Corner Matching Method Research Articles

A marker-less assembly stage recognition method based on corner feature

Fast and robust product assembly stage recognition is a key step in human–machine cooperative assembly. To solve the recognition problem of similar adjacent assembly stages, a marker-less assembly stage recognition method is proposed based on corner feature between an assembling product and a digital model. Considering the geometric features of mechanical products, a corner identification method is proposed based on the circumferential angle difference (CADF). Then a corner matching method based on distance constraint is studied for ICP registration to realize the point cloud registration between the product and digital model. Based on the registration relationship, a similarity algorithm based on proximity point proportion is used to calculate the similarity between models and the input assembling product. The model with the greatest similarity is taken as the stage recognition result. In experiments on four group assembling products, the average stage recognition accuracy is 96.15%, which indicates that the proposed method can solve the stage recognition problem. The corner identification method based on the CADF outperforms the Harris-3D corner detection method in the efficiency of assembly stage recognition.

Moving Target Localization in Sports Image Sequence Based on Optimized Particle Filter Hybrid Tracking Algorithm

This paper proposes a fusion stadium positioning algorithm, which uses self-optimizing particle filter to integrate the improved athlete dead reckoning and WiFi position fingerprint algorithm for stadium positioning. In order to determine the initial absolute position of the stadium positioning, for athletes entering the stadium from the outside, a seamless switching algorithm outside the stadium is proposed, using the characteristics of high-altitude satellite GPS to find a suitable switching point as the initial absolute position. If in the stadium, WiFi static positioning determines the initial absolute position. Then, aiming at the problem that the poorly diversified particles cannot be better integrated and localized, a self-optimized particle filter algorithm is proposed. After resampling and retaining high-weight particles, the characteristics of low-weight particles are embedded in the copied high-weight particles. This can improve diversity, and we finally carry out fusion positioning. The target tracking algorithm based on Mean Shift has a fixed-scale tracking window, and the tracking effect of variable-size targets is not ideal. In this paper, an affine transformation algorithm is introduced to improve it. First, we iterate the adjacent image frames in reverse Mean Shift to determine the center position of the target and then use the corner matching method to perform template matching on the target to adjust the size of the tracking window. Through simulation verification, it is proved that the optimized particle filter hybrid tracking algorithm can achieve the ideal result when the target size changes. For the image sequence S1, the tracking window of the 20th frame and the 40th frame has a small offset, but the optimal position can be quickly found by Mean Shift iteration. For the image sequence S2, between the 40th frame and the 60th frame, the target occlusion causes the accuracy of the target template to decrease, and the Bhattacharyya coefficient is at a relatively low value. For the image sequence S3, the tracking effect of the optimized particle filter hybrid tracking algorithm meets the requirements.

An anchor-free object detector with novel corner matching method

Recently, remarkable object detection performance has been made by keypoint-based detectors with different keypoint matching strategies. However, the factors considered in most of keypoint matching strategies are not comprehensive, which greatly affects the detection results. In this paper, based on CornerNet we propose a novel anchor-free detector with a brand new keypoint matching method. In our approach, instead of using embedding of each corner to achieve keypoint matching like CornerNet, we predict a matching degree score for each predicted bounding box formed by corners. In order to train model to get accurate matching degree prediction results, we fully consider the location and geometric information of targets, calculating the distance between centers of predicted and ground truth bounding boxes as well as IoU value to decide which pair of top-left and bottom-right corners can form the right bounding box. Besides that, to relieve the problem that categorical predictions associated with corners are not always reliable, we set an additional classification score for each predicted bounding boxes to further promote final detection results. We apply our model on MS-COCO test−dev set for evaluation and the result shows that our method achieves an AP of 46.3 % at single-scale and 47.9% at multi-scale, which are competitive with other state-of-the-art models such as CentripetalNet and Corner Proposal Net (CPN).

Robust Harris Corner Matching Based on the Quasi-Homography Transform and Self-Adaptive Window for Wide-Baseline Stereo Images

Corner feature matching remains a difficult task for wide-baseline images because of viewpoint distortion, surface discontinuities, and partial occlusions. In this paper, we propose a robust Harris corner matching method based on the quasi-homography transform (QHT) and self-adaptive window. Our method is divided into three steps. First, high-quality Harris corners were extracted from stereo images using optimal detecting, and initial matches were simultaneously acquired by integrating complementary affine-invariant features and the scale-invariant feature transform descriptor. Second, the pair of fundamental matrices was estimated based on the initial matches and improved random sample consensus algorithm. Subsequently, the global QHT was produced by duplicate epipolar geometries. Third, conjugate Harris corners were obtained by combining QHT and normalized cross correlation, and the accuracy of the corresponding points was further improved based on self-adaptive least-squares matching (SALSM). Experiments on six groups of wide-baseline images demonstrate the effectiveness of the proposed method, and a comprehensive comparison with the existing corner matching algorithms indicates that our method has notable superiority in terms of accuracy and distribution. The main contribution of this paper is that the proposed global QHT can reduce the search range effectively for candidates, and the proposed SALSM can notably improve the accuracy of the corresponding corners.

Brain medical image diagnosis based on corners with importance-values

BackgroundBrain disorders are one of the top causes of human death. Generally, neurologists analyze brain medical images for diagnosis. In the image analysis field, corners are one of the most important features, which makes corner detection and matching studies essential. However, existing corner detection studies do not consider the domain information of brain. This leads to many useless corners and the loss of significant information. Regarding corner matching, the uncertainty and structure of brain are not employed in existing methods. Moreover, most corner matching studies are used for 3D image registration. They are inapplicable for 2D brain image diagnosis because of the different mechanisms. To address these problems, we propose a novel corner-based brain medical image classification method. Specifically, we automatically extract multilayer texture images (MTIs) which embody diagnostic information from neurologists. Moreover, we present a corner matching method utilizing the uncertainty and structure of brain medical images and a bipartite graph model. Finally, we propose a similarity calculation method for diagnosis.ResultsBrain CT and MRI image sets are utilized to evaluate the proposed method. First, classifiers are trained in N-fold cross-validation analysis to produce the best θ and K. Then independent brain image sets are tested to evaluate the classifiers. Moreover, the classifiers are also compared with advanced brain image classification studies. For the brain CT image set, the proposed classifier outperforms the comparison methods by at least 8% on accuracy and 2.4% on F1-score. Regarding the brain MRI image set, the proposed classifier is superior to the comparison methods by more than 7.3% on accuracy and 4.9% on F1-score. Results also demonstrate that the proposed method is robust to different intensity ranges of brain medical image.ConclusionsIn this study, we develop a robust corner-based brain medical image classifier. Specifically, we propose a corner detection method utilizing the diagnostic information from neurologists and a corner matching method based on the uncertainty and structure of brain medical images. Additionally, we present a similarity calculation method for brain image classification. Experimental results on two brain image sets show the proposed corner-based brain medical image classifier outperforms the state-of-the-art studies.

Corner matching method of constraints of distance combining local and global information

Image matching technology has important applications in many fields.A corner matching method of the constraints of distance was proposed to solve the rotation and translation problem between two images.Firstly the values of corners were utilized to achieve coarse matching election,and then the local and global distance between the corners was combined to select the matching corners.The experimental results show that the methods can achieve accurate matching of no unmatched conners with high accuracy,certain robustness to noise,and as a result of the main use of the distance relationship between two corners without complex calculations in the matching process,so it achieves a substantial reduction in matching time,and also has the practical value.

A model-based machine vision system using fuzzy logic

An effective model-based machine vision system is designed for use in practical production lines. In the proposed system, the gray level corner is selected as a local feature, and a gray level corner detector is developed. The gray level corner detection problem is formulated as a pattern classification problem to determine whether a pixel belongs to the class of corners or not. The probability density function is estimated by means of fuzzy logic. A corner matching method is developed to minimize the amount of calculation. All available information obtained from the gray level corner detector is used to make the model. From a fuzzy inference procedure, a matched segment list is extracted, and the resulted segment list is used to calculate the transformations between the model object and each object in the scene. In order to reduce the fuzzy rule set, a notion of overlapping cost is introduced. To show the effectiveness of the developed algorithm, simulations are conducted for synthetic images, and an experiment is conducted on an image of a real industrial component.