一种新的高分辨率遥感影像道路半自动追踪方法  

A Semi-automatic Road Tracking Method Based on KL Divergence for High-resolution Remote Sensing Imagery

作　　者：刘立志[1,2] 李海涛[2] 韩颜顺[2] 吕剑锋[3] 唐冲[1] 

机构地区：[1]黑龙江工业学院,黑龙江鸡西158100 [2]中国测绘科学研究院,北京100830 [3]黑龙江省测绘地理信息局,哈尔滨150000

出　　处：《遥感信息》2017年第3期104-108,共5页Remote Sensing Information

基　　金：国家科技支撑项目(2012BAH28B03);行业科研专项项目(201412008)

摘　　要：道路自动提取方面的研究研究历史已有40年,由于问题本身的复杂性,其提取精度仍难以达到实际生产的要求。为了改善这一问题,该文提出了一种基于KL散度的道路半自动提取方法,以KL散度作为自动提取算子相似性的量度,并将人工干预作为一个重要因素有机地融入到道路提取过程中,避免了道路自动提取过程中由于各种噪声的影响所带来的误提取,有效提高了道路提取的效率与精度。The research for road automatic extraction has lasted for more than 40 years,but the extraction accuracy still cannot meet the needs of actual production because of the complexity of the problem itself.This paper proposes a method for semi-automatic road extraction based on the KL divergence.During the road extraction process,the KL divergence performs as the measurement of two templates,and human intervention is still put in the process as an important factor to avoid extraction errors brought by all kinds of noises.Experimental results prove that this method can effectively improve the efficiency and precision of the road extraction.

关 键 词：高分辨率 KL散度 道路追踪 半自动 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]