期刊论文

Research and application of damage detection of highway billboard damage based on vehicle-mounted remote sensing image

中文

测绘通报

0494-0911

2023

CSCD

04

59-63+98

42171418:国家自然科学基金 2020JJ1003:湖南省自然科学基金创新群体项目 2021GK4001:湖南省高新技术产业科技创新引领计划项目

本校为其他机构

现行高速公路广告牌通过人工巡检的管理方式存在低效与交通安全问题，本文提出了一种以车载遥感广告牌影像破损识别为技术支撑的高速公路广告牌巡检新方法。该方法基于改进的SIFT算法和RANSAC算法，在SIFT高斯差分空间极值点选取之前，通过离散余弦变换将描述图像的光强信号转换为频谱信号，同时进行门限操作筛除高频系数，以此提高初始内点集的质量。采用单适应矩阵与RANSAC算法构建透视变换测试模型，计算最佳匹配点后进行精匹配，求取两张互相作差的影像之和，标记并提取迥异的连通域。试验结果表明，本文算法在广告牌破损检测中表现稳健，在多种干扰条件下，检测精度均超过80%,满足高速路广...

There is an inefficient and dangerous problem in the current manual inspection method of highway billboard management,and a new method of highway billboard inspection is proposed with the identification of damaged images of vehicle remote sensing billboards as the techn...MORE There is an inefficient and dangerous problem in the current manual inspection method of highway billboard management,and a new method of highway billboard inspection is proposed with the identification of damaged images of vehicle remote sensing billboards as the technical support.Based on the improved SIFT algorithm an...