Image-Enhancement-for-SLAM:SLAM的图像增强

上传者: 42099755 | 上传时间: 2023-02-20 18:00:48 | 文件大小: 1.87MB | 文件类型: ZIP
C++
Image Enhancement for SLAM 在使用Semi-direct Method跑Euroc Dataset的v103数据时,发现效果很不好。导致错误的主要的原因有:图片太暗,对比度太低;图片亮度变化很大(不限于帧间,左右目有时候也会出现亮度不一致的情况)。于是,需要对输入图像进行预处理,提高图片的对比度,并且使得进行跟踪的两张图片亮度一致。 对于提高图片的对比度,最简单的方法是使用直方图均衡化。不过直方图均衡化有一些很明显的缺点,如变换后细节消失;不自然的过分增强。对于SLAM系统,往往会在过份增强的纹理上提取出一些关键点,而这些关键点我们认为是不稳定的。所以,我们需要一种更加先进的图像增强算法用于SLAM的图像预处理。 本文提出了一种基于Retinex理论的图像增强算法,对欠曝光的图像进行增强, 能够恢复图像中的纹理,并且做到实时处理。 References Paper

文件下载

资源详情

[{"title":"( 37 个子文件 1.87MB ) Image-Enhancement-for-SLAM:SLAM的图像增强","children":[{"title":"Image-Enhancement-for-SLAM-master","children":[{"title":"data","children":[{"title":"2.png <span style='color:#111;'> 70.98KB </span>","children":null,"spread":false},{"title":"3.png <span style='color:#111;'> 118.60KB </span>","children":null,"spread":false},{"title":"2_enhanced.png <span style='color:#111;'> 70.27KB </span>","children":null,"spread":false},{"title":"1_enhanced.png <span style='color:#111;'> 741.12KB </span>","children":null,"spread":false},{"title":"1.png <span style='color:#111;'> 556.49KB </span>","children":null,"spread":false},{"title":"3_enhanced.png <span style='color:#111;'> 143.29KB </span>","children":null,"spread":false}],"spread":true},{"title":"src","children":[{"title":"image_enhance","children":[{"title":"image_enhance.cpp <span style='color:#111;'> 7.70KB </span>","children":null,"spread":false},{"title":"fgs_filter.cpp <span style='color:#111;'> 24.43KB </span>","children":null,"spread":false},{"title":"CMakeLists.txt <span style='color:#111;'> 493B </span>","children":null,"spread":false}],"spread":true},{"title":"CMakeLists.txt <span style='color:#111;'> 31B </span>","children":null,"spread":false}],"spread":true},{"title":"LICENSE <span style='color:#111;'> 17.67KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 2.82KB </span>","children":null,"spread":false},{"title":"tests","children":[{"title":"test_image_enhance.cpp <span style='color:#111;'> 1.83KB </span>","children":null,"spread":false},{"title":"CMakeLists.txt <span style='color:#111;'> 340B </span>","children":null,"spread":false}],"spread":true},{"title":"include","children":[{"title":"image_enhance","children":[{"title":"image_enhance.h <span style='color:#111;'> 1.94KB </span>","children":null,"spread":false},{"title":"fgs_filter.h <span style='color:#111;'> 3.30KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"thirdparty","children":[{"title":"opencv-3.4","children":[{"title":"opencv2","children":[{"title":"core","children":[{"title":"cvdef.h <span style='color:#111;'> 15.53KB </span>","children":null,"spread":false},{"title":"cv_cpu_dispatch.h <span style='color:#111;'> 5.46KB </span>","children":null,"spread":false},{"title":"hal","children":[{"title":"intrin_sse.hpp <span style='color:#111;'> 84.73KB </span>","children":null,"spread":false},{"title":"intrin.hpp <span style='color:#111;'> 13.13KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"video.hpp <span style='color:#111;'> 2.57KB </span>","children":null,"spread":false},{"title":"ts","children":[{"title":"cuda_perf.hpp <span style='color:#111;'> 4.85KB </span>","children":null,"spread":false},{"title":"ts_ext.hpp <span style='color:#111;'> 4.92KB </span>","children":null,"spread":false},{"title":"ts_gtest.h <span style='color:#111;'> 853.80KB </span>","children":null,"spread":false},{"title":"cuda_test.hpp <span style='color:#111;'> 14.57KB </span>","children":null,"spread":false},{"title":"ocl_test.hpp <span style='color:#111;'> 12.91KB </span>","children":null,"spread":false},{"title":"ocl_perf.hpp <span style='color:#111;'> 5.21KB </span>","children":null,"spread":false},{"title":"ts_perf.hpp <span style='color:#111;'> 28.40KB </span>","children":null,"spread":false}],"spread":true},{"title":"ts.hpp <span style='color:#111;'> 22.89KB </span>","children":null,"spread":false},{"title":"video","children":[{"title":"video.hpp <span style='color:#111;'> 2.31KB </span>","children":null,"spread":false},{"title":"tracking.hpp <span style='color:#111;'> 30.67KB </span>","children":null,"spread":false},{"title":"tracking_c.h <span style='color:#111;'> 11.21KB </span>","children":null,"spread":false},{"title":"background_segm.hpp <span style='color:#111;'> 13.39KB </span>","children":null,"spread":false}],"spread":false}],"spread":true},{"title":"lkpyramid.hpp <span style='color:#111;'> 935B </span>","children":null,"spread":false},{"title":"cvconfig.h <span style='color:#111;'> 5.01KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":".vscode","children":[{"title":"settings.json <span style='color:#111;'> 70B </span>","children":null,"spread":false}],"spread":true},{"title":"CMakeLists.txt <span style='color:#111;'> 550B </span>","children":null,"spread":false}],"spread":true}],"spread":true}]

评论信息

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明