https://github.com/tentone/monodepth

Python ROS depth estimation from RGB image based on code from the paper "High Quality Monocular Depth Estimation via Transfer Learning"
https://github.com/tentone/monodepth

depth-estimation machine-vision rgbd robotics ros vision

Last synced: 3 months ago
JSON representation

Python ROS depth estimation from RGB image based on code from the paper "High Quality Monocular Depth Estimation via Transfer Learning"

• Host: GitHub
• URL: https://github.com/tentone/monodepth
• Owner: tentone
• License: gpl-3.0
• Created: 2019-12-14T13:39:12.000Z (about 5 years ago)
• Default Branch: master
• Last Pushed: 2020-11-15T11:26:37.000Z (about 4 years ago)
• Last Synced: 2024-10-03T12:16:10.927Z (4 months ago)
• Topics: depth-estimation, machine-vision, rgbd, robotics, ros, vision
• Language: Python
• Homepage: https://tentone.github.io/monodepth/
• Size: 1.55 MB
• Stars: 52
• Watchers: 5
• Forks: 8
• Open Issues: 3
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
## Mono Depth ROS

 - ROS node used to estimated depth from monocular RGB data.

 - Should be used with Python 2.X and ROS

 - The original code is at the repository [Dense Depth Original Code](https://github.com/ialhashim/DenseDepth)

 - [High Quality Monocular Depth Estimation via Transfer Learning](https://arxiv.org/abs/1812.11941) by Ibraheem Alhashim and Peter Wonka



### Configuration

- Topics subscribed by the ROS node

  - /image/camera_raw - Input image from camera (can be changed on the parameter topic_color)

- Topics published by the ROS node, containing depth and point cloud data generated.

  - /image/depth - Image message containing the depth image estimated (can be changed on the parameter topic_depth).

  - /pointcloud - Pointcloud2 message containing a estimated point cloud (can be changed on the parameter topic_pointcloud).

- Parameters that can be configurated

  - frame_id - TF Frame id to be published in the output messages.

  - debug - If set true a window with the output result if displayed.

  - min_depth, max_depth - Min and max depth values considered for scaling.

  - batch_size - Batch size used when predicting the depth image using the model provided.

  - model_file - Keras model file used, relative to the monodepth package.

### Setup

- Install Python 2 and ROS dependencies

```bash

apt-get install python python-pip curl

pip install rosdep rospkg rosinstall_generator rosinstall wstool vcstools catkin_tools catkin_pkg

```

- Install project dependencies

```bash

pip install tensorflow keras pillow matplotlib scikit-learn scikit-image opencv-python pydot GraphViz tk

```

- Clone the project into your ROS workspace and download pretrained models

```bash

git clone https://github.com/tentone/monodepth.git

cd monodepth/models

curl –o nyu.h5 https://s3-eu-west-1.amazonaws.com/densedepth/nyu.h5

```

### Launch

- Example ROS launch entry provided bellow, for easier integration into your already existing ROS launch pipeline.

```xml

    

    

```

### Pretrained models

 - Pre-trained keras models can be downloaded and placed in the /models folder from the following links:

    - [NYU Depth V2 (165MB)](https://s3-eu-west-1.amazonaws.com/densedepth/nyu.h5) 

    - [KITTI (165MB)](https://s3-eu-west-1.amazonaws.com/densedepth/kitti.h5)

### Datasets for training

 - [NYU Depth V2 (50K)](https://cs.nyu.edu/~silberman/datasets/nyu_depth_v2.html) 

    - The NYU-Depth V2 data set is comprised of video sequences from a variety of indoor scenes as recorded by both the RGB and Depth cameras from the Microsoft Kinect.

    - [Download dataset](https://s3-eu-west-1.amazonaws.com/densedepth/nyu_data.zip) (4.1 GB)

 - [KITTI Dataset (80K)](http://www.cvlibs.net/datasets/kitti/) 

    - Datasets captured by driving around the mid-size city of [Karlsruhe](http://maps.google.com/?ie=UTF8&z=15&ll=49.010627,8.405871&spn=0.018381,0.029826&t=k&om=1), in rural areas and on highways. Up to 15 cars and 30 pedestrians are visible per image.