RANSAC Algorithm Research Articles

Methodology of Detection and Classification of Selected Aviation Obstacles Based on UAV Dense Image Matching

Currently, more and more accurate data provided by UAVs make it possible to analyze land cover, which requires the detection of objects and their individual elements. Object detection and determination of their geometric features is possible thanks to dense point clouds generated based on imagery obtained from low altitudes. 3D data from UAVs turn out to be extremely useful for ensuring safety in the airspace in the close vicinity of the airport. This article presents the methodology of automatic aviation obstacle detection based on low altitude data (UAV). The research was carried out on a dense 3D point cloud. The developed methodology for detecting aviation obstacles consists of three main stages. The first is point cloud filtration based on height–preliminary identification of aviation obstacles, followed by 3D point cloud segmentation using a modified RANSAC algorithm, supplemented with two-dimensional vector data of aviation obstacles to improve the accuracy of the segmentation process. The last stage is the classification of aviation obstacles according to the adopted height and cross-section criterion. The proposed method of detecting aviation obstacles is characterized by high accuracy. The mean error of fitting the point cloud to the obstacle database ranged from ± 0.04 m to ± 0.07 m.

Image mosaicing based on BRISK and improved RANSAC algorithm

Image mosaicing based on BRISK and improved RANSAC algorithm

Real-time and automatic map stitching through aerial images from UAV

Real-time aerial map stitching through aerial images had been done through many different methods. One of the popular methods was a features-based algorithm to detect features and to match the features of two and more images to produce a map. There are several feature-based methods such as ORB, SIFT, SURF, KAZE, AKAZE and BRISK. These methods detect features and compute homography matrix from matched features to stitch images. The aim for this project is to further optimize the existing image stitching algorithm such that it will be possible to run in real-time as the UAV capture images while airborne. First, we propose to use a matrix multiplication method to replace a singular value decomposition method in the RANSAC algorithm. Next, we propose to change the workflow to detect the image features to increase the map stitching rate. The proposed algorithm was implemented and tested with an online aerial image dataset which contain 100 images with the resolution of 640 × 480. We have successfully achieved the result of 1.45 Hz update rate compared to original image stitching algorithm that runs at 0.69 Hz. The improvement shown in our proposed improved algorithm are more than two folds in terms of computational resources. The method introduced in this paper was successful speed up the process time for the program to process map stitching.

Extracting Crown Morphology with a Low-Cost Mobile Lidar Scanning System in the Natural Environment

To meet the demand for intelligent measurements of canopy morphological parameters, a mobile LiDAR scanning system with LiDAR and IMU as the main sensors was constructed. The system uses a LiDAR-IMU tight coupling odometry method to reconstruct a point cloud map of the area surveyed. After using the RANSAC algorithm to remove the map ground, the European clustering algorithm is used for point cloud segmentation. Finally, morphological parameters of the canopy, such as crown height, crown diameter, and crown volume, are extracted using statistical and voxel methods. To verify the algorithm, a total of 43 trees in multiple plots of the campus were tested and compared. The algorithm defined in this study was evaluated with manual measurements as reference, and the morphological parameters of the canopy obtained using the LOAM and LeGO-LOAM algorithms as the basic framework were compared. Experiments show that this method can be used to easily obtain the crown height, crown diameter, and crown volume of the area; the correlation coefficients of these parameters were 0.91, 0.87, and 0.83, respectively. Compared with the LOAM and LeGO-LOAM methods, they were increased by 0.004, 0.12, and 0.13 and 0.07, 0.15, and 0.04, respectively. The test results for this new system are positive and meet the requirements of horticulture and orchard measurements, indicating that it will have significant value as an application.

Grasp Detection under Occlusions Using SIFT Features

Distinguishing target object under occlusions has become the forefront of research to cope with grasping study in general. In this paper, a novel framework which is able to be utilized for a parallel robotic gripper is proposed. There are two key steps for the proposed method in the process of grasping occluded object: generating template information and grasp detection using the matching algorithm. A neural network, trained by the RGB-D data from the Cornell Grasp Dataset, predicts multiple grasp rectangles on template images. A proposed matching algorithm is utilized to eliminate the influence caused by occluded parts on scene images and generates multiple grasp rectangles for objects under occlusions using the grasp information of matched template images. In order to improve the quality of matching result, the proposed matching algorithm improves the SIFT algorithm and combines it with the improved RANSAC algorithm. In this way, this paper obtains suitable grasp rectangles on scene images and offers a new thought about grasping detection under occlusions. The validation results show the effectiveness and efficiency of this approach.

A calibration method of 2D LIDAR-Visual sensors embedded on an agricultural robot

In the robotics field, mobile platforms typically combine data from multiple sensors and have been extensively researched. Estimating the homogeneous transformation between sensors is a critical step in associating their measurements data. In this paper, we present a calibration method of 2D LIDAR-Visual sensors embedded on an agricultural robot intended for strawberry greenhouse applications. The method is based on plan-to-plan homography approach and employs a set of point correspondences. The correspondences points are the measured intersection points of the laser range finder plane with the edges of the calibration pattern. The extracted points are used to estimate the homography matrix. The RANSAC algorithm is used with more points obtained from pairs scans/images by sensors to generate a robust homography. The estimated homography matrix is identified as the rigid transformation between the 2D LIDAR and the monocular camera. The results of the proposed method show that we can achieve accurate extrinsic parameters, avoiding the need for intrinsic parameters in advance or complex calibration objects. The system is composed of the Hokuyo URG-04LX-UG01 sensor and a monocular camera with an infrared filter. All of the software modules were created using Robot Operating System (ROS) and Python.

Film and television industry cloud exhibition design based on 3D imaging and virtual reality

The three-dimensional virtual scene can provide users with a visual three-dimensional virtual environment, with various multimedia channels such as sound, video, force feedback equipment, etc., to bring users a completely immersive interactive experience. This paper introduces 3D imaging and virtual reality technology in the film and television industry cloud exhibition, and develops a virtual display platform. First of all, this paper divides the registration into two processes: camera calibration and joint calibration of the camera and laser scanner based on the calibration results. Camera calibration can determine the plane model of the calibration board in the camera coordinate system, and the joint calibration uses the RANSAC algorithm to extract the point cloud of the plane model of the calibration board, and then optimizes the distance between the points in the plane model point cloud and the corresponding plane in the camera coordinate system Find the optimal transformation between the two sets of data, and then calculate the registration relationship between the point cloud and the image. Secondly, this article conducts a demand analysis of the film and television industry cloud exhibition platform based on virtual reality technology, including the business goals set by the platform, platform system analysis, overall design, and system operating environment and configuration requirements. This model provides a feasible solution for the visual interaction of the cloud exhibition design of the film and television industry.

EVALUATION OF 3D BUILDING MODEL USING TERRESTRIAL LASER SCANNING AND DRONE PHOTOGRAMMETRY

Abstract. The objective of our study is the evaluation of the 3D modeling of buildings and the extraction of structural elements from point clouds obtained using two acquisition techniques (drone and terrestrial laser scanner), as well as the evaluation of the usefulness of their integration. The drone shooting mission was carried using the DJI Phantom 3 Professional and the Sony EXMOR 1/2.3" CMOS RGB camera. For the TLS scanning mission, 9 scanning stations were performed using the FARO Focus S350 laser scanner.To allow the fusion of the two point clouds obtained from drone imagery and TLS, an alignment step is applied. This step was performed using the Iterative Closest Point algorithm. Segmentation was performed using the adapted RANSAC algorithm on point clouds obtained from the drone mission and the TLS mission as well as on the merged point cloud in order to extract structural elements of the building such as windows, doors and stairs. Analysis of the results emphasizes the importance of TLS and drone in 3D modeling. TLS gave better results than the drone in extracting structural elements. This work confirms the importance of complementarity between these two technologies to produce detailed, complete and precise 3D models.

Uncertainty determination of a microvolume characterized through confocal microscope technique

Standardized measurements protocols are widely used and necessary in order to ensure a relivable and repetitive data. This work introduces a new procedure to measure the volume of any irregular micro-hole on a rough surface. A filtering and fitting model is proposed for calculating the void volume of the cavity. Experimental point cloud is acquired by optically measuring the micro-hole with a confocal microscope. RANSAC algorithm is used to establish the reference plane, while the limits of the cavity and the volume are determined by a proposed algorithm. The mentioned model is validated by measuring six real samples. In addition, the corresponding uncertainty is estimated by using Monte Carlo method.

A Matching Algorithm T-AKAZE for Image Recognition of Hydroelectric Equipment Failure

Aiming at the shortcomings of the current image-based fault identification algorithm for hydropower station equipment, such as low efficiency and poor accuracy, an improved image matching algorithm based on AKAZE, T-AKAZE was proposed. In this paper, AKAZE algorithm is firstly used to obtain image feature points. Then, the improved algorithm T-AKAZE is used for coarse matching of feature points. On the basis of Tanimoto coarse matching, RANSAC algorithm is used for fine matching to improve the algorithm accuracy. In order to verify the matching effect of the improved algorithm, ORB algorithm, AKAZE algorithm and ORB+Tanimoto algorithm were compared and analyzed. The experimental results show that the proposed algorithm has good robustness for image matching of different scales and similarity, and its timeliness also meets the application requirements, which provides convenience for the staff to identify the fault of hydropower station equipment.

An Image Matching Method Based on SIFT Feature Extraction and FLANN Search Algorithm Improvement

In order to solve the problems of less feature information and high mismatching rate in traditional image matching algorithms, this paper proposed to extract and describe features based on the SIFT algorithm. FLANN algorithm was used to pre-match feature points, and RANSAC algorithm was used to optimize the matching results, so as to realize real-time image matching and recognition. Experimental results show that the proposed algorithm has better accuracy and better matching effect than traditional image matching methods.

RESEARCH ON EVALUATION OF THE SPALLING DISEASE OF NICHE FOR BUDDHA IN GROTTOES

Abstract. The niche for Buddha is an important part of the cultural relics in the grottoes, but it has caused serious spalling disease due to human activities and natural disasters. This paper presents a new quantitative evaluation method for the spalling disease of niche for Buddha. First, the random forest-based method was used to identify the niche for Buddha . Then, the spatial clustering of the head of the niche for Buddha was performed by DBSCAN, and the reference surface was determined by the RANSAC algorithm. Based on this, the spallation depth of the grotto surface was extracted and the relevant index elements were established. The experiment of point cloud data in Cave 18 of Yungang Grottoes proves the rationality of this method, which is of great significance to the protection and virtual restoration of cultural relics in grottoes.

Ground Segmentation Algorithm of Lidar Point Cloud Based on Ray-Ransac

Aiming at the problems of poor segmentation effect, low efficiency and poor robustness of the Ransac ground segmentation algorithm, this paper proposes a radar segmentation algorithm based on Ray-Ransac. This algorithm combines the structural characteristics of three-dimensional lidar and uses ray segmentation to generate the original seed point set. The random sampling of Ransac algorithm is limited to the original seed point set, which reduces the probability that Ransac algorithm extracts outliers and reduces the calculation. The Ransac algorithm is used to modify the ground model parameters so that the algorithm can adapt to the undulating roads. The standard deviation of the distance from the point to the plane model is used as the distance threshold, and the allowable error range of the actual point cloud data is considered to effectively eliminate the abnormal points and error points. The algorithm was tested on the simulation platform and the test vehicle. The experimental results show that the lidar point cloud ground segmentation algorithm proposed in this paper takes an average of 5.784 milliseconds per frame, which has fast speed and good precision. It can adapt to uneven road surface and has high robustness.

Triple screening point cloud registration method based on image and geometric features

Three-dimensional reconstruction of cochlear model is commonly used to measure the cochlear contour of patients with high accuracy and configure appropriate hearing aids. To improve the matching accuracy of 3D reconstruction of cochlear model, a triple screening point cloud registration method based on image and geometric features is proposed in this paper. Firstly, extracting the image feature points by SIFT algorithm, then eliminating the mismatched point pairs according to the RANSAC algorithm. Secondly, the average value of the normal feature is introduced to select the feature points with obvious geometric feature region. Thirdly, based on the point cloud fast point feature histogram (FPFH), the matching feature point pairs with image features and geometric features are selected to complete the coarse registration. Finally, iterative closest point (ICP) algorithm is used to achieve fine registration. The proposed algorithm is more comprehensive and effective for finding feature points then ensures the accuracy of registration results. In addition, results of the simulation show that the proposed algorithm reduces both the matching error and the total number of iterations compared with some existing algorithms.

ДЕТЕКТИРОВАНИE ВЫБРОСОВ В МЕТОДЕ ПРЯМОЙ СТЕРЕО-ВИЗУАЛЬНОЙ ОДОМЕТРИИ НА БАЗЕ ИЕРАРХИЧЕСКОЙ КЛАСТЕРИЗАЦИИ

This paper presents an approach to stereo-visual odometry without explicitly calculatingoptical flow. Visual odometry is a method of obtaining navigation information by processing asequence of frames from onboard cameras. There are two approaches to processing video information- using well-localized areas of the image - feature points and using all high-contrast pixels- a direct method. The direct method works by using the intensities of all high-contrast pixels inthe image, making it possible to reduce the computational complexity spent searching, describing,and matching feature points and increasing the accuracy of motion estimation. However, methodsof this class have a drawback - the presence of moving objects in the frame significantly reducesthe accuracy of the estimation of motion parameters. Outlier detection techniques are used toavoid this problem. Classical methods for detecting outliers in input data, such as RANSAC, arepoorly applicable and have high computational costs due to the computationally complex functionof rating hypotheses. This work aims to describe and demonstrate an outlier detection approachbased on the hierarchical clustering algorithm, which selects the statistically most probable solution,bypassing the stage of rating each hypothesis, which significantly reduces the computationalcomplexity. For hierarchical clustering, a measure of the distance between hypotheses with lowsensitivity to errors in estimating motion parameters is proposed. An extension of the stereo-visualodometry algorithm is also proposed to work in more complex visibility conditions due to the transitionfrom the intensity representation of the image to a multichannel binary one. Transformingan image to a multichannel binary representation gives invariance to changes in image brightness.However, it requires modification of nonlinear optimization algorithms to work with binary descriptors.As a result of the work, it has been shown that the proposed outlier detection algorithmcan operate in real-time on mobile devices and can serve as a less resource-intensive replacementfor the RANSAC algorithm in problems of visual odometry and optical flow eviction. Qualitativemetrics of the proposed solution are demonstrated on the KITTI dataset. The dependences of theperformance of the algorithm on the parameters of the algorithm are given.

USE OF QUANTILE REGRESSION AND RANSAC ALGORITHM IN FITTING VOLUME EQUATIONS UNDER THE INFLUENCE OF DISCREPANT DATA

The objective of this study was to evaluate three estimation methods to fit volume equations in the presence of influential or leverage data. To do so, data from the forest inventory carried out by the Centro Tecnológico de Minas Gerais Foundation were used to fit the Schumacher and Hall (1933) model in its nonlinear form for Cerradão forest, considering the quantile regression (QR), the RANSAC algorithm and the nonlinear Ordinary Least Squares (OLS) method. The correlation coefficient ( ) between the observed and estimated volumes, root-mean-square error (RMSE), as well as graphical analysis of the dispersion and distribution of the residuals were used as criteria to evaluate the performance of the methods. After the analysis, the nonlinear least squares method presented a slightly better result in terms of the goodness-of-fit statistics, however it altered the expected trend of the fitted curve due to the presence of influential data, which did not happen with the QR and the RANSAC algorithm, as these were more robust in the presence of discrepant data.

Fruit Detection and Pose Estimation for Grape Cluster-Harvesting Robot Using Binocular Imagery Based on Deep Neural Networks.

Reliable and robust fruit-detection algorithms in nonstructural environments are essential for the efficient use of harvesting robots. The pose of fruits is crucial to guide robots to approach target fruits for collision-free picking. To achieve accurate picking, this study investigates an approach to detect fruit and estimate its pose. First, the state-of-the-art mask region convolutional neural network (Mask R-CNN) is deployed to segment binocular images to output the mask image of the target fruit. Next, a grape point cloud extracted from the images was filtered and denoised to obtain an accurate grape point cloud. Finally, the accurate grape point cloud was used with the RANSAC algorithm for grape cylinder model fitting, and the axis of the cylinder model was used to estimate the pose of the grape. A dataset was acquired in a vineyard to evaluate the performance of the proposed approach in a nonstructural environment. The fruit detection results of 210 test images show that the average precision, recall, and intersection over union (IOU) are 89.53, 95.33, and 82.00%, respectively. The detection and point cloud segmentation for each grape took approximately 1.7 s. The demonstrated performance of the developed method indicates that it can be applied to grape-harvesting robots.

Parametric Architectural Elements from Point Clouds for HBIM Applications

To preserve tangible cultural assets for the future, it is crucial to make sure that the maintenance, repair, and restoration of these buildings are of high quality. To ensure proper cultural heritage preservation, highly accurate measurement and modelling methods are necessary. For this purpose, laser scanner systems are widely used; without any doubt, these systems provide many advantages over conventional measuring techniques. On the other hand, the scan angle, the distance to the object, the object’s material composition, the atmospheric conditions, as well as obstacles between the scanner and objects, can cause gaps or noise in the point clouds, making it challenging to manage and interpret the resulting datasets. Thus, extracting the geometries of architectural façade elements from these point clouds is often tedious and requires a high level of expertise. Projects utilizing Building Information Modelling (BIM) Systems have recently begun in Turkey. Although this technology is generally applied to address the whole life cycle of new buildings beginning with the design stage, it is necessary to define existing structures in this system. In this context, research-development and practices related to tangible cultural assets are carried out under the name of the Historic Building Information System (HBIM). In our study, we create parametric models that needed for transferring the cultural assets, which subject to deformation over years. A semi-automatic methodology based on the RANSAC algorithm was applied to extract geometry from point cloud data that contains noise. The obtained model was transferred to BIM following IFC standards. Şehzade Mosque, built by Mimar Sinan in the 16th century Ottoman Classical Period during the reign of Sultan Suleyman the Magnificent, was chosen as the application area of the study. The architectural elements obtained from the application of the current point clouds were compared with the existing architectural drawings, and the contributions of the study were evaluated.

RANSAC algorithm for instantaneous frequency estimation and reconstruction of frequency-modulated undersampled signals

Frequency modulated (FM) signals sampled below the Nyquist rate or with missing samples (nowadays part of wider compressive sensing (CS) framework) are considered. Recently proposed matching pursuit and greedy techniques are inefficient for signals with several phase parameters since they require a search over multidimensional space. An alternative is proposed here based on the random samples consensus algorithm (RANSAC) applied to the instantaneous frequency (IF) estimates obtained from the time-frequency (TF) representation of recordings (undersampled or signal with missing samples). The O’Shea refinement strategy is employed to refine results. The proposed technique is tested against third- and fifth-order polynomial phase signals (PPS) and also for signals corrupted by noise.

Image Augmentation Using Hybrid RANSAC Algorithm

The process of augmenting the number of images in a dataset is called Image Augmentation. Data volume is essential to process and generate digital outputs from a variety of features. This work focuses on the image augmentation using a hybrid RANSAC algorithm. The features extracted is used to join or merge the images by the blending of images. The proposed RANSAC algorithm is used to extract features from four images and produce the desired mosaiced image. A mosaiced picture is best suited for aerial photos and real-world objects. The blur metric of the proposed method is 185.2587 and which is 2.86% higher than the feathering blending algorithms. The total number of images in the dataset is 2100. The number of images after augmentation is 6300 with average accuracy of 95.6%. The reported remarkable results are beneficial to all the stakeholders on image augmentation.