object_detection's Introduction
============================================================ == Object Detection using LiDAR point cloud ============================================================ Object detection, tracking, and classification using LiDAR point cloud - Current implementation: ROS with Python - Classifier is not optimized yet ============================================================ == What's included ============================================================ object_detection +-- include | +-- Eigen | +-- Tracker.h | +-- kalman_filter.h +-- launch | +-- object_detection.launch +-- rviz_cfg | +-- obj_detect.rviz +-- scripts | +-- classification_svm.py | +-- connected.py | +-- features_extraction.py | +-- object_detection_node.py | +-- occupancy_grid.py | +-- scan_conversion.py | +-- segmentation.py | +-- trained_classifier_4classes.pkl +-- src | +-- Tracker.cpp | +-- kalman_filter.cpp | +-- tracking_node.cpp +-- CMakeLists.txt +-- package.xml +-- readme.txt (this file) +-- requirements_python36.txt ============================================================ == Getting Started ============================================================ Prerequisites: -Ubuntu 16.04 with ROS Kinetic (Installation instruction: http://wiki.ros.org/kinetic/Installation/Ubuntu) -Catkin workspace (how to create catkin workspace: http://wiki.ros.org/catkin/Tutorials/create_a_workspace) -Python 3.6 (tested with Python 3.6, but 3.5 should work) -Phtyon libraries: numpy, scipy, scikit-learn, etc. (requirements file (requirements_python36.txt) is provided just in case; create your virtual environment, and run: pip install -r requirements_python36.txt) How to build with catkin: $ unzip ros_object_detection.zip -d ~/catkin_ws/src/ $ cd ~/catkin_ws $ catkin_make $ source ~/catkin_ws/devel/setup.bash Python scripts are under ~/catkin_ws/src/object_detection/scripts ============================================================ == How to run ============================================================ $ roslaunch object_detection object_detection.launch (This launches three separete programs, which can be run in three separete terminals as follows: $ roscore $ rosrun object_detection object_detection_node.py $ rosrun object_detection tracking_node $ rosrun rviz rviz -d ~/catkin_ws/src/object_detection/rviz_cfg/obj_detect.rviz ) In second terminal, play sample rosbag file including LiDAR data (VLP-32C): $ rosbag play sample_rosbag.bag Note: Please find the links below for ROSBAG with Velodyne LiDAR Data and Camera https://app.box.com/s/nueax6f2ylcspf796xk13xnoxb2zra71 https://velodyne-my.sharepoint.com/:f:/p/algorithmteam/EruWWshc4gtCqxHYCNYy4JEBq3GGg8QM8RpPssV6AbxjsA?e=qrbAeq * 2017-10-01-19-54-57_Velodyne-VLP-16-Data.pcap file and _2017-12-12-21-58-53_CESDemo.bag file are VLP-32 bag file. * 2017-10-16-13-23-15_Alameda_Marina.pcap file is VLP-16 bag file.
object_detection's People
Forkers
collector-m dhiren-hamal dyu117 ahmedabdlhamid navidmostofi i201821180 cacao1987 turingdriving signalimagecv charlie13 torchlidar mr-d-self-drivingobject_detection's Issues
How to train new model?
Hello,
I want to use SVM to classify human in ROS with VLP 16
Would you please tell me how to train my own model? How to get the feature for SVM training
Thank you
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. ๐๐๐
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.