# SequenceSfM **Repository Path**: pi-lab/SequenceSfM ## Basic Information - **Project Name**: SequenceSfM - **Description**: Structure from Motion (SfM) for sequence images - **Primary Language**: Unknown - **License**: Not specified - **Default Branch**: master - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 1 - **Forks**: 3 - **Created**: 2020-08-07 - **Last Updated**: 2023-05-18 ## Categories & Tags **Categories**: cv **Tags**: None ## README # Sequence SfM This program is a demo to show structure from motion for sequence images input. The program is based on https://github.com/royshil/SfM-Toy-Library, but we fix some bugs and use Qt as the interface. You can add more advanced tricks such used in PTAM or ORB-SLAM, to make it faster and robust. ## 1. Plateform Use Ubuntu 18.04 or later. ## 2. Requirements * SuiteSparse * Qt4 * g++ 4.8 ``` sudo apt-get install libsuitesparse-dev sudo apt-get install libqt4-core libqt4-dev sudo apt-get install gcc-4.8 g++-4.8 ``` ## 3. Build: 由于本项目使用老版本的Feature,因此必须使用OpenCV 2.4。需要确保系统里没有安装其他版本的OpenCV。具体安装的方法请参考[《OpenCV安装说明》](https://gitee.com/pi-lab/pi-slam/blob/master/thirdparty/opencv_install.md) ### 3.1 Build command ``` mkdir build; cd build cmake -DCMAKE_CXX_COMPILER=/usr/bin/g++-4.8 \ -DCMAKE_C_COMPILER=/usr/bin/gcc-4.8 \ -DOpenCV_DIR=/opt/opencv-2.4.9/share/OpenCV \ .. make ``` ## 4. Usage ``` ./SequenceSFM fn_in=../data/img_sfm_1s ``` ## 5. Screenshot -![Cover Image](images/SequenceSfM.png) ## 6. Project homepage http://www.adv-ci.com/blog/source/sequence-sfm/ ## 7. References Tutorial: * [Structure from Motion Tutorial](https://imkaywu.github.io/tutorials/sfm/) Soft: * [Bundler v0.4 User's Manual](https://www.cs.cornell.edu/~snavely/bundler/bundler-v0.4-manual.html) * [Bundler: Structure from Motion (SfM) for Unordered Image Collections](http://www.cs.cornell.edu/~snavely/bundler/) * [Patch-based Multi-view Stereo Software](https://www.di.ens.fr/pmvs/) * [Clustering Views for Multi-view Stereo (CMVS)](https://www.di.ens.fr/cmvs/)