This code was developed under the work of my Thesis with title "Automatic detection and clustering of arbitrary objects using image data and depth information". The code is able to:
- Detect objects of arbitrary shape through image data and depth information.
- Specify the location of detected objects on the map.
- Group the detected objects by shape.
The Finite State Machine (FSM) of the system is:
The node diagram is the following:
These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.
Linux (Kernel >= 4.13.0-45-generic)
Python (Version >= 3.3)
NumPy (Version >= 1.8.2)
ROS (Version = Kinetic Kame)
Installation instructions for ROS Kinetic
sudo apt-get install numpy python-yaml
sudo apt-get install python-opencv
pip install -U scikit-learn
- ROS - The Robot Operating System as a flexible framework for writing the robot software
- OpenCV - Open Source Computer Vision Library
- PCL - Library for 2D/3D image and point cloud processing
- scikit-learn - Machine Learning in Python
- Eleftherios Mylonakis - Code and thesis writing - lefos99
- Manos Tsardoulias - Guidance during Thesis writing - etsardou