Improved RANSAC Algorithm Research Articles

A 3D Vision-Based Weld Seam Extraction Method for Arbitrarily Placed Spatial Planar Weldments

Vision-based weld seam extraction poses a significant challenge for weldments with complex spatial structures in automated welding. Existing research primarily focuses on identifying weld seams from weldments with given positions and postures, while practical weld path planning requires multiple weld seams identified within arbitrarily placed weldments. This paper proposes a methodology that identifies weld seams from arbitrarily placed spatial planar weldments in a single run. First, by introducing a turntable calibrated with respect to a 3D camera, we perform 3D reconstruction on an arbitrarily placed spatial planar weldment. Second, an improved RANSAC algorithm based on Euclidean clustering is proposed to carry out plane segmentation, focusing on segmentation accuracy. Finally, we present a novel weld seam extraction algorithm leveraging the half-edge data structure to efficiently compute weld seams from the segmented planes. The experiments conducted in this study demonstrate that the average segmentation errors (as an indirect indicator of weld seam extraction error) are reduced by 90.3% to 99.8% over conventional segmentation methods, and the standard deviations are reduced by 64.8% to 97.0%.

Extraction of River Water Bodies Based on ICESat-2 Photon Classification

The accurate extraction of river water bodies is crucial for the utilization of water resources and understanding climate patterns. Compared with traditional methods of extracting rivers using remote sensing imagery, the launch of satellite-based photon-counting LiDAR (ICESat-2) provides a novel approach for river water body extraction. The use of ICESat-2 ATL03 photon data for inland river water body extraction is relatively underexplored and thus warrants investigation. To extract inland river water bodies accurately, this study proposes a method based on the spatial distribution of ATL03 photon data and the elevation variation characteristics of inland river water bodies. The proposed method first applies low-pass filtering to denoised photon data to mitigate the impact of high-frequency signals on data processing. Then, the elevation’s standard deviation of the low-pass-filtered data is calculated via a sliding window, and the photon data are classified on the basis of the standard deviation threshold obtained through Gaussian kernel density estimation. The results revealed that the average overall accuracy (OA) and Kappa coefficient (KC) for the extraction of inland river water bodies across the four study areas were 99.12% and 97.81%, respectively. Compared with the improved RANSAC algorithm and the combined RANSAC and DBSCAN algorithms, the average OA of the proposed method improved by 17.98% and 7.12%, respectively, and the average KC improved by 58.38% and 17.69%, respectively. This study provides a new method for extracting inland river water bodies.

Measurement method of spherical radius size of differential planetary gear tooth surface based on 3D vision

Abstract In order to accurately measure the spherical radius dimensions of planetary gear tooth surfaces, we propose a non-contact measurement method based on 3D vision technology. Firstly, the point cloud data of the planetary gear captured by the laser 3D profiler is preprocessed, and the tooth surface point cloud is extracted. Next, based on the structural characteristics of the planetary gear tooth surface, a uniform slicing and sampling algorithm is used to extract circular contour points where the tooth surface point cloud intersects with the slicing planes. These points are then projected onto a two-dimensional plane, where an improved RANSAC algorithm is used to precisely fit each circular cross-section. Contour points associated with significant fitting errors are removed based on a set tolerance value. Finally, an improved differential evolution algorithm is used to perform a three-dimensional spherical fitting on the contour points that meet the tolerance criteria, achieving accurate measurement of the spherical radius of the planetary gear tooth surfaces. Experimental results demonstrate that the repeatability error of the proposed method is ±0.02 mm, with a maximum absolute error of 0.026 mm and an average measurement time of 4.76 s. The method exhibits high robustness and measurement accuracy, meeting practical engineering measurement requirements.

An Improved RANSAC Based Segmentation Algorithm for the Belt Wedge Point Cloud of the Automotive V-Ribbed Belt

Point cloud segmentation is an important part of the belt wedge dimension measurement of automotive V-ribbed belt, and accurate segmentation is the basis of the subsequent dimension calculation of the belt wedge. In view of the problem of randomly selecting initial points and over-segmented plane in orthodox RANSAC algorithm, this text presents an modified RANSAC arithmetic for segmentation of belt wedge point clouds of automotive V-ribbed belt, which uses the radius space to redefine the selection method of initial points, obtains the optimal plane result through multiple iterations, and uses the angle and distance of vectors to prevent over-segmentation of point clouds. In the experiment, RANSAC and improved RANSAC are used to segment the belt wedge point cloud datas of cloud data of the PK type automotive V-ribbed belt collected by line laser displacement sensor. Compare segmentation results, Facts prove that the improved RANSAC algorithm has better segmentation effect, the proportion of plane points h is increased by 7.5%.

A navigation method for paddy field management based on seedlings coordinate information

Compared to tillage, transplanting, and harvesting operations in paddy fields, field management operations such as spraying and weeding require completing tasks along the rice seedling rows to minimize seedling damage and reduce operational losses. Visual navigation, as a commonly used navigation method, can identify rice seedling rows, but it is susceptible to complicated paddy field environments. To address these challenges, our study combines UAV (unmanned aerial vehicle) surveying technology with the YOLOv5s object detection algorithm and proposes a navigation method for paddy field management based on seedling coordinate information. Firstly, the YOLOv5s object detection algorithm was used to identify and locate rice seedling points in the UAV image, and a coordinate transformation model was established to extract the geographic coordinates of the seedling points. Secondly, in order to classify the recognized seedling points into different seedling rows, a classification algorithm was proposed, and the improved RANSAC algorithm further promoted the classification effect. Once again, to obtain a smooth navigation path for agricultural machinery navigation, B-spline curves were used to approximate the classified seedling points. Finally, the generated navigation paths were written into the navigation controller, and the navigation performance was tested on flat ground and paddy fields using a vehicle platform. The results of the flat ground test indicated that different bending degrees have a significant impact on the lateral error. When the bending degree was large, the maximum lateral error was less than 7 cm, and when the bending degree was small, the maximum lateral error was less than 4 cm. The navigation accuracy of RMS in the flat ground test was 2.7 cm. In the paddy field experiment, due to the influence of loose soil surfaces and potholes, the maximum lateral error was about 16 cm. The navigation accuracy of RMS in the paddy field experiment was 5.9 cm, which can meet the operational requirements. The experimental results show that the proposed navigation method can achieve automatic navigation of agricultural machinery along curved rice seedling rows under complex paddy field environments, such as light change, seedling shortage, uneven road surfaces, and curved seeding rows.

Target Localization and Grasping of Parallel Robots with Multi-Vision Based on Improved RANSAC Algorithm

Some traditional robots are based on offline programming reciprocal motion, and with the continuous upgrades in vision technology, more and more tasks are being replaced with machine vision. At present, the main method of target recognition used in palletizers is the traditional SURF algorithm, but this method of grasping leads to low accuracy due to the influence of too many mis-matched points. Due to the accuracy of robot target localization with binocular-based vision being low, an improved random sampling consistency algorithm for performing complete parallel robot target localization and grasping under the guidance of multi-vision is proposed. Firstly, the improved RANSAC algorithm, based on the SURF algorithm, was created based on the SURF algorithm; next, the parallax gradient method was applied to iterate the matched point pairs several times to further optimize the data; then, the 3D reconstruction was completed using the improved algorithm via the program technique; finally, the obtained data were input into the robot arm, and the camera’s internal and external parameters were obtained using the calibration method so that the robot could accurately locate and grasp objects. The experiments show that the improved algorithm shows better recognition accuracy and grasping success with the multi-vision approach.

Unmanned aerial vehicle remote sensing image registration based on an improved oriented FAST and rotated BRIEF- random sample consensus algorithm

Unmanned Aerial Vehicle (UAV) remote sensing image registration is the key step of remote sensing image stitching, image fusion and multi-frames image super-resolution. Its speed and accuracy determines the effect of remote sensing image applications, such as object detection, environment monitoring. To meet the speed and accuracy requirements of UAV remote sensing image registration, an improved Oriented FAST and Rotated BRIEF- Random sample consensus (ORB-RANSAC) algorithm is proposed. Firstly, images to be registered are divided into non-overlapping sub-images, and then a simplified image pyramid is constructed for these sub-images to get scale invariance. Secondly, the traditional FAST corner detection algorithm is improved by setting the adaptive corner detection threshold, and more feature points are detected. Meanwhile, the traditional quadtree algorithm is improved to remove redundant feature points and keep the remaining high-quality feature points. Thirdly, feature points coarse matching is done by bidirectional matching combined with cosine similarity method. Finally, the improved RANSAC algorithm is used for feature points fine matching to eliminate mismatches and calculate the transformation matrix. Experiment results show that, comparing with the traditional ORB algorithm, the number of feature points detected is significantly increased and its distribution is more uniform, and the correct matching rate increases by 58.10% in the case of image scale changing. Comparing with the state-of-the-art UAV remote sensing image registration algorithm, the correct matching rate and mutual information of our method are increased by 0.68% and 1.91% respectively, matching time and root mean square error are reduced by 3.89% and 11.2% respectively.

Rail profile matching method based on stepped calibration plate and improved SURF algorithm

In order to avoid the calibration plane and laser plane do not coincide and the rail profile is difficult to match dynamically, a stepped calibration plate is made, and a rail profile matching method based on the improved SURF algorithm and random sample consensus algorithm (RANSAC) is proposed. Firstly, a stepped rail profile calibration plate is designed and fabricated, which can directly calibrate the laser plane, avoiding the problem that the calibration plane and the line laser plane do not coincide completely in practical application. In the calibration process, collect the optimal control points and calibrate the image by polynomial transformation and bilinear interpolation, then complete contour rough matching using SURF algorithm. During the SURF algorithm, construct the matching constraint of the center of the orbit waist to delete part of the false matches. Finally, the improved RANSAC algorithm is used to filter the wrong matches, achieving precise contour matching. The experimental results show that compared with traditional contour matching methods, the improved contour matching algorithm has higher accuracy and stronger robustness.

Three-dimensional system modeling and design of ecological garden landscape based on the interlaced spatial pattern of light and shadow

The layout and design of ecological landscaping is an important part of the construction and development of modern cities. In the 3D reconstruction of the spatial pattern of the light and shadow interlaced zone of the ecological landscape, the complexity and particularity of the ecological landscape structure make it difficult for the three-dimensional reconstruction stereo matching set to meet the accuracy requirements, and the quality 3D image construction cannot meet the requirements of landscape planning. Based on the principle of binocular stereo vision, a regional feature stereo matching algorithm (rsurf) is used to improve the accuracy of feature matching. Considering that the algorithm is easy to filter out the detailed features of the image, the improved RANSAC algorithm is used to filter the matching results. The experimental results show that in the matching cost test of the optimal matching window, the 15 × window neighborhood has the lowest matching cost, and the generated value in the 100 × 100 source window is 0.824. In the test after matching and fusion, the rsurf algorithm is superior to the surf algorithm in both RMS and PMS error performance, and can better meet the requirements of 3D reconstruction of the binocular vision system. The research content has an important reference for the application of landscape visualization 3D technology, and improves the overall layout effect of landscape landscape.

3D Reconstruction Method based on Medical Image Feature Point Matching.

Medical 3D image reconstruction is an important image processing step in medical image analysis. How to speed up the speed while improving the accuracy in 3D reconstruction is an important issue. To solve this problem, this paper proposes a 3D reconstruction method based on image feature point matching. By improving SIFT, the initial matching of feature points is realized by using the neighborhood voting method, and then the initial matching points are optimized by the improved RANSAC algorithm, and a new SFM reconstruction method is obtained. The experimental results show that the feature matching rate of this algorithm on Fountain data is 95.42% and the matching speed is 4.751 s. It can be seen that this algorithm can shorten the reconstruction time and obtain sparse point clouds with more reasonable distribution and better reconstruction effect.

Indoor Target Detection and Pose Estimation Based on Point Cloud

The indoor environment faced by service robots is complex, with plenty of objects and mutual occlusion, traditional algorithms cannot detect the target and estimate its pose accurately. We propose a set of target detection and pose estimation algorithm based on point cloud templates to solve the above problems. Through the segmentation and clustering of scenes, the application of the algorithm in complex scenes is realized. Based on the key points to estimate the pose of the target, we achieve the adaptation to mutual occlusion. Besides, we propose an improved RANSAC algorithm, which maintains the accuracy of the original algorithm while greatly improving the speed. Finally, we test the algorithm through the open source model library, simulated and actual scenarios, compared with the SAC-IA algorithm, our algorithm improves the time by 89%, and in the application of complex scenes, the error of the pose estimation is at the millimeter level.

Ground Obstacle Detection Technology Based on Fusion of RGB-D and Inertial Sensors

Aiming at the real-time detection of ground obstacles in the passable area for the visually impaired, a ground obstacle detection technology based on the fusion of RGB-D and inertial sensor is proposed. Firstly, the spatial model of the ground obstacle is established, and the inertial sensor parameters are fused to calculate the camera inclination to correct the world coordinates of the ground obstacle. Secondly, according to the actual scenes and needs of the visually impaired, the remote detection pixels in the depth image are removed by threshold segmentation algorithm, and the depth map is divided into 4 regions, and the dynamic division of ROI is realized by fusing inertial sensor data. Finally, an obstacle detection algorithm is designed by improved RANSAC algorithm based on the growth of ground area algorithm, and collected real data for experimental verification. The experimental results show that the accuracy and recall rates of the proposed technology reach 90.87% and 89.33%, and better than the existing detection algorithms in the time efficiency of execution, which meets the real-time requirements of the algorithm for the visually impaired.

Application of Image Mosaic Technology in Tai Chi Animation Creation.

Panorama can reflect the image seen at any angle of view at a certain point of view. How to improve the quality of panorama stitching and use it as a data foundation in the “smart tourism” system has become a research hotspot in recent years. Image stitching means to use the overlapping area between the images to be stitched for registration and fusion to generate a new image with a wider viewing angle. This article takes the production of “Tai Chi” animation as an example to apply image stitching technology to the production of realistic 3D model textures to simplify the production of animation textures. A handheld camera is used to collect images in a certain overlapping area. After cylindrical projection, the Harris algorithm based on scale space is adopted to detect image feature points, the two-way normalized cross-correlation algorithm matches the feature points, and the algorithm to extract the threshold T iteratively removes mismatches. The transformation parameter model is quickly estimated through the improved RANSAC algorithm, and the spliced image is projected and transformed. The Szeliski grayscale fusion method directly calculates the grayscale average of the matching points to fuse the image, and finally, the best stitching method is used to eliminate the ghosting at the image mosaic. Data experiments based on Matlab show that the proposed image splicing technology has the advantages of high efficiency and clear spliced images and a more satisfactory panoramic image visual effect can be achieved.

Image mosaicing based on BRISK and improved RANSAC algorithm

Image mosaicing based on BRISK and improved RANSAC algorithm

Matching of small packages of traditional Chinese medicine based on improved RANSAC algorithm

The vision system model of small package sorting of traditional Chinese medicine was constructed, and the chessboard calibration method was used to calibrate the binocular camera. Surf algorithm and orb algorithm are analyzed by experiments, and orb algorithm with high real-time performance is used to extract feature points. The fast nearest neighbor FLANN algorithm is used to quickly match the feature points, and the matched feature points are screened according to Lowe’s algorithm and v-axis coordinate consistency principle, to solve the problem of false matching points. The method of selecting feature points based on matching quality ranking to calculate the homography matrix is designed, which solves the random sampling problem of the RANSAC algorithm and effectively shortens the time of feature matching.

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.

Research on convergence analysis method of metro tunnel section--Based on mobile 3D laser scanning technology

The protection and monitoring of subway tunnels have always been an important guarantee for the safe operation of urban rail transit. The current monitoring of tunnel deformation and convergence relies on traditional technology methods such as convergence meters and electronic total stations. Although the 3D laser scanning method of stationary station setup and station-to-station splicing of monitoring station is gradually becoming mature, the error accumulation and slow operation efficiency brought by station-to-station splicing are still the bottleneck of subway tunnel protection and monitoring. Based on the analysis of the principles and advantages of mobile 3D laser scanning technology, this paper deeply studies the mobile 3D laser scanning technology for rapid collection of point cloud data in subway tunnels, proposes an improved RANSAC algorithm based on the tunnel ellipse parameter model, and extracts metro tunnel deformation information through denoising and fitting of the tunnel cross section point cloud data, achieving convergence analysis of metro tunnel section. The results show that this method can quickly and accurately obtain tunnel section data, which provides a new and efficient technical approach for subway tunnel protection monitoring.

A novel image matching algorithm based on PCA and SIFT

In order to solve the problem of low matching precision and slow matching speed of image matching algorithm based on classical SIFT, a new image matching algorithm based on PCA, SIFT and improved RANSAC is proposed. Firstly, the SIFT feature was extracted from images; Secondly, principal component analysis is used to reduce the dimension of SIFT feature descriptor, from 128 to 20; then, the EUCLIDEAN distance is used for feature matching; finally, an improved RANSAC algorithm is proposed to eliminate the mismatched feature points. Experimental results show that the proposed algorithm improves the accuracy and speed of image matching.

An improved image registration and fusion algorithm

Under the background of telemedicine, a new registration and mosaic algorithm for medical images is proposed in this paper to solve the problems of electronic noise, uneven illumination and ray scattering in the real-time medical process. The improved Retinex algorithm by trilateral filter and homomorphic filtering algorithm can enhance the image effectively in preprocessing. The improved phase correlation algorithm based on log polar transformation was used to calculate parameters, such as rotation, scaling and translation. Then, the SUSAN corner matching points were extracted in overlapping positions, the improved KD tree was used for enhancing matching efficiency. Later, matching points were purified by the improved RANSAC algorithm. Finally, images were processed by Laplacian pyramid decomposition algorithm to make the image joint seemed smooth and natural. The results of experiments and evaluation criteria confirm that the new method has high robustness in the process of medical image registration and stitching in the network.

Anomaly Detection of Trackside Equipment Based on GPS and Image Matching

The health of trackside equipment often seriously affects the safe driving of the train, while manually checking their status is an indispensably laborious task. In order to automate the task, this paper addresses the problem of automatically and accurately detecting anomalies of equipment located along the track through GPS and image calibration techniques. Considering the unnoticeable changes in equipment, including screws missing and cable corrosion, detection by classification-based machine learning methods is difficult to implement, thus in this paper we propose and conduct a novel detection mechanism by an efficient way of image subtraction. Especially, our method consists of four steps. The first step is to collect images of the trackside equipment and their corresponding mileage in the same route several times through cameras and GPS devices installed in the inspection train. Then, by introducing an improved RANSAC algorithm, the GPS data is further corrected. Secondly, we define one pass of the collected image data along with GPS information as template, and for the rest passes that need to be detected, the first frame alignment operation is operated through GPS and image information. For the third step, the SURF algorithm is implemented for image matching, and then the subtraction operation is conducted between each matched image pairs. Finally, we use empirical filtering mechanism to remove false positives that we have detected. Experimental results demonstrate the efficiency and effectiveness of our proposed method for anomalies detection of trackside equipment.