CAJ | 학술논문

针对粒子群优化算法应用在目标跟踪时，其惯性权重调节机制的局限性，提出了改进的粒子群优化目标跟踪方法。首先，对目标及粒子群算法中相应参数进行初始化；接着，引入粒子进化率的概念，对惯性权重调节机制进行改进，根据每代每个粒子的不同状态及时调整惯性权重；然后，在更新粒子的速度和位置的同时，更新个体最优解和全局最优解，进行下一次迭代；最后，比较粒子的适应度，选择相似性函数值最大的区域为目标。实验结果表明，该方法与使用自适应惯性权重调节机制的粒子群优化目标跟踪方法相比，减少了获取相同适应度所需的迭代次数，运算效率提高了42.9％。实现了目标在相似性函数出现“多峰”情况下的准确定位，对目标出现部分遮挡的情况具有很好的适应性。
침대입자군우화산법응용재목표근종시，기관성권중조절궤제적국한성，제출료개진적입자군우화목표근종방법。수선，대목표급입자군산법중상응삼수진행초시화；접착，인입입자진화솔적개념，대관성권중조절궤제진행개진，근거매대매개입자적불동상태급시조정관성권중；연후，재경신입자적속도화위치적동시，경신개체최우해화전국최우해，진행하일차질대；최후，비교입자적괄응도，선택상사성함수치최대적구역위목표。실험결과표명，해방법여사용자괄응관성권중조절궤제적입자군우화목표근종방법상비，감소료획취상동괄응도소수적질대차수，운산효솔제고료42.9％。실현료목표재상사성함수출현“다봉”정황하적준학정위，대목표출현부분차당적정황구유흔호적괄응성。
To overcome the limitations of inertia weight adjustment mechanism when the particle swarm optimi -zation algorithm is applied to object tracking , an improved particle swarm optimization object tracking algo-rithm is proposed.Firstly, the object and the parameters in particle swarm optimization algorithm are initial-ized.Secondly, the inertia weight adjustment mechanism is improved by using the evolution rate of particle , and the inertia weight is achieved by taking the conditions of different particles in each generation into consid -eration .Then the speed , the position , the individual optimum and the global optimum of the particles are up-dated simultaneously while the next iteration is proceeding .Finally, the area which has the largest similarity function value is defined as the object by comparing the fitness value of each particle with the others .Experi-mental results indicate that the method reduces the iterations to obtain the same fitness value , and improves the operation efficiency by 42.9% in comparison with the particle swarm optimization object tracking method which uses self-adapted inertia weight adjustment mechanism .The accurate positioning of the object is a-chieved in the case of the similarity function presenting “multimodal”, and the method is well adapted to the situation when partial occlusion occurs in object tracking .