摘要
将人工蚁群优化算法(AACO)尝试性地引入遥感图像分类,并进行了探索性研究。作为计算智能新的分支,人工蚁群优化算法具有很强的自组织性和自适应性。因此,自然成为科学工程领域一种强有力的信息处理和解决问题的手段;AACO算法利用蚂蚁的生物特性来实现遥感图像分类等非线性操作,具有并行性、鲁棒性。初步试验分析,此方法用于遥感图像分类是有效的,在一定程度上克服传统统计分类方法与ANN方法的某些不足。本文也推动人类利用群智能在遥感图像处理及相关领域的深入研究。
Some initial investigations are conducted to apply Artificial Ant Colony Algorithm (AACO) for classification of remotely sensed images.As a novel branch of computational intelligence,AACO has strong capabilities of Serforganization adaptation,hence it is natural to view AACO as a powerful information processing and problem-solving method in both the scientific and engineering fields.Artificial Ant Colony Algorithm posses nonlinear classification properties along with the biological properties,being parallel operation and insensitiveness to initial condition of images. Preliminary Results indicate effectiveness and application of our method proposed and efficiently avoid some drawbacks of traditional statistical and neural network methods.In addition,our work also push research on this problem further.
出处
《计算机工程与应用》
CSCD
北大核心
2005年第29期77-80,116,共5页
Computer Engineering and Applications
关键词
蚁群优化
人工蚁群
遥感图像
分类
外激素
ant colony optimization,srtificial snt colony,remotely sensed image,classification,pheromone