| 基于图像处理的深海底障碍物和地形识别及检测 |
| |
| 引用本文： | 王财政,杨耀东,冯雅丽,张文明,高峰飞.基于图像处理的深海底障碍物和地形识别及检测[J].北京科技大学学报,2011(7):777-784. |
| |
| 作者姓名： | 王财政 杨耀东 冯雅丽 张文明 高峰飞 |
| |
| 作者单位： | 北京科技大学土木与环境工程学院; |
| |
| 基金项目： | 国家自然科学基金资助项目(No.50874006); 国际海底区域性研究开发“十一五”项目(No.DYXM-115-04-02-03) |
| |
| 摘 要： | 针对海底集矿机采矿环境图像,采用分段线性变换提高图像细节,中值滤波去除悬浮物干扰.利用形态学抗噪声梯度算子提取地形和障碍物轮廓,并用分段线性拟合计算出地表亮度变化率.根据表面亮度变化特征判断障碍物类型,采用自适应形态学对轮廓进行细化与连接.通过障碍投影变换计算出障碍物的距离、高度和宽度等信息.对陆地图像进行了分析,证明位置、高度和坡度等参数计算的可行性.利用上述方法对深海底的图像进行处理,不仅保留了边界信息,且提高了抗干扰能力和抗边界间相互影响能力,可有效识别深海底地形和障碍物,得出位置和形状等参数,可以为集矿机避障系统信息融合技术提供可靠数据.
|
| 关 键 词： | 海洋工程 采矿 形态学 图像处理 图像识别 |
Identification and detection of deep-sea obstacles and terrains based on image processing |
| |
| WANG Cai-zheng,YANG Yao-dong,FENG Ya-li,ZHANG Wen-ming,GAO Feng-fei School of Civil , Environmental Engineering,University of Science , Technology Beijing,Beijing ,China.Identification and detection of deep-sea obstacles and terrains based on image processing[J].Journal of University of Science and Technology Beijing,2011(7):777-784. |
| |
| Authors: | WANG Cai-zheng YANG Yao-dong FENG Ya-li ZHANG Wen-ming GAO Feng-fei School of Civil Environmental Engineering University of Science Technology Beijing Beijing China |
| |
| Institution: | WANG Cai-zheng,YANG Yao-dong,FENG Ya-li,ZHANG Wen-ming,GAO Feng-fei School of Civil and Environmental Engineering,University of Science and Technology Beijing,Beijing 100083,China |
| |
| Abstract: | Aimed at the mining environment image of a seabed nodule-collecting vehicle,the detail of the image was enhanced by subsection linear transformation,and the interferences of suspensions were removed with a median filter.The profile of terrains and obstacles was extracted by an anti-noise gradient operator in morphology,and the rate of change of surface brightness was computed by subsection-linear fitting.According to the feature of the brightness variation,the type of obstacles was estimated,and the profile... |
| |
| Keywords: | ocean engineering mining topography image processing image recognition |
| 本文献已被 CNKI 等数据库收录！ |
|
