SLAM-良好线切割-转为PL-SLAM等线辅助VSLAM设计的增强模块-辅助姿态优化-优质项目实战.zip

# Good Line Cutting Version of PL-SLAM Good line cutting is an enhancement module that is designed for line-assisted VSLAM, such as PL-SLAM. The primary objective of good line cutting is to pre-condition line-assisted pose optimization, therefore improving the robustness of optimization under 3D line triangulation error. [] ## Build & Run This repo is an integration of good line cutting to stereo PL-SLAM. When tested on multiple challenging scenarios that point feature may fail, GF-PL-SLAM has better performance than PL-SLAM baseline and other state-of-the-art stereo SLAM systems. To build GF-PL-SLAM, first download the repo Build dependencies for GF-PL-SLAM with ./build_dep.sh Build the GF-PL-SLAM itself ./build.sh To run GF-PL-SLAM, please refer to some example batch evaluation scripts at folder batch_script ## 1. Prerequisites and dependencies ### OpenCV 3.x.x It can be easily found at http://opencv.org. ### Eigen3 (tested with 3.2.92) http://eigen.tuxfamily.org ### Boost Installation on Ubuntu: ``` sudo apt-get install libboost-dev ``` ### g2o - General Graph Optimization It can be found at: ``` https://github.com/RainerKuemmerle/g2o.git ``` ### YAML (tested with 0.5.2) Installation on Ubuntu: ``` sudo apt-get install libyaml-cpp-dev ``` ### stvo-pl It can be found at: ``` https://github.com/rubengooj/stvo-pl ``` ### MRPT In case of using the provided representation class. Download and install instructions can be found at: http://www.mrpt.org/ #### Known Issues: If working with the most recent versions of the MRPT library you might find some issues due to hard refactoring, for which we recommend to use this version instead (the last one we tested): ``` https://github.com/MRPT/mrpt/tree/0c3d605c3cbf5f2ffb8137089e43ebdae5a55de3 ``` ### Line Descriptor We have modified the [*line_descriptor*](https://github.com/opencv/opencv_contrib/tree/master/modules/line_descriptor) module from the [OpenCV/contrib](https://github.com/opencv/opencv_contrib) library (both BSD) which is included in the *3rdparty* folder. ## 2. Configuration and generation Executing the file *build.sh* will configure and generate the *line_descriptor* and *DBoW2* modules, uncompress the vocabulary files, and then will configure and generate the *PL-SLAM* library for which we generate: **libplslam.so** in the lib folder, and the application **plslam_dataset** that works with our dataset format (explained in the next section). ## 3. Usage ### Datasets configuration We employ an environment variable, *${DATASETS_DIR}*, pointing the directory that contains our datasets. Each sequence from each dataset must contain in its root folder a file named *dataset_params.yaml*, that indicates at least the camera model and the subfolders with the left and right images. We provide dataset parameters files for several datasets and cameras with the format *xxxx_params.yaml*. ### Configuration files For running SLAM we can load the default parameters file or employ the *config_xxxx.yaml* files provided for every dataset. ### SLAM Application Usage: ./plslam_dataset <dataset_name> [options] Options: -c Config file -o Offset (number of frames to skip in the dataset directory -n Number of frames to process the sequence -s Parameter to skip s-1 frames (default 1) A full command would be: ./plslam_dataset kitti/00 -c ../config/config_kitti.yaml -o 100 -s 2 -n 1000 where we are processing the sequence 00 from the KITTI dataset (in our dataset folders) with the custom config file, with an offset *-c* allowing to skip the first 100 images, a parameter *-s* to consider only one every 2 images, and a parameter *-n* to only consider 1000 input pairs.