Skip to content

tue-robotics/image_recognition

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

TU/e Robotics image_recognition

CI Industrial CI

Packages for image recognition - Robocup TU/e Robotics

Package status & Description

Package Build status Xenial Kinetic x64 Description
image_recognition Build Status Meta package for all image_recognition packages.
image_recognition_analysis Build Status analysis for image recognition
image_recognition_color_extractor Build Status Extract dominant colors from images
image_recognition_jetson Build Status ROS wrapper for Jetson Inference (https://github.com/dusty-nv/jetson-inference) for running inference using TensorRT.
image_recognition_keras Build Status ROS wrappers for Keras neural nets.
image_recognition_msgs Build Status Interface definition for image recognition
image_recognition_openface Build Status ROS wrapper for Openface (https://github.com/cmusatyalab/openface) to detect and recognize faces in images.
image_recognition_openpose Build Status ROS wrapper for Openpose (https://github.com/CMU-Perceptual-Computing-Lab/) for getting poses of 2D images.
image_recognition_pytorch Build Status ROS wrapper around a PyTorch model for (https://github.com/Nebula4869/PyTorch-gender-age-estimation) for getting age & gender estimations on faces
image_recognition_rqt Build Status RQT tools with helpers testing this interface and training/labeling data.
image_recognition_skybiometry Build Status ROS wrapper for Skybiometry (https://skybiometry.com/) for getting face properties of a detected face, e.g. age estimation, gender estimation etc.
image_recognition_tensorflow Build Status Object recognition with use of Tensorflow. The user can retrain the top layers of a neural network to perform classification with its own dataset as described in this tutorial.
image_recognition_tensorflow_rqt Build Status RQT tools for retraining a Tensorflow neural network.
image_recognition_util Build Status Utils shared among image recognition packages

How to

Object recognition

Step 1: label images with the image_recognition_rqt#annotation-plugin

Annotate <-- Youtube video

Step 2: train a neural network with the image_recognition_tensorflow_rqt

Train <-- Youtube video

Step 3: predict labels for new data with the image_recognition_rqt#test-plugin

Recognize <-- Youtube video

Face recognition

See the tutorial at image_recognition_openface

Face recognition <-- Youtube video

Installation

Clone the repo in your catkin_ws:

    cd ~/catkin_ws/src
    git clone https://github.com/tue-robotics/image_recognition.git

Build your catkin workspace cd ~/catkin_ws catkin_make