moz4r's blog

BodyPart service for a flexible skeleton ( poc )

moz4r's picture

Almost cooked, this is very inspired by InMoov service, for a universal service, for the next InMoov service...
Kwatters pointed the interest to use a tree to identify the skeleton. I have no more cofee, but I learned cool things!

Image result for tree java

What is the goal


Summary about current languages wip

moz4r's picture

 

Namaste,

 

Many of mrl services use direct or indirectly language as a parameter ( or should that is the goal )

Ex, Webbit for voice recognition, chatbot for a corresponding set and derivated, speech tts to choose a good voice, translator service etc …

Lots of things can derive from this logic so we can put more intelligence ( user country for weather service, locale money, metric system for measurement etc … )


VivaTech some pics

moz4r's picture

Great day to meet some friends at the turn of the aisles and discover cool things. Special thanks for InMoov stand that was here and represent open source things among the crowd maybe the most important thing.

Pepper army for the reception

 


Servo calibration

moz4r's picture

This is now worky for testing, what is the goal :

- One place for servo settings and calibration process ( mapping etc ... )
- Share settings automatically ( or not ) between differents script

 

 


Speech refactored

moz4r's picture

Why: Too many same things for same result with diffents code lines. From python land code & result was different from 1 speech service to an other.

Now, every speech service should use SpeechInterface and a common method will do the job to cache text and play it with AudioFile.


I2C Inmoov hand ( WIP )

moz4r's picture

New hand finished ! There no place left inside the forearm.. Time to think how InMoov service can drive all of this ( sensors + i2c )  ...

Goal of this is to limit wires and add extra sensors/servos

EDIT 16/1/18 : Seem there is a pin issue with nervoboard + arduino mega R3 ( I2C pins ). This is worky pinout for i2c :

 

 


FaceRecognizer debug & enhance

moz4r's picture

EDIT 5/11/2017 - Video explanations ( inmoov use )

 

EDIT 4/11/2017 - Added unicode support

Added unicode support to this filter because opencv dont like it ( cannot use unicode inside folder names ).


Kinmoov ( kinect microphone + chrome )

moz4r's picture

2 problems (  if you have others solutions, it is welcome ) :

Still not satisfied with final microphone's rendering, but I've tried, that was fun...

 

- I can't use anymore kinect microphone inside chrome ( refused )

- Microphones orientation, hidden

About chrome :

Uncheck this, from main sound card