposed method. This method classifies EEG signals with 96% accuracy using SIFT features and 94% using ORB features. The Random Forest (RF) classifier surpasses state-of-the-art approaches in precision, recall, F1-score, specificity, and Area Under Curve (AUC). The Receiver Operating Characteristic (ROC) curve shows that Random Forest outperforms Support Vector Machine (SVM) and k-Nearest Neighbors (k-NN) classifiers. The suggested method has many advantages over time-series EEG data analysis and machine learning classifiers used in epilepsy detection studies. A novel image-based preprocessing pipeline using GASF for robust image synthesis and SIFT and ORB for feature extraction is presented here. The study found that the suggested method can accurately discriminate between normal and focal EEG signals, improving patient outcomes through early and accurate epilepsy diagnosis.

Practical application of interactive AI technology based on visual analysis in professional system of physical education in universities

Currently, physical education teaching in universities tends to adopt the traditional model of one teacher for multiple students, which has high requirements for teachers and is difficult to consider students' strengths. On this basis, an interactive system has been established, including three modules: behavior information, user data collection, and behavior evaluation. Taking the 400 m running physical education teaching as an example, Kinectv2 was used to collect students' movements and contours while running, and ORB (Oriented FAST and Rotated BRIEF) feature extraction algorithm was used to extract students' movement features. After importing the data into the interactive system, students and teachers could view it in the system and provide guidance based on the students’ actions. This article took 10 students as examples to test their performance changes in the 400 m running before and after systematic training. The results showed that the evaluation score after receiving systematic instruction increased by 6–7 s compared to the score without receiving instruction, with a significant change. This indicated that the interactive AI (artificial intelligence) system constructed in this article can play a significant role in sports teaching of 400 m running.

Adaptive feature extraction method for capsule endoscopy images

The traditional feature-extraction method of oriented FAST and rotated BRIEF (ORB) detects image features based on a fixed threshold; however, ORB descriptors do not distinguish features well in capsule endoscopy images. Therefore, a new feature detector that uses a new method for setting thresholds, called the adaptive threshold FAST and FREAK in capsule endoscopy images (AFFCEI), is proposed. This method, first constructs an image pyramid and then calculates the thresholds of pixels based on the gray value contrast of all pixels in the local neighborhood of the image, to achieve adaptive image feature extraction in each layer of the pyramid. Subsequently, the features are expressed by the FREAK descriptor, which can enhance the discrimination of the features extracted from the stomach image. Finally, a refined matching is obtained by applying the grid-based motion statistics algorithm to the result of Hamming distance, whereby mismatches are rejected using the RANSAC algorithm. Compared with the ASIFT method, which previously had the best performance, the average running time of AFFCEI was 4/5 that of ASIFT, and the average matching score improved by 5% when tracking features in a moving capsule endoscope.

A novel occluded face detection approach using Enhanced ORB and optimized GAN

Objectives:This research presents an approach to detect occluded face images. In order to achieve this, the research presents a novel technique that involves feature extraction and occluded face recognition. Methods: Feature extraction is performed by the enhanced ORB algorithm, which is proposed by the modification of the Oriented Fast and Rotated Brief (ORB) algorithm, by adding a phase for contrast adjustment, together with CNN features. For occluded face recognition, a Generative Adversarial Network (GAN) optimized by the proposed SR-SSA is designed. SR-SSA is proposed by the integration of Search and Rescue Optimization (SAR) in the Sparrow Search Algorithm (SSA). Results: The experimental results demonstrate that the SR-SSA-based GAN algorithm outperforms existing methods in terms of accuracy of 0.956, FAR of 0.045 and FRR of 0.021.

Comparative study of feature extraction algorithms for panorama stitching

Panorama stitching is a fascinating and rapidly advancing research field. By integrating many photographs that were taken from various angles and viewpoints, with various exposure and color settings, a seamless image is primarily the aim of panorama stitching. This paper investigates the performance of three widely used feature extraction algorithms Speeded-Up Robust Features (SURF), Scale-Invariant Feature Transform (SIFT), and Oriented FAST and Rotated BRIEF (ORB) for panorama stitching. The study compares these algorithms in terms of accuracy, robustness, and speed. Results indicate that while SURF and SIFT produce more accurate and robust results than ORB, they require longer processing time. The study evaluates the approach on a real-world dataset and demonstrates its effectiveness in creating seamless and visually appealing panoramas. This study provides valuable insights into the trade-offs between different feature extraction algorithms and presents a practical solution for panorama stitching applications.

Research of different feature detection and matching algorithms on panoramic image

Image stitching is the process of combining numerous photos to make a panorama. The technique of image stitching has rapidly advanced and grown to be a significant area of digital image processing. Many image stitching methods have been proposed and studied in prior study. In this paper, the image stitching process is implemented using different algorithms. For keypoints detection, the algorithms of Harris corner detection, SIFT(Scale-Invariant Feature Transform), SURF(Speeded Up Robust Feature) and ORB(Oriented FAST and Rotated BRIEF) algorithms are applied, then use different methods (i.e., Brute Force, etc.) for feature matching. The RANSAC(Random Sample Consensus) method is used to calculate a homography matrix from matched feature vectors and use it to warp the images. Image blending and cropping methods are proposed to enhance the image quality. Given groups of the self-captured images, experiments have been down to shown the performance of different techniques.

Vehicle Detection and Classification via YOLOv8 and Deep Belief Network over Aerial Image Sequences

Vehicle detection and classification are the most significant and challenging activities of an intelligent traffic monitoring system. Traditional methods are highly computationally expensive and also impose restrictions when the mode of data collection changes. This research proposes a new approach for vehicle detection and classification over aerial image sequences. The proposed model consists of five stages. All of the images are preprocessed in the first stage to reduce noise and raise the brightness level. The foreground items are then extracted from these images using segmentation. The segmented images are then passed onto the YOLOv8 algorithm to detect and locate vehicles in each image. The feature extraction phase is then applied to the detected vehicles. The extracted feature involves Scale Invariant Feature Transform (SIFT), Oriented FAST and Rotated BRIEF (ORB), and KAZE features. For classification, we used the Deep Belief Network (DBN) classifier. Based on classification, the experimental results across the three datasets produced better outcomes; the proposed model attained an accuracy of 95.6% over Vehicle Detection in Aerial Imagery (VEDAI) and 94.6% over Vehicle Aerial Imagery from a Drone (VAID) dataset, respectively. To compare our model with the other standard techniques, we have also drawn a comparative analysis with the latest techniques in the research.

Binocular measurement method for a continuous casting slab based on the one-dimensional probabilistic Hough transform and local sub-pixel sifting.

Due to the low measurement accuracy of the continuous casting slab model caused by difficulty in detecting ideal corners, a binocular measurement method based on the one-dimensional probabilistic Hough transform and local sub-pixel sifting is proposed. First, the one-dimensional probabilistic Hough transform based on inclination angle voting and the Freeman chain code is used to detect the line segments of the exterior outline. Next, sub-pixel points are extracted in each region of interest (ROI) by using Zernike moments, and sifted in the overlapping area of adjacent ROIs. Then the orthogonal total least squares (TLS) method is applied to fitting sub-pixel edges. Finally, after the key points are matched, three-dimensional localization and measurement are completed according to the binocular vision measurement principle. The experimental results show that the minimum relative error and average relative error of length reach 0.3401% and 0.3945%, respectively, satisfying the measurement requirement. Compared with scale-invariant feature transform (SIFT) and the oriented FAST and rotated BRIEF (ORB), the measurement error of the proposed algorithm is reduced by 80.01% and 74.63%, respectively. Compared with another edge fitting method based on k-means clustering and least squares fitting, its measurement error is reduced by 34.11%, and the time consumption is shortened by 39.07%, verifying its excellent performance in accuracy and efficiency.

A Smart System for Detection of Road Lane and Divider

Road Lane and divider detection is a core part in environmental perception for driver assistance system. The paper discusses about machine learning and computer vision approach to identify road lanes and dividers and proposes a system for detection of road lane and divider. Driving assistance systems heavily rely on the road lane and divider recognition. Voting classification was implemented using 7 different classifiers. The combination of Scale Invariant Feature Transform (SIFT) and Oriented FAST and Rotated BRIEF (ORB) provided feature extraction. Principle Component Analysis (PCA) provided dimension reduction. The performance has been examined on the basis of accuracy (95.50%), precision (78.81%), recall (65.71%), and F1 score (71.67%). The proposed solution is helpful in solving issues related to road safety and reducing road accidents.

Matching evaluation based on image content discriminative features for different image types

ABSTRACT Search by image has taken the place of the prior wordy approach, considering spatial image comparison in the feature space. Several query image forms are available. Sketch-to-real image matching is very challenging problem, which is commonly based on edge feature detectors to extract features from sketches. However, they are inconvenient, and it is crucial to select different methods. Thus, methods assessment is conducted for similarity matching between sketched and real images for different drawing contents and clarity levels. The assessment approach includes comparing feature keypoints gathered using the Scale-Invariant Feature Transform (SIFT) and Oriented FAST and Rotated BRIEF (ORB) methods. In addition, the comparison includes matching of objects inside High-Definition (HD) images and 3D images based on their generated features. The textual-Hcontent image search is another search type that is frequently used in brand logo cases. Hence, it is presented for text-logo image search based on visual features. Besides, the motives and downsides of the considered methods are declared, including the space and time complexities within test cases.

An Improved Visual SLAM Method with Adaptive Feature Extraction

The feature point method is the mainstream method to accomplish inter-frame estimation in visual Simultaneous Localization and Mapping (SLAM) methods, among which the Oriented FAST and Rotated BRIEF (ORB) feature-based method provides an equilibrium of accuracy as well as efficiency. However, the ORB algorithm is prone to clustering phenomena, and its unequal distribution of extracted feature points is not conducive to the subsequent camera tracking. To solve the above problems, this paper suggests an adaptive feature extraction algorithm that first constructs multiple-scale images using an adaptive Gaussian pyramid algorithm, calculates adaptive thresholds, and uses an adaptive meshing method for regional feature point detection to adapt to different scenes. The method uses Adaptive and Generic Accelerated Segment Test (AGAST) to speed up feature detection and the non-maximum suppression method to filter feature points. The feature points are then divided equally by a quadtree technique, and the orientation of those points is determined by an intensity centroid approach. Experiments were conducted on publicly available datasets, and the outcomes demonstrate the algorithm has good adaptivity and solves the problem of a large number of corner point clusters that may result from using manually set detection thresholds. The RMSE of the absolute trajectory error of SLAM applying this method on four sequences of TUM RGB-D datasets is decreased by 13.88% when compared with ORB-SLAM3. It is demonstrated that the algorithm provides high-quality feature points for subsequent image alignment, and the application to SLAM improves the reliability and accuracy of SLAM.

Parking Management System Based on Key Points Detection

Abstract In urban areas, efficient parking management is crucial for reducing traffic congestion and environmental impact. This research introduces a new view for making the parking management system that leverages the capabilities of the NVidia Jetson Nano Single Board Computer (SBC) and OpenCV for real-time detection and classification of parking slot occupancy. Unlike traditional systems that rely on intrusive sensors, our proposed solution employs non-intrusive Oriented Fast and Rotated Brief (ORB) key point detection techniques using video feeds. The system architecture integrates video stream processing, ORB via OpenCV, cloud-based data storage, and a Flask server for user notifications. The methodology prioritizes traditional computer vision methods optimized for the Jetson Nano’s CUDA cores, offering a computationally efficient alternative to deep learning approaches. Python’s versatility and MongoDB’s document-based storage are employed for backend development. Our system’s performance, evaluated using open datasets, demonstrates high accuracy, precision, recall, and F1 scores, underlining its effectiveness in real-world urban parking scenarios. This study not only presents a robust solution for parking management but also opens avenues for similar applications in traffic measurement and urban planning.

Visual camera relocalization using both hand-crafted and learned features

The localization of the camera is essential in AR, MR, and robotics. Diverse pipelines employ a hand-crafted or learning based way to predict the camera pose as per the task. In the localization process, both weaknesses and strengths are maintained. However, few current frameworks consider these two features simultaneously. In this study, a novel relocalization pipeline for RGB or RGB-D input is proposed, including a coarse stage with learned features, further refinement with hand-crafted features, and a stable process to measure the confidence of both stages for improving localization robustness. Instead of directly regressing the camera pose, the coarse procedure uses registration to the known source and predicted weighted target point cloud to obtain the initial result. Therefore, we design a deep network called PGNet to construct the weighted target point cloud with the image and previous poses as inputs. Moreover, in consideration of dynamic surroundings, we add a segmentation branch distinguishing each point as either fixed or dynamic with the purpose of promoting dynamic perception. Correspondingly, the segmentation-extended Chamfer Distance is added to optimize PGNet. During the pose refinement, the feature space is established via hand-crafted feature extraction and matching on the training set. Based on the coarse pose, we obtain the accurate pose by applying Kabsch or Perspective-n-Point (PnP) algorithm to point-to-point correspondences built through searching the space and matching Oriented Fast and Rotated Brief (ORB) features. Furthermore, an additional process is presented by defining coarse and refinement metrics to gain a more stable performance. Finally, experiments on both static and dynamic scenes are conducted. On the one side, the results demonstrate the state-of-the-art performance over other existing methods on 7 Scenes, INDOOR-6, Cambridge Landmarks and TUM RGB-D. On the other side, the positive effects of the pose learning part, dynamic branch, confidence regression and hand-crafted feature based refinement are also provided.