Based on the crosstalk faults of interconnects between IP cores in SOC, this paper presented an implementation method for the model by using the control and operation function of processor core in the SOC. The method ...
详细信息
Based on the crosstalk faults of interconnects between IP cores in SOC, this paper presented an implementation method for the model by using the control and operation function of processor core in the SOC. The method for software implementation needed less hardware burden in comparison with the traditional implementation one based on the hardware. A new IP core framework to improve the detecting speed of crosstalk fault was presented. The improved IP core made the test finished in the real-time and parallel requirement.
A new path planning method of mobile robot in unknown environment using self-learn visual graph is proposed. In this paper, a presentation named by self-learn visual graph (SLVG) is used to represent unknown environme...
详细信息
A new path planning method of mobile robot in unknown environment using self-learn visual graph is proposed. In this paper, a presentation named by self-learn visual graph (SLVG) is used to represent unknown environment, the SLVG is empty at first, when the path planning is conduct, the SLVG is built partly, when the path planning is finished, the SLVG is built completely. On the base of SLVG, a local optimal obstacle avoidance algorithm and a local optimal path planning algorithm are also present in the paper. Experimental results using simulation demonstrate that the method is fast and can produce a local optimal path for mobile robot in unknown environment.
In this paper, a new approach to track rigid objects is presented. The affine transformation method is built and extended. The matching problem which few parameters are used to represent the transformation between the...
详细信息
In this paper, a new approach to track rigid objects is presented. The affine transformation method is built and extended. The matching problem which few parameters are used to represent the transformation between the image and the template is formulated. On the basis of the similarity measurement, a suitable template updating template strategy is proposed. By using these techniques to track objects over several long image sequences, the experimental results show that this image matching method can bear affine image motions and image distortion to some extent and the stability of the algorithm is improved greatly in this way.
The infrared image is enhanced to improve its contrast, and the dim noises are removed by the use of the morphological filters. The segmentation algorithm are presented to separate the target and brighter noises from ...
详细信息
The infrared image is enhanced to improve its contrast, and the dim noises are removed by the use of the morphological filters. The segmentation algorithm are presented to separate the target and brighter noises from the background. According to the algorithm of recursive moving-target-indication (RMTI), the targets in an image sequence are recognized and the moving trajectory of the target is acquired. The experiment results indicate that this method can detect and locate small moving target validly.
Based on the analysis of the nonuniformity noise characteristics in infrared focal plane arrays, an adaptive algorithm for nonuniformity correction in infrared focal plane arrays by using noise canceling technique is ...
详细信息
Based on the analysis of the nonuniformity noise characteristics in infrared focal plane arrays, an adaptive algorithm for nonuniformity correction in infrared focal plane arrays by using noise canceling technique is proposed in this paper. The experiments with real image sequences are made and the results show that the performance of the noise canceling technique is much better than that of the neural networks.
A parallel algorithm for bridge recognition operated in a real-time image processing system is developed based on multiple-bus and multi-DSPs. The pipelining technology is used in the algorithm. It is intensively cons...
详细信息
A parallel algorithm for bridge recognition operated in a real-time image processing system is developed based on multiple-bus and multi-DSPs. The pipelining technology is used in the algorithm. It is intensively considered that the algorithm is partitioned into independent and modular sub-tasks, and these sub-tasks are equally assigned to every DSP. The algorithm is optimized for speeding up and improving efficiency. The experiment results show that the cost of the parallel algorithm is the best optimum with high efficiency.
In this paper, parallel implementation for detecting small targets on infrared sea surface is provided, which a small detection algorithm is adopted based on multi-level filters and real-time image processing system i...
详细信息
In this paper, parallel implementation for detecting small targets on infrared sea surface is provided, which a small detection algorithm is adopted based on multi-level filters and real-time image processing system is operated based on multiple-bus and multi-DSPs designed Optimization of this scheme is carefully discussed to get an optimal parallel implementation in cost and parallel efficiency. The experiment results show the parallel algorithm is feasible and the analysis about the optimization is correct.
The wavelet maxima representation is a new reorganization of an image information in order to solve the image processing problem from the properties of the image edges. The multiscale method of wavelet for edge detect...
详细信息
The wavelet maxima representation is a new reorganization of an image information in order to solve the image processing problem from the properties of the image edges. The multiscale method of wavelet for edge detection and reconstruction is presented. The experiment shows that image approximation may be reconstructed from the wavelet modulus maxima without the visual degradation.
A method of the structure feature extraction, recognition and understanding for airfield is proposed. The linear geometric structure of airfield is extracted after the airfield image is segmented, thinned, broken line...
详细信息
A method of the structure feature extraction, recognition and understanding for airfield is proposed. The linear geometric structure of airfield is extracted after the airfield image is segmented, thinned, broken lines and burr branches deleted. The airfield is recognized according to the parallel lines structure features of main and additional runways and structure feature of Chinese "ri(sun)", "mu(eye)" words consisting of the runways and the paths connecting with them. The geometric structure relationship of various facilities in airfield is finally understood. The experiments show that this method can accurately recognize airfield and understand the various facilities in it.
The recognition method of the harbor target is presented. There are two aspects in the recognition. One is the recognition of the harbor contour, the other is the recognition of the texture of the harbor area on one s...
详细信息
The recognition method of the harbor target is presented. There are two aspects in the recognition. One is the recognition of the harbor contour, the other is the recognition of the texture of the harbor area on one side of the contour. The chain code of the contour represents the orientation and the curvature of the contour, and the control points are detected by the extrema of the wavelet transform after adaptive smoothing. The primitive of the harbor contour is some structure of successive control points. The primitive is recognized by three features related to these points, which are scale-and rotation-invariant.
暂无评论