电子测量与仪器学报

尹胜楠,崔学荣,李娟,李世宝.基于快速 ACE 算法的视觉里程计图像增强方法[J].电子测量与仪器学报,2021,35(6):27-33

基于快速 ACE 算法的视觉里程计图像增强方法

Image enhancement method of visual odometer based on fast ACE algorithm

DOI：

英文关键词:visual odometry image enhancement feature extraction feature matching

基金项目:国家自然科学基金(61902431, 91938204, 61972417)、山东省重点研发项目（2019GGX101048）、中央高校基本科研业务费专项基金(19CX05003A-9，18CX02136A)、潍坊市科技计划项目(2019ZJ1063)资助

作者	单位
尹胜楠	1. 中国石油大学(华东)计算机科学与技术学院
崔学荣	2. 中国石油大学(华东)海洋与空间信息学院
李娟	1. 中国石油大学(华东)计算机科学与技术学院
李世宝	2. 中国石油大学(华东)海洋与空间信息学院

Author	Institution
Yin Shengnan	1. College of Oceanography and Space Informatics, China University of Petroleum (East China),
Cui Xuerong	2. College of Computer Science and Technology, China University of Petroleum (East China)
Li Juan	1. College of Oceanography and Space Informatics, China University of Petroleum (East China),
Li Shibao	2. College of Computer Science and Technology, China University of Petroleum (East China)

摘要点击次数: 644

全文下载次数: 3

中文摘要:

为提高同时定位与地图构建(simultaneous localization and mapping,SLAM)在室内定位的不同场景下的鲁棒性,应对室内场景纹理少,光线差等极端环境的挑战。通过利用改进快速自动彩色增强(automatic color enhancement,ACE)图像增强技术, 优化定向 FAST 和旋转 BRIEF(oriented FAST and rotated briEF,ORB)特征点法的前端视觉里程计。同时将原始图像数据、限制对比度自适应直方图均衡( contrast limited adaptive histogram equalization,CLAHE) 增强后、单尺度 Retinex( single scale retinex, SSR)增强后,改进快速 ACE 增强后图像数据应用于楼梯间,地下停车场等不同现实场景中做基于图像质量和特征提取匹配两方面对比实验。实验结果表明,改进快速 ACE 增强后图像质量其他算法,并且视觉里程计(visual odometry,VO)应用该算法增强后提取到的特征点数量增幅达到倍数级,极端环境下匹配数量增幅在 7% ~ 25%,鲁棒性提高。

英文摘要:

In order to improve the robustness of simultaneous localization and mapping (SLAM) in different indoor scenes and deal with the challenges in extreme environments such as less texture and poor light. The visual odometry based on ORB algorithm is improved by using the improved fast automatic color enhancement (ACE) image enhancement technique. At the same time, the original image data, the image data enhanced by contrast limited adaptive histogram equalization (CLAHE), single scale retinex ( SSR), and the improved fast ACE were applied to different real scenes, such as stairwells, subterranean parking lots, and two comparison experiments based on image quality and feature extraction matching are done. The experimental results show that the quality of the image enhanced by the improved fast ACE is better than the other algorithms. After enhancement, the number of feature points of visual odometry (VO) is increased by a multiple order, the matching number is increased by 7% ~ 25% in extreme environments, and the robustness is improved.

查看全文查看/发表评论下载PDF阅读器