基于质量扰动鹈鹕优化算法的图像匹配方法研究

Research on Image Matching Method Based on Disturbance Quality Pelican Optimization Algorithm

针对传统群优化算法在图像匹配中存在调节参数多、不易操作等问题,提出了一种基于质量扰动的鹈鹕优化算法(disturbance quality pelican optimization algorithm,DPOA)的图像匹配方法。传统的鹈鹕优化算法(pelican optimization algorithm,POA)在求解多峰函数问题时,其全局收敛性需要进一步改进。首先,引入了一种新的质量扰动方法,通过检测分布点附近的点来收敛到更好的解,提高了在解决多峰函数问题时易陷入局部最优的问题,同时提高了算法的收敛精度。其次,通过数据集CEC2019对算法的有效性进行评价。最后,通过提取图像的方向梯度直方图(histogram of oriented gradient,HOG)将DPOA算法在图像匹配中应用,并通过实验仿真,证明了DPOA算法在图像匹配中的可行性与有效性。

A disturbance quality pelican optimization algorithm for image matching was proposed as an answer to the problems of the traditional swarm optimization algorithm in image matching,such as the difficulty of operating many adjustment parameters.The traditional pelican optimization algorithm(POA)had a global convergence property,and requried further improvement when solving multi-peak function problems.Firstly,a new disturbance quality method was introduced,which could detect points near the distribution points,thereby improving the problem of local optima tendency when solving multi-peak function problems and increasing the convergence accuracy of the algorithm.Secondly,the effectiveness of the algorithm was evaluated using the CEC2019 dataset.Finally,the DPOA algorithm was applied to image matching by extracting the histogram of oriented gradient(HOG)of the image,the feasibility and effectiveness of the DPOA algorithm in image matching was demonstrated through experimental simulations.