Skip to content

Commit

Permalink
Merge pull request #4 from Dagiopia/master
Browse files Browse the repository at this point in the history
readme
  • Loading branch information
smigad authored Apr 24, 2018
2 parents c75eec1 + 61ecf3f commit d7c5913
Show file tree
Hide file tree
Showing 2 changed files with 44 additions and 5 deletions.
44 changes: 40 additions & 4 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,11 +1,47 @@
# OpenCogER

This repo was started by [yantrabuddhi](https://github.com/yantrabuddhi) to be a collection of functionalities a toy robot needs on a small
system such as a Raspberry Pi computer. The goal is to have some detectors that are as efficient as possible
on a rpi3 computer feeding a behavior program that reacts based on data from these detectors.
The sense functions are suppose to sense stuff such as faces, emotions, gesture and salient points.

Hardware-wise, a RPI3 computer, a Pi Camera V2 and a USB Microphone are required and are also the constraints
of the project.

The current code has a few detectors and there's a lot more to add. Most importantly, it needs to have an
interface for [Ghost](https://github.com/opencog/opencog/tree/master/opencog/ghost) which would handle the behavior
of the robot.

## Setup

Everything here is meant to run on a rpi3 computer but one can also compile everything on a desktop computer.

### Install
festival
opencv-3.x
opencv_contrib-3.x
raspicam >1.5 (https://sourceforge.net/projects/raspicam/files/?)

Need to have these whether on desktop or rpi
* [Opencv-3.x](https://github.com/opencv/opencv/releases/latest)
* [Opencv_contrib-3.x](https://github.com/opencv/opencv_contrib/releases)
* [Dlib](https://github.com/davisking/dlib/releases/latest)
* [Festival](http://festvox.org/festival/)
*
On rpi3 only
* [Raspicam](https://sourceforge.net/projects/raspicam/files/?) > v1.5
* [WiringPi](http://wiringpi.com/download-and-install/)

Use cmake for building.
```
cd to OpenCogEr dir
mkdir build
cd build
cmake ..
make
```


## ToDo

* Offline Speech (command) Recognition (shouldn't be heavy on the hardware)
* Ghost interface
* Ghost rules
* Stories for a specific identity we need the robot to have
* Access to Singnet applications
5 changes: 4 additions & 1 deletion examples/sense/vision/AllTest.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -98,6 +98,8 @@ int main(int argc, char **argv)

BoxTrackerThread *bt;

int nfings = 0;

while (true)
{
#ifdef _NEED_TIME_INFO_
Expand Down Expand Up @@ -126,8 +128,9 @@ int main(int argc, char **argv)
hands[i].y - hands[i].y*SCALE,
hands[i].width + hands[i].width*SCALE,
hands[i].height + hands[i].height*SCALE));
nfings = fc.num_fingers(img2);
#ifdef _NEED_GUI_
putText(frame, to_string(fc.num_fingers(img2)), Point(20, 20),
putText(frame, to_string(nfings), Point(20, 20),
FONT_HERSHEY_COMPLEX_SMALL, 1.5, CV_RGB(255, 0, 0), 2, CV_AA);
cvtColor(img2, img2, COLOR_GRAY2BGR);
for(size_t j = 0; j < fc.f_tips.size(); ++j)
Expand Down

0 comments on commit d7c5913

Please sign in to comment.