基于粗-精搜索策略的电线塔鸟巢检测

Coarse-to-fine detection for nests on pylon

在智能输电线路综合监测系统中,高压塔架上的鸟巢对整个电力系统的安全运行带来了极大的威胁。文中基于电线塔上鸟巢的位置以及颜色特性分析,提出了一种基于粗-精搜索策略的电线塔鸟巢检测方法。文中利用了检测和跟踪相结合的方法,针对塔架这类特殊的细结构物体基于特征学习建立相关分类器,并进一步利用鸟巢的颜色特性在候选区域中实现可靠检测。实验结果表明,文中提出的鸟巢检测方法,具有检测准确以及抗干扰能力强的优势。

In an intelligent surveillance system,nets on the pylon bring great threat to the safe operation of the whole electric system. According to the fact that nets always locate on the pylons,this paper proposes a detection method for nets on the pylons based on a coarse to fine searching strategy.Considering that the structures of pylons are very thin and difficult to be distinguished from complex backgrounds,it proposes to establish a classifier of pylons based on sparse HOG features to achieve promising performance of pylon detecting and tracking,which is illustrated to have good invariance to view changes and cluttered background. Given the location of pylons,it can further find out candidate regions of nets based on color filtering. As compared with the traditional methods,the experimental results demonstrate that the proposed pylon net detection method has the advantages of high efficiency,localization accuracy and robustness in varied scenes.