A star map recognition algorithm is proposed. According to the observation accuracy of star sensor, the algorithm eliminates observation error of star triangle before recognition and codes the error-free star triangle...
详细信息
A star map recognition algorithm is proposed. According to the observation accuracy of star sensor, the algorithm eliminates observation error of star triangle before recognition and codes the error-free star triangle to form characteristics quantity. The recognition for navigation triangle can only be carried out on the matching of single characteristics quantity. The combination of multi-triangle improves correct recognition ratio. Simulation experiments show that compared with the traditional triangle algorithm, the proposed algorithm has better timeliness and robustness.
The common method for image matching is correlation matching. The calculating number was very large when correlation function was used between two matching images. Two steps approach was proposed for image matching th...
详细信息
The common method for image matching is correlation matching. The calculating number was very large when correlation function was used between two matching images. Two steps approach was proposed for image matching that was coarse and exact way. Firstly every pixel's gray level was summed up along every column to calculate the mean of column pixels. Then one dimension signal was coarsely matched using one order correlation function. Secondly the points with larger correlation matching values were chosen as the better matching points. These less points were used in the original image as the coordinate origins to calculate the two orders correlation functions. The point with maximum correlation value would be the optimal matching position. Experiences with three kinds of images prove that this approach is faster than conventional one and the matching result is accurate.
The multiple subimage were extracted from the reference image according to a predefined selection method. They were regarded as a template and correlated with the real image. The multiple matching results were integra...
详细信息
The multiple subimage were extracted from the reference image according to a predefined selection method. They were regarded as a template and correlated with the real image. The multiple matching results were integrated with the clustering method based on the spatial relation among the subimages. The confidence of the final matching result was given. The test result showed that the method had improved the performance of correlation-based matching.
Moment invariants are important shape descriptors in computer vision. The method of generating trigonometric function is suggested as a new efficient way to derive various moment invariants. General rule of moment inv...
详细信息
Moment invariants are important shape descriptors in computer vision. The method of generating trigonometric function is suggested as a new efficient way to derive various moment invariants. General rule of moment invariant construction is summarized and the notion of moment invariant space is established. Five more moment invariants are derived and tested. Furthermore, general explicit constructions of some high-order moment invariants are developed. The comparisons are made between the stabilities of several invariants for the discrete image. With the help of these additional moment invariants, we can distinguish the image and the object more accurately.
Aiming at the nonlinearity of photoresponse characteristic in infrared focal plane array (IRFPA), an approach for nonuniformity correction in IRFPA was proposed, which is simple and easy to implement by hardware circu...
详细信息
Aiming at the nonlinearity of photoresponse characteristic in infrared focal plane array (IRFPA), an approach for nonuniformity correction in IRFPA was proposed, which is simple and easy to implement by hardware circuit. The theoretical analysis and comparison of simulation results show that its performance is more perfect than that of the piecewise linear algorithm and the polynomial fitting algorithm, and only a few correction factors are needed.
This paper proposed a method for generating chaotic key stream based on the chaotic map and a fast algorithm to implement it. This method divides the chaotic attractor into 2n symmetric sub-intervals, samples from the...
详细信息
This paper proposed a method for generating chaotic key stream based on the chaotic map and a fast algorithm to implement it. This method divides the chaotic attractor into 2n symmetric sub-intervals, samples from the chaotic orbit every n time intervals, and gets the independently and uniformly distributed 2n-phase key stream. The theoretical and numerical analyses show that the sequence also has a high complexity. This method can be used in fields such as cryptography, numerical simulation and spread spectrum communication, etc.
This paper presents improvements in generation of wideband and high dynamic range analog signal for area-efficient MADBIST, especially for the on-chip testing of wireless communication IF digitizing sigma-delta modula...
详细信息
A FLIR image segmentation algorithm based on genetic algorithm and fuzzy set theory was presented. The method defines different member function for the object and background of the image to transform the image into fu...
详细信息
A FLIR image segmentation algorithm based on genetic algorithm and fuzzy set theory was presented. The method defines different member function for the object and background of the image to transform the image into fuzzy domain with maximum fuzzy entropy. The procedure for finding combination of a, b and c is implemented by genetic algorithm, thresholding image into object and background by maximizing the fuzzy entropy. The experiment results show that our proposed method gives better performance and higher calculation speed than other general methods with good real-time by using genetic algorithm.
The concept of occlusion mesh model is introduced. A novel object tracking algorithm based on occlusion mesh model is proposed. A modified occlusion detection method is considered to improve the detection accuracy. Me...
详细信息
ISBN:
(纸本)0780375084
The concept of occlusion mesh model is introduced. A novel object tracking algorithm based on occlusion mesh model is proposed. A modified occlusion detection method is considered to improve the detection accuracy. Mesh nodes motion estimation method based on feature window matching is presented to achieve sub-pixel resolution and overcome block artifacts produced by block matching. Experiment results indicate that the proposed algorithm is practical and feasible, it can be used to object tracking effectively. Also it solves 2D motion estimation problem existed in occlusion regions and shows better visual performance.
This paper presented a method that incorporates Markov Random Field(MRF), watershed segmentation and merging techniques for performing image segmentation and edge detection tasks. MRF is used to obtain an initial esti...
详细信息
This paper presented a method that incorporates Markov Random Field(MRF), watershed segmentation and merging techniques for performing image segmentation and edge detection tasks. MRF is used to obtain an initial estimate of x regions in the image under process where in MRF model, gray level x , at pixel location i , in an image X , depends on the gray levels of neighboring pixels. The process needs an initial segmented result. An initial segmentation is got based on K means clustering technique and the minimum distance, then the region process in modeled by MRF to obtain an image contains different intensity regions. Starting from this we calculate the gradient values of that image and then employ a watershed technique. When using MRF method it obtains an image that has different intensity regions and has all the edge and region information, then it improves the segmentation result by superimpose closed and an accurate boundary of each region using watershed algorithm. After all pixels of the segmented regions have been processed, a map of primitive region with edges is generated. Finally, a merge process based on averaged mean values is employed. The final segmentation and edge detection result is one closed boundary per actual region in the image.
暂无评论