# Stereo-Visual-Odometry **Repository Path**: xinhua6/Stereo-Visual-Odometry ## Basic Information - **Project Name**: Stereo-Visual-Odometry - **Description**: Stereo Visual Odometry system for self-driving cars using image sequences from KITTI dataset - **Primary Language**: C++ - **License**: Not specified - **Default Branch**: master - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 1 - **Created**: 2019-05-21 - **Last Updated**: 2020-12-19 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README ## Synopsis System is developed to achieve Visual Odometry for a moving car, using the output of a stereo camera. Rectified stereo images from a moving camera is used to estimate camera pose and reconstruct a 3D map of scene points. Our system is further optimized using bundle adjustment and pose-graph optimization. Developed model was used to estimate the trajectory of the camera for various scenarios in the KITTI dataset. ## Results Visual Odometry results for two sequences from the KITTI dataset. [![](https://img.youtube.com/vi/EFFH1OTh_IQ/0.jpg)](https://www.youtube.com/watch?v=EFFH1OTh_IQ) ## Dependencies: ``` OpenCV2.4 PCL g2o ``` ## Building Project in terminal: ``` mkdir build cd build cmake .. make ``` ## Running project ``` cd ./vo PATH_TO_LEFT_IMAGE_SET_DIRECTORY PATH_TO_RIGHT_IMAGE_SET_DIRECTORY PATH_TO_YAML_FILE ``` ## Contributors ``` Xiaoyu Zhou @ucsdxiaoyuzhou Akshaya Purohit @akshayapurohit23 Bolun Zhang @zblzcj Leonard Melvix @lmelvix ```