Visible images are always slantwise, simultaneity ground control points layout are not easy, so we must choose one method which can correct the slantwise image based on few reference points. When exterior orientation elements known, the paper can build a correction plane founded on collinearity equations, and then correct the slantwise image using gray interpolation. The corrective effect is very visible, and the speed is rapid.

提出一种基于SA-WPSO的遥感图像校正方法.该方法利用多项式模型对图像进行初步几何校正,得到多项式校正系数后,将模拟退火(SA)思想引入粒子群优化(PSO)算法,通过改进的SA-WPSO算法优化多项式校正系数,在此基础上实现图像的几何校正.实验结果证明,与二次多项式及三次多项式校正方法相比,该方法的校正精度更高、鲁棒性更好.

In recent years,ship detection using synthetic aperture radar (SAR) images is a hot-spot of the research on marine monitoring,has become one of the most effective means.The current SAR ship detection,surveillance,and targeting.This paper reviewed the field of SAR ship detection images nearly 20 years of important research results,and then detection algorithm used in the current theory and detection performance were analyzed and compared,pointing out the advantages and problems of each method,the the development trend of this technical areas was viewed in the end.

Image correction technology is very important both for image mosaic and for measurement. To overcome the defects and limitations of polynomial and TPS models, basing on polynomial and TPS correction models, an improved algorithm is proposed in this paper. In this method, the processing is divided into two stages, global correction and local correction, and different screening methods of GCPs are adopted in different stages. By fully utilizing all GCPs, the respective correction advantages of the two sub-models can be efficiently demonstrated, and, in the meanwhile, the ultra-plus effect of this combination can be stimulated. Eventually, image correction accurcy can be improved. Simulation results show that, comparing with currently available approximate geometric correction methods, this method has high accuracy, good robustness and can effectively coordinate the conflict of the global correction and local correction.

In order to solve the defects of particle swarm optimization (PSO) algorithm such as to be easily trapped in local extremum, converge slowly and optimize poorly at the final evolution stage, an improved PSO (WPSO) is proposed in this paper. Based on the spatial distribution of fitness, the population is divided into three sub-groups. For each sub-group, different strategies are used to maintain the diversity of inertia weight, thus global and local optimization can be ensured at the same time. And three classic test functions are adopted in simulation, comparing with linear decreasing inertia weight PSO algorithm, the results indicate that: the proposed method effectively avoids the premature convergence, significantly improves convergence rate and search capability, and has good robustness.

Image matching is a fast developing technique in image processing.It is widely used in the field of image mosaicking,image fusion,military and so on.Image matching is a technique which aims to make two or more images into one system and make them as one picture that covers a large region.These technologies are divided into two categories: spatial-domain and frequency domain.This essay mainly focused on the classical methods of the image matching on the base of drawing lessons from the research results of predecessors,compared different methods from aspects of principles and registration performance and put forward the advantages and disadvantages of each methods.

This paper puts forward a method of target recognition based on multi-feature integration and polar coordinates transformation.It uses multi-feature fusion method to extract from the original image to be identified to achieve the objective dimension of compression tasks.The polar coordinate and Fast Fourier Transform(FFT) method are introduced to determine the invariant features of the transformed matrix.The targets are classified and recognized by calculating the same correlation of the characteristic matrix and the template features matrix.Experimental results show that this method has good reliability and high recognition rate.

针对作战中航母目标系统子目标选择与排序问题,利用对航母目标系统的打击效果评估系统分析各个子目标损伤对目标系统的影响,确定不同打击方案和目标函数.然后利用遗传算法对打击方案进行优先排序,由此构建了基于打击效果评估的航母子目标选择模型.实验证明:根据实际情况确定终止条件后,可以选择最优作战方案.

Image registration is one of the image processing technologies developed rapidly in recent years.It is an essential step in the fields of image fusion,image mosaic,and super-resolution image processing etc.The new automatic registration technologies for remote sensing images are summarized. Those technologies are divided into three categories:gray level-based regional registration,image feature-based registration,and image understanding and explanation-based registration.Their principles and registration performance are analyzed and their advantages and disadvantages are pointed out finally.