摘要
提出将类Haar特征与级联AdaBoost算法应用于输电线路防震锤的识别,以解决目前仅能针对单一防震锤进行识别的问题。首先,基于积分图计算快速得到图像的扩展类Haar特征,然后利用AdaBoost算法选取关键的具有较强分类特性的特征,产生一系列弱分类器以构成强分类器,最后通过级联的方式将强分类器组成级联AdaBoost分类器进行防震锤的分类识别。以实际的航拍图像作为测试样本进行实验,结果表明,该方法能够在复杂背景中有效地识别出防震锤,为后续的防震锤故障的诊断工作奠定了基础。
A research on vibration damper recognition based on Haar-like features and cascade AdaBoost classifier is proposed to solve the problem of only detecting a single vibration damper. At first, the extended Haar-like features are extracted by integral image, then a small set of critical features are chosen to compose complex classifier in the process of training AdaBoost, finally the complex classifiers were combined in a cascade method for vibration damper recognition. Experimental results demonstrate that the proposed method has better performance in recognizing vibration damper from complex background.
出处
《系统仿真学报》
CAS
CSCD
北大核心
2012年第9期1806-1809,共4页
Journal of System Simulation
基金
国家自然科学基金(51177109)