Entity

Time filter

Source Type


Gui Y.,National University of Defense Technology | Gui Y.,Hunan Key Laboratory for Image Measurement and Vision Navigation | Bai X.,Beijing Institute of Technology | Li Z.,Chinese Institute of Scientific and Technical Information | And 2 more authors.
2012 12th International Conference on Control, Automation, Robotics and Vision, ICARCV 2012 | Year: 2012

A novel approach is presented for color image segmentation. By incorporating the advantages of mean shift (MS) segmentation and spectral clustering (SC) method, the proposed approach provides effective and robust segmentation. Firstly, input image is transformed from a pixel-based to a region-based model by using the MS algorithm. The input image after MS segmentation is composed of multiple disjoint regions that preserve the desirable discontinuity characteristics of the image. Then the regions are treated as nodes in the image plane and a graph structure is applied to represent them. The final step is to apply the improved SC to perform globally optimal clustering. To avoid some incorrect partitioning when considering each region as one graph node, we assign different numbers of nodes to represent the regions according to area ratios among the regions. In addition, K-harmonic means (KHM) instead of K-means is applied in the improved SC procedure in order to enhance its stability and performance. The superiority of the proposed approach is demonstrated and examined through a mass of experiments using color images. © 2012 IEEE.


Gui Y.,National University of Defense Technology | Gui Y.,Hunan Key Laboratory for Image Measurement and Vision Navigation | Zhang X.,National University of Defense Technology | Zhang X.,Hunan Key Laboratory for Image Measurement and Vision Navigation | And 2 more authors.
Eurasip Journal on Advances in Signal Processing | Year: 2012

A novel approach is presented for synthetic aperture radar (SAR) image segmentation. By incorporating the advantages of maximally stable extremal regions (MSER) algorithm and spectral clustering (SC) method, the proposed approach provides effective and robust segmentation. First, the input image is transformed from a pixelbased to a region-based model by using the MSER algorithm. The input image after MSER procedure is composed of some disjoint regions. Then the regions are treated as nodes in the image plane, and a graph structure is applied to represent them. Finally, the improved SC is used to perform globally optimal clustering, by which the result of image segmentation can be generated. To avoid some incorrect partitioning when considering each region as one graph node, we assign different numbers of nodes to represent the regions according to area ratios among the regions. In addition, K-harmonic means instead of K-means is applied in the improved SC procedure in order to raise its stability and performance. Experimental results show that the proposed approach is effective on SAR image segmentation and has the advantage of calculating quickly. © 2012 Gui et al.


Gui Y.,National University of Defense Technology | Gui Y.,Hunan Key Laboratory for Image Measurement and Vision Navigation | Su A.,National University of Defense Technology | Su A.,Hunan Key Laboratory for Image Measurement and Vision Navigation | And 2 more authors.
Optik | Year: 2013

Point-pattern matching is an important topic in the fields of computer vision and pattern recognition. We present a novel point-pattern matching method based on Speeded Up Robust Feature (SURF) and Shape Context to increase the matching accuracy. In the original point-pattern matching method using SURF algorithm, incorrect matching point pairs are likely to be produced and are difficult to be eliminated only by using information of image regions around the feature points. In the proposed method, firstly, SURF bidirectional matching method is applied to match the feature points in two images preliminarily. Then Shape Context descriptors are calculated for the feature points so that the information of relative positions among the feature points can be integrated in this way. Finally, incorrect matching point pairs can be eliminated gradually by an iteration method. Experiment results show that the proposed method can eliminate incorrect matching point pairs effectively and increase the accuracy of point-pattern matching. © 2012 Elsevier GmbH.


Chao Z.-C.,National University of Defense Technology | Chao Z.-C.,Hunan Key Laboratory for Image Measurement and Vision Navigation | Yu Q.-F.,Hunan Key Laboratory for Image Measurement and Vision Navigation | Yu Q.-F.,National University of Defense Technology | And 4 more authors.
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2011

Traditional videometric approach cannot be used to measure the pose deformation of objects in a large viewing field or of non-intervisible objects in the large structures, however, pose-relay videometric using camera series or camera network can be used to overcome the difficulties. It is a usual practice to fuse the pose data by using the constrained conditions abounding in the camera network in order to improve the measurement precision. This article first provides a brief introduction to the principle underlying the method of camera network videometric and an analysis of its constraint conditions in light of the graph theory; then it proposes and experiments on an adjustment-based data fusion method in the pose relay videometric using camera network; finally, it manifests a numerical simulation on the proposed method. The results show that it is able to effectively suppress noises and improve the measurement precision because they can take full advantages of the constraint conditions intrinsic to the camera network. © 2011 SPIE.


Yu Q.,National University of Defense Technology | Yu Q.,Hunan Key Laboratory for Image Measurement and Vision Navigation | Sun X.,National University of Defense Technology | Sun X.,Hunan Key Laboratory for Image Measurement and Vision Navigation | And 9 more authors.
Science China Technological Sciences | Year: 2011

This article proposes a relay camera videometrics based method to convert an unstable measuring platform to a static reference to solve the problems of large error or invalidation caused by measuring platform instability in photogrammetric and videometric measurements. The method installs a relay camera on the unstable platform and captures images of a reference marker fixed on a static reference or vice versa to resolve the 3D movement of the unstable platform relative to the static reference, based on which it corrects the error of the measured results and thus eliminating the influence of the platform movement. It finds new and important applications for videometrics by making high-precision dynamic measurement possible on unstable platforms. Verification experiments and numerical simulations have proven its validity and practicability. © 2011 Science China Press and Springer-Verlag Berlin Heidelberg.

Discover hidden collaborations