Time filter

Source Type

Miao X.,CAS Shenyang Institute of Automation | Miao X.,University of Chinese Academy of Sciences | Miao X.,Chinese Academy of Sciences | Miao X.,Key Laboratory of Image Understanding and Computer Vision | And 13 more authors.
Guangxue Xuebao/Acta Optica Sinica | Year: 2013

Docking ring is a typical component on space vehicle, which can provide a single circle feature. But monocular vision pose estimation based on single circle with two solutions, which can not be applied to practical engineering application. In order to exclude the interference of false solution, a new method of removing the false solution using Euclidean distance invariance as a constraint is proposed to solve the pose ambiguity, and the paper gives the proof of a unique solution under the constraint. The error simulation analyses of the method are done, and feasible strategies to improve the measurement accuracy are given. According to the projection of the circle on the image, two pose solutions of the circle are calculated. Then a reference point on the circle supporting plane outside the circle is selected. The distance between the reference point and circle center is Euclidean invariant and prior knowledge, which can be used for a constraint to exclude the false solution to get the uniquely correct solution. The effectiveness and superiority of the method are verified by numerical simulation and experiments. Experimental results indicate that the method is robust to the noise, can get the right solution, requires least constraint conditions for the circle, and the calculation process is simple. Pose results are stable and reliable, and more accurate. The relative error of the circle center is less than 0.5%, and the absolute error of pose angle is less than 0.8°.

Luo H.,CAS Shenyang Institute of Automation | Luo H.,Chinese Academy of Sciences | Luo H.,Key Laboratory of Image Understanding and Computer Vision | Chang Z.,CAS Shenyang Institute of Automation | And 5 more authors.
Hongwai yu Jiguang Gongcheng/Infrared and Laser Engineering | Year: 2011

Target tracking with local non-texture is a difficult point and hot topic in the field of ground imaging guidance. Since the automatic suitable-matching area selection is an effective method to solve this problem, an algorithm of automatic suitable-matching area selection based on multi-feature fusion was proposed. Firstly, the edge density, the average edge strength, the edge direction dispersion degree and the space distance were integrated to form a suitable-matching measure function. Then, the credibility of suitable-matching of each point in the image was calculated by this function. Lastly, through developing adaptive selection strategy to the suitable-matching area, three suitable-matching areas with high credibility were segmented as target template for matching tracking. Experimental results show that the segmented suitable-matching area with proposed algorithm can achieve more tracking precision compared with the results judged by the human experience. This proposed algorithm can be widely used in the applications of the ground imaging-guided target tracking with local non-texture target and the scene matching task planning.

Zhang H.-H.,CAS Shenyang Institute of Automation | Zhang H.-H.,University of Chinese Academy of Sciences | Luo H.-B.,CAS Shenyang Institute of Automation | Luo H.-B.,Chinese Academy of Sciences | And 3 more authors.
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2014

Due to the restriction of infrared imaging component and the radiation of atmosphere, Infrared images are discontented with image contrast, blurry, large yawp. Aimed on these problems, A multi-scale image enhancement algorithm is proposed. The main principle is as follows: firstly, On the basis of the multi-scale image decomposition, We use an edge-preserving spatial filter that instead of the Gaussion filter proposed in the original version, adjust the scale-dependent factor With a weighted information. Secondly, Contrast is equalized by applying nonlinear amplification. Thirdly, Subband image is the weighted sum of sampled subband image and subsampled then upsampled subband image by a factor of two. Finally, Image reconstruction was applied. Experiment results show that the proposed method can enhance the original infrared image effectively and improve the contrast, moreover, it also can reserve the details and edges of the image well. © 2014 SPIE.

Liu Y.,CAS Shenyang Institute of Automation | Liu Y.,University of Chinese Academy of Sciences | Liu Y.,Chinese Academy of Sciences | Liu Y.,Key Laboratory of Image Understanding and Computer Vision | And 3 more authors.
Eurasip Journal on Advances in Signal Processing | Year: 2010

Region covariance descriptor recently proposed has been approved robust and elegant to describe a region of interest, which has been applied to visual tracking. We develop a geometric method for visual tracking, in which region covariance is used to model objects appearance; then tracking is led by implementing the particle filter with the constraint that the system state lies in a low dimensional manifold: affine Lie group. The sequential Bayesian updating consists of drawing state samples while moving on the manifold geodesics; the region covariance is updated using a novel approach in a Riemannian space. Our main contribution is developing a general particle filtering-based racking algorithm that explicitly take the geometry of affine Lie groups into consideration in deriving the state equation on Lie groups. Theoretic analysis and experimental evaluations demonstrate the promise and effectiveness of the proposed tracking method. Copyright © 2010 Yunpeng Liu et al.

Dong S.,CAS Shenyang Institute of Automation | Dong S.,University of Chinese Academy of Sciences | Dong S.,Chinese Academy of Sciences | Dong S.,Key Laboratory of Image Understanding and Computer Vision | And 3 more authors.
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2015

A high dynamic range infrared image of the sea surface scene includes the effects due to the sea clutter, mirror reflections from the wave facets, which decrease the visibility of the ship targets and their details. This paper provides an efficient adaptive enhancement technique for ship targets based on bilateral filtering and visual saliency detection. The 14- bit raw image is separated into a detail layer and a base layer by applying an adaptive bilateral filter. Then the two layers are processed separately and added afterward. Hereafter by employing visual saliency detection we can get the gain matrix to improve the contrast of ship targets. Finally, the image whose contrast is improved is quantized to the display range. The strength of our proposed method lies in its ability to inhibit the sea clutter and adaptability in different sea surface scene and shows a better performance in the contrast of the ship targets and the visibility of their details. © 2015 SPIE.

Chen H.,CAS Shenyang Institute of Automation | Chen H.,University of Chinese Academy of Sciences | Chen H.,Chinese Academy of Sciences | Chen H.,Key Laboratory of Image Understanding and Computer Vision | And 3 more authors.
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2015

With the development of modern military, infrared imaging technology is widely used in this field. However, limited by the mechanism of infrared imaging and the detector, infrared images have the disadvantages of low contrast and blurry edge by comparison with the visible image. These shortcomings lead infrared image unsuitable to be observed by both human and computer. Thus image enhancement is required. Traditional image enhancement methods on the application of infrared image, without taking into account the human visual properties, is not convenient for the human observation. This article purposes a new method that combines the layering idea with the human visual properties to enhance the infrared image. The proposed method relies on bilateral filtering to separate a base component, which contains the large amplitude signal and must be compressed, from a detail component, which must be expanded because it contains the small signal variations related to fine texture. The base component is mapped into the proper range which is 8-bit using the human visual properties, and the detail component is applied the method of adaptive gain control. Finally, the two parts are recombined and quantized to 8-bit domain. Experimental results show that this algorithm exceeds most current image enhancement methods in solving the problems of low contrast and blurry detail. © 2015 SPIE.

Xu B.,CAS Shenyang Institute of Automation | Xu B.,University of Chinese Academy of Sciences | Xu B.,Chinese Academy of Sciences | Xu B.,Key Laboratory of Image Understanding and Computer Vision | And 7 more authors.
Guangxue Xuebao/Acta Optica Sinica | Year: 2011

Modulation transfer function (MTF) is one of significant parameters for designing and evaluating an electro-optical imaging system. By proving the linear relation between an edge spread function and an inverse cumulative histogram of edge, an MTF measurement method based on statistical histogram is presented. Simulation and experiment including optics and detectors are designed. Physical experimental platform including an integrating sphere, target, collimator, digital camera and other devices is developed. Taking the theoretical model and design parameters of electro-optical imaging system as a reference, the validity of our measurement method is verified by the simulation and experiment. Experimental results indicate that, comparing with the existing MTF measurement method, the proposed method can overcome the phase effects which is caused by under-sampling of imaging detector. It is more robust to angle of knife edge and noisy environment, and can measure response properties beyond the sampling frequency of an electro-optical imaging system.

Ma J.,CAS Shenyang Institute of Automation | Luo H.,University of Chinese Academy of Sciences | Chang Z.,Chinese Academy of Sciences | Hui B.,Key Laboratory of Image Understanding and Computer Vision
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2014

In this paper, we propose a robust tracking method for infrared object. We introduce the appearance model and the sparse representation in the framework of particle filter to achieve this goal. Representing every candidate image patch as a linear combination of bases in the subspace which is spanned by the target templates is the mechanism behind this method. The natural property, that if the candidate image patch is the target so the coefficient vector must be sparse, can ensure our algorithm successfully. Firstly, the target must be indicated manually in the first frame of the video, then construct the dictionary using the appearance model of the target templates. Secondly, the candidate image patches are selected in following frames and the sparse coefficient vectors of them are calculated via ℓ1-norm minimization algorithm. According to the sparse coefficient vectors the right candidates is determined as the target. Finally, the target templates update dynamically to cope with appearance change in the tracking process. This paper also addresses the problem of scale changing and the rotation of the target occurring in tracking. Theoretic analysis and experimental results show that the proposed algorithm is effective and robust. © 2014 SPIE.

Sun Z.,CAS Shenyang Institute of Automation | Sun Z.,University of Chinese Academy of Sciences | Sun Z.,Chinese Academy of Sciences | Sun Z.,Key Laboratory of Image Understanding and Computer Vision | And 3 more authors.
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2014

Detection of visually salient objects plays an important role in applications such as object segmentation, adaptive compression, object recognition, etc. A simple and computationally efficient method is presented in this paper for detecting visually salient objects in Infrared Radiation images. The proposed method can be divided into three steps. Firstly, the infrared image is pre-processed to increase the contrast between objects and background. Secondly, the spectral residual of the pre-processed image is extracted in the log spectrum, then via corresponding inverse transform and threshold segmentation we can get the rough regions of the salient objects. Finally, we apply a sliding window to acquire the explicit position of the salient objects using the probabilistic interpretation of the semi-local feature contrast which is estimated by comparing the gray level distribution of the object and the surrounding area in the original image. And as we change the size of the sliding window, different size of objects can be found out. In our proposed method, the first two steps combined together to play a role in narrowing the searching region and thus accelerating computation. The third procedure is applied to extract the salient objects. We test our method on abundant amount of Infrared Radiation images, and the results show that our saliency detection based object detection method is effective and robust. © 2014 SPIE.

Shao C.,CAS Shenyang Institute of Automation | Shao C.,University of Chinese Academy of Sciences | Shao C.,Chinese Academy of Sciences | Ding Q.,Research Institute of General Development and Demonstration of Equipment | And 3 more authors.
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2014

Affine invariant feature computing method is an important part of statistical pattern recognition due to the robustness, repeatability, distinguishability and wildly applicability of affine invariant feature. Multi-Scale Autoconvolution (MSA) is a transformation proposed by Esa Rathu which can get complete affine invariant feature. Rathu proved that the linear relationship of any four non-colinear points is affine invariant. The transform is based on a probabilistic interpretation of the image function. The performance of MSA transform is better on image occlusion and noise, but it is sensitive to illumination variation. Aim at this problem, an improved MSA transform is proposed in this paper by computing the map of included angle between N-domain vectors. The proposed method is based on the probabilistic interpretation of N-domain vectors included angle map. N-domain vectors included angle map is built through computing the vectors included angle where the vectors are composed of the image point and its N-domain image points. This is due to that the linear relationship of included angles between vectors composed of any four non-colinear points is an affine invariance. This paper proves the method can be derived in mathematical aspect. The transform values can be used as descriptors for affine invariant pattern classification. The main contribution of this paper is applying the N-domain vectors included angle map while taking the N-domain vector included angle as the probability of the pixel. This computing method adapts the illumination variation better than taking the gray value of the pixel as the probability. We illustrate the performance of improved MSA transform in various object classification tasks. As shown by a comparison with the original MSA transform based descriptors and affine invariant moments, the proposed method appears to be better to cope with illumination variation, image occlusion and image noise. © 2014 SPIE.

Loading Key Laboratory of Image Understanding and Computer Vision collaborators
Loading Key Laboratory of Image Understanding and Computer Vision collaborators