BlenderOcv, “blender” can be good and powerful tool for computer vision with OpenCV
This is the question: can be Blender a powerful tool for computer vision with OpenCv.
Blender is now a powerful suite of 3d content creation, where have a various characteristich as animation, composit, shade, model, texture, interactive … And OpenCV is ga powerful realtime library for computer Vision.
Then my goal is provide a new and powerfull tool based on Blender for Computer Vision Tasks with OpenCV Library.
How?, with a particular characteristic of Blender, the compositor node.
Nodes are a good tool that provide a user interactive, each node is a box with inputs and outputs that implement a function. Each node have interactive parameters that user can be set.
Each node can be linked with others nodes linking outputs to inputs
In this page we can see more about node compositor
With this properties we can create a workflow of a computer vision tasks.
For example here are the basic edge detection with blenderocv, this example implement the basic opencv sample “edge.c”
Now there are a demo with some few functions.
I have to implement a lot of functions as nodes, and now there are a lot of work to do, and sure i make important decisions in development. If anybody want colaborate with this project, please send me mail (david at artresnet dot com) or send me a comment.
There are more info and progress about this project in http://code.google.com/p/blenderocv/
16 Comments + Add Comment
Got anything to say? Go ahead and leave a comment!
Category
- blenderocv (1)
- Personal (2)
- Tutorials (24)
- ActionScript (1)
- Blender (2)
- CSS (1)
- Java and Netbeans (1)
- Linux/Unix (7)
- OpenCV (15)
- OpenGL (1)
- other (4)
- Uncategorized (2)
- Works (2)
Last comments
Tag cloud
Twitter: damiles3D
- Finishing coding a card marker AR functions in API. Next step, facedetection.
- Que tardecita. Después de correr 5km para recoger el coche acabo haciendo un duatlon cogiendo bici para volver en tren. X(
- En el tren de camino al trabajo. Lunes lunero....
- @Neoxisme do you want this list of camera features to set http://t.co/jCqNnWct
- Finished QR integration, and first basic UI OpenGL framework.
- Review Finished, I like this chapter. Now continue developing OpenGL user interfaces and Events management
- Reviwing a book... only review 30 pages and 15 gnuplot scripts.
- @pipotux Siempre que puedas evitar pagar la licencia ;)
- @pipotux Suena dificil! :S
- @joshis_tweets Check this first. Read it http://t.co/3AEMSxRa




Posted under: 
I found your site on google and read a few of your other posts. Keep up the good work.
Hey great to see your work. Looking forward to trying it out.
Hi ibkanat, so time i don’t see, i expect this was a good computer vision tool.
i tried to compile blenderocv on os x. i got as far as the linker and then i got the following error:
[100%] Built target bf_sumo
Linking C executable ../../bin/blender.app/Contents/MacOS/blender
Undefined symbols:
“_cmp_node_image2cvImage”, referenced from:
_cmp_node_image2cvImage$non_lazy_ptr in libbf_blenkernel.a(node.o)
“_cmp_node_cvImage2Image”, referenced from:
_cmp_node_cvImage2Image$non_lazy_ptr in libbf_blenkernel.a(node.o)
“_cmp_node_cvAdd”, referenced from:
_cmp_node_cvAdd$non_lazy_ptr in libbf_blenkernel.a(node.o)
“_cmp_node_cvNot”, referenced from:
_cmp_node_cvNot$non_lazy_ptr in libbf_blenkernel.a(node.o)
“_cmp_node_cvCanny”, referenced from:
_cmp_node_cvCanny$non_lazy_ptr in libbf_blenkernel.a(node.o)
“_cmp_node_CvPoint”, referenced from:
_cmp_node_CvPoint$non_lazy_ptr in libbf_blenkernel.a(node.o)
“_cmp_node_cvCopy”, referenced from:
_cmp_node_cvCopy$non_lazy_ptr in libbf_blenkernel.a(node.o)
“_cmp_node_cvSmooth”, referenced from:
_cmp_node_cvSmooth$non_lazy_ptr in libbf_blenkernel.a(node.o)
“_cmp_node_cvCvtColor”, referenced from:
_cmp_node_cvCvtColor$non_lazy_ptr in libbf_blenkernel.a(node.o)
“__dummy”, referenced from:
ld: symbol(s) not found
collect2: ld returned 1 exit status
make[2]: *** [bin/blender.app/Contents/MacOS/blender] Error 1
make[1]: *** Error 2
make: *** [all] Error 2
any help would be greatly appreciated
Hi liubo,
first i want comment that i’m working on it, and only i have implemented some nodes, 4 or 5 nodes only, and i’m now working for the correct node implementation, then the other nodes are more simply to implement.
Second, I only configure the scons compiler, i no configure make compiler, then you must use scons/scons.py for compile, it use python for this task, and you sure must change the opencv directory source to point your opencv, you can change it in config/darwin-config.py where put BF_OPENCV…
If you like help me in this project, i’m very happy, and i can have access to svn commit.
Regards David.
looks very nice
i write similiar tool cvpreprocessor
good luck
Your work is wonderful. come on !
Thanks for the post.
fantastic work…please keep going in this project
Step on it!
Hi, in few weeks i want make some demos!
Great project!
Have you been able to add movie support (instead of only image support)?
Best wishes,
Daniel
Hi Daniel, the project is now beta, but in few months we go to publish a beta release with documentations.
Regards David.
Hello, Damiles.
It’s great.I want to collaborate with your project.
Please, give me a response.
Damiles, hello from Trukey.
I want to collaborate with your project to.
Please, give me a response.
Hi, please send me by email a gmail account and why you want to collaborate in this project. Regards David.