CSF又来刷屏了,在 cloudcompare官方论坛 中浏览量已经过万,再有个把月应该就超过cloudcompare引用主贴了,应该一定程度能反映CSF的被关注程度吧。 另外,今天发现CSF文章又有了新的引用,发表一年半已经有11篇SCI引用,最新这篇文章 Investigating the performances of commercial and non-commercial software for ground filtering of UAV-based point clouds 把几个商品化(包括著名的photoscan和global mapper)和免费软件的点云滤波算法进行了详细的对比,结论中说CSF是最优选择,即便是对具有挑战性的质量较差的无人机影像生成的点云。 一些朋友开玩笑说我要靠CSF吹一辈子,但我觉得这没什么,canny、hough、sift不都是一个算法吹一辈子嘛,地球上这么多人,每个人做一件真正有用的事情就不得了。那些只知道灌水和争名夺利的好好反思一下,真正做过一件有用的事情吗? 我不想掩饰为CSF而骄傲,这篇文章幸亏不是国人写的,不然以为找托儿了呢
CSF的第一个正式引用终于出现了,是一篇机载点云地面滤波的综述文章(Chen, Z.; Gao, B.; Devereux, B.State-of-the-Art: DTM Generation Using Airborne LIDAR Data. Sensors 2017 , 17 , 150.),评价是 The results proved that the CSF achieved satisfactory accuracy in most terrain and the post-processing significantly enhances the performance of CSF in steep terrain. 期待后面引用雪崩式爆发。 另外,python下也可以使用CSF了,见项目最新日志。 https://www.researchgate.net/project/CSF-Ground-filtering-of-point-cloud-based-on-Cloth-Simulation
今天突然发现在另外一个帖子里有人对CSF有所反馈,虽然不完美,但已经是很大的肯定了。 over 80 million points(能处理超过8千万个点的数据),very irregular surfaces(非常复杂的地形),performed very well(以前参加ISPRS建筑物三维重建测评时也得到过同样的评价)。 另外,CSF mex在mathworks网站上的30天下载量超过50次,也截屏留念一下。 Re: qCANUPO (classifier files, etc.) Report this post Quote Post by uasghar Wed Dec 14, 2016 3:13 pm wpqjbzwm wrote:Hi, @uasghar. For bare-earth extraction, there is another option. You may try new CSF plugin. (see http://www.danielgm.net/cc/forum/viewtopic.php?f=21t=1724 ) Hope to see your comparison of qCANUPO and CSF. I guess qCANUPO should be better, because it uses more information to classify ground and non-ground points. But CSF will be easier to use. I tested your plugin today on Photogrammetrically point cloud consisting of over 80 million points, and I must thank you that it worked better than my expectations, for very irregular surfaces (e.g. erosion gullies with very sharp spikes) it CSF performed very well. However, the settings I used were 0.2, 800, and 0.5 (with both steep slope options checked). I actually moved step by step from cloth resolution of 1 to 0.1 while keeping all other values constant, and until 0.2 my bare-earth model constantly improved. However, when I changed from 0.2 to 0.1, my bare-earth model had less points (especially in areas with erosion gullies), what I got for 0.2. Do you know if there's any specific reason behind that? and thanks again for your plugin. Regards, Umair.
巧了,CSF的文章( An Easy-to-Use Airborne LiDAR Data Filtering Method Based on Cloth Simulation )今天在researchgate上也开始有人评价了。 https://www.researchgate.net/publication/303975654_An_Easy-to-Use_Airborne_LiDAR_Data_Filtering_Method_Based_on_Cloth_Simulation Ersilia Oniga added a comment 1h ago I have used the CSF implemented into CloudCompare software on a UAV point cloud and it worked great. Congratulation for your work and for integrating the algorithm into two free softwares.