# VDO-SLAM
# Prerequisites
We have tested the library in **Mac OS X 10.14** and **Ubuntu 16.04**, but it should be easy to compile in other platforms.
## c++11, gcc and clang
We use some functionalities of c++11, and the tested gcc version is 9.2.1 (ubuntu), the tested clang version is 1000.11.45.5 (Mac).
## OpenCV
We use [OpenCV](http://opencv.org) to manipulate images and features. Download and install instructions can be found at: http://opencv.org. **Required at least 3.0. Tested with OpenCV 3.4**.
## Eigen3
Required by g2o (see below). Download and install instructions can be found at: http://eigen.tuxfamily.org. **Required at least 3.1.0**.
## g2o (Included in dependencies folder)
We use modified versions of [g2o](https://github.com/RainerKuemmerle/g2o) library to perform non-linear optimizations. The modified libraries (which are BSD) are included in the *dependencies* folder.
## Use Dockerfile for auto installation
For Ubuntu users, a Dockerfile is added for automatically installing all dependencies for reproducible environment, built and tested with KITTI dataset. (Thanks @satyajitghana for the contributions ���� )
# Building VDO-SLAM Library
We provide a script `build.sh` to build the *dependencies* libraries and *VDO-SLAM*.
Please make sure you have installed all required dependencies (see section 2).
**Please also change the library file suffix, i.e., '.dylib' for Mac (default) or '.so' for Ubuntu, in the main CMakeLists.txt.**
Then Execute:
```
cd VDO-SLAM
chmod +x build.sh
./build.sh
```
This will create
1. **libObjSLAM.dylib (Mac)** or **libObjSLAM.so (Ubuntu)** at *lib* folder,
2. **libg2o.dylib (Mac)** or **libg2o.so (Ubuntu)** at */dependencies/g2o/lib* folder,
3. and the executable **vdo_slam** in *example* folder.
# 4. Running Examples
## KITTI Tracking Dataset
1. Download the demo sequence: [kitti_demo](https://drive.google.com/file/d/1LpjIdh6xL_UtWOkiJng0CKSmP7qAQhGu/view?usp=sharing), and uncompress it.
2. Execute the following command.
```
./example/vdo_slam example/kitti-0000-0013.yaml PATH_TO_KITTI_SEQUENCE_DATA_FOLDER
```
## Oxford Multi-motion Dataset
1. Download the demo sequence: [omd_demo](https://drive.google.com/file/d/1t4rG685a_7r0bHuW0bPKNbOhyiugnJK7/view?usp=sharing), and uncompress it.
2. Execute the following command.
```
./example/vdo_slam example/omd.yaml PATH_TO_OMD_SEQUENCE_DATA_FOLDER
```
# 5. Processing Your Own Data
You will need to create a settings (yaml) file with the calibration of your camera. See the settings files provided in the *example/* folder. RGB-D input must be synchronized and depth registered. A list of timestamps for the images is needed for input.
The system also requires image pre-processing as input, which includes instance-level semantic segmentation and optical flow estimation. In our experiments, we used [Mask R-CNN](https://github.com/matterport/Mask_RCNN) for instance segmentation (for KITTI only; we applied colour-based method to segment cuboids in OMD, check the matlab code in [tools](https://github.com/halajun/VDO_SLAM/blob/master/tools) folder), and [PWC-NET](https://github.com/NVlabs/PWC-Net) (PyTorch version) for optic-flow estimation. Other state-of-the-art methods can also be applied instead for better performance.
For evaluation purpose, ground truth data of camera pose and object pose are also needed as input. Details of input format are shown as follows,
## Input Data Pre-processing
1. The input of segmentation mask is saved as matrix, same size as image, in .txt file. Each element of the matrix is integer, with 0 stands for background, and 1,2,...,n stands for different instance label. Note that, to easily compare with ground truth object motion in KITTI dataset, we align the estimated mask label with the ground truth label. The .txt file generation (from .mask) and alignment code is in [tools](https://github.com/halajun/VDO_SLAM/blob/master/tools) folder.
2. The input of optical flow is the standard .flo file that can be read and processed directly using OpenCV.
## Ground Truth Input for Evaluation
1. The input of ground truth camera pose is saved as .txt file. Each row is organized as follows,
```
FrameID R11 R12 R13 t1 R21 R22 R23 t2 R31 R32 R33 t3 0 0 0 1
```
Here Rij are the coefficients of the camera rotation matrix **R** and ti are the coefficients of the camera translation vector **t**.
2. The input of ground truth object pose is also saved as .txt file. One example of such file (**KITTI Tracking Dataset**), which each row is organized as follows,
```
FrameID ObjectID B1 B2 B3 B4 t1 t2 t3 r1
```
Where ti are the coefficients of 3D object location **t** in camera coordinates, and r1 is the Rotation around Y-axis in camera coordinates. B1-4 is 2D bounding box of object in the image, used for visualization. Please refer to the details in **KITTI Tracking Dataset** if necessary.
The provided object pose format of **OMD** dataset is axis-angle + translation vector. Please see the provided demos for details. A user can input a custom data format, but need to write a new function to input the data.
SLAM-视觉动态物体感知SLAM系统-优质项目实战-优秀毕业设计.zip （188个子文件） 
os_specific.c 2KB Tracking.cc 150KB Optimizer.cc 120KB ORBextractor.cc 43KB Frame.cc 23KB figure.cc 21KB vdo_slam.cc 18KB System.cc 13KB window.cc 10KB Converter.cc 4KB highgui.cc 4KB color.cc 2KB Map.cc 333B FindBLAS.cmake 13KB FindLAPACK.cmake 10KB FindEigen3.cmake 3KB FindEigen3.cmake 3KB FindSuiteSparse.cmake 3KB FindCSparse.cmake 618B FindCSparse.cmake 618B types_six_dof_expmap.cpp 31KB optimizable_graph.cpp 27KB sparse_optimizer.cpp 20KB kitti_mask_sem2gt.cpp 12KB estimate_propagator.cpp 10KB hyper_dijkstra.cpp 9KB dquat2mat_maxima_generated.cpp 9KB hyper_graph_action.cpp 9KB optimization_algorithm_dogleg.cpp 8KB opengl_primitives.cpp 8KB marginal_covariance_cholesky.cpp 7KB edge_se3_pointxyz.cpp 7KB optimization_algorithm_levenberg.cpp 7KB solver_csparse.cpp 6KB edge_se3.cpp 6KB factory.cpp 6KB types_seven_dof_expmap.cpp 6KB edge_se3_offset.cpp 5KB cache.cpp 5KB csparse_extension.cpp 5KB string_tools.cpp 5KB robust_kernel_impl.cpp 5KB isometry3d_mappings.cpp 5KB vertex_se3.cpp 5KB optimization_algorithm_factory.cpp 5KB edge_se3_prior.cpp 4KB parameter_container.cpp 4KB hyper_graph.cpp 4KB parameter_se3_offset.cpp 4KB vertex_pointxyz.cpp 4KB vertex_point_xy.cpp 4KB csparse_helper.cpp 4KB sparse_optimizer_terminate_action.cpp 4KB timeutil.cpp 4KB matrix_structure.cpp 3KB dquat2mat.cpp 3KB optimization_algorithm_with_hessian.cpp 3KB optimization_algorithm_gauss_newton.cpp 3KB property.cpp 3KB robust_kernel_factory.cpp 3KB jacobian_workspace.cpp 3KB batch_stats.cpp 3KB types_slam3d.cpp 3KB types_dyn_slam3d.cpp 3KB sparse_block_matrix_test.cpp 3KB types_sba.cpp 3KB edge_xyz_prior.cpp 3KB solver.cpp 3KB optimization_algorithm.cpp 2KB robust_kernel.cpp 2KB isometry3d_gradients.cpp 2KB parameter.cpp 2KB Dockerfile 2KB optimizable_graph.h 25KB types_six_dof_expmap.h 19KB sparse_optimizer.h 12KB linear_solver_csparse.h 12KB isometry3d_gradients.h 11KB sparse_block_matrix_ccs.h 11KB sparse_block_matrix.h 9KB linear_solver_eigen.h 9KB se3quat.h 8KB Frame.h 8KB hyper_graph.h 8KB hyper_graph_action.h 8KB Tracking.h 8KB block_solver.h 7KB sim3.h 7KB estimate_propagator.h 6KB optimization_algorithm_factory.h 6KB factory.h 6KB isometry3d_mappings.h 6KB vertex_se3.h 6KB types_seven_dof_expmap.h 6KB solver.h 5KB property.h 5KB eigen_types.h 5KB cache.h 5KB string_tools.h 5KB robust_kernel_factory.h 5KB共 188 条
- 1
- 2
资源评论
