Group members: Di Deng, Radhika Mohanan, and Samiran Gode

We integrate image segmentation result with ORB_SLAM2 to remove extracted ORB features on dynamic objects based on objects' category. In this project , walking people are used to illustrate the effectiveness of the proposed method.

We have tested the code with Ubuntu 18.04.

The licence of this repo follows the licence of ORB_SLAM2.

• The simulation environment is from UnrealEngine MarketPlace Modular School Pack
• The walking character, Brian, is downloaded from Adobe mixamo.

Features obtained from ORB feature extractor:

1. Install ORB-SLAM2
2. Replace src, include, Examples and CMakeLists.txt with the files in this repo.
3. Download dataset and put it within the main directory.
4. Run:

chmod +x build.sh
./build.sh
./Examples/Monocular/mono_dynamic_airsim Vocabulary/ORBvoc.txt Examples/Monocular/airsim.yaml dynamic_obstacle_dataset

You can find that all features on dynamic objects are removed using this code comparing to the features extracted directly using ORB-SLAM2.

Features obtained from ORB feature extractor:

This dataset also contains depth images and the ground truth pose information. We want to integrate depth and semantic information with the estimated camera trajectory to reconstruct the voxel map of the environment without the dynamic objects.

Reconstructed pointcloud based on the ground truth pose information.