Profile cover photo
Profile photo
Booppey Computer Vision Blog
Blog for share knowledge about image processing, computer vision and others related domains
Blog for share knowledge about image processing, computer vision and others related domains
About
Posts

Post has attachment

Post has attachment
"A company called Bonsai joins a movement to democratize machine learning. Get ready to build your own neural net."

https://backchannel.com/you-too-can-become-a-machine-learning-rock-star-no-phd-necessary-107a1624d96b#.mqazf1ssf
Add a comment...

Post has attachment
"The ability to learn from experience will likely be a key in enabling robots to help with complex real-world tasks, from assisting the elderly with chores and daily activities, to helping us in offices and hospitals, to performing jobs that are too dangerous or unpleasant for people..."
Great!
Computer vision and machine learning help robots become more intelligent!
https://research.googleblog.com/2016/10/how-robots-can-acquire-new-skills-from.html
Add a comment...

Post has attachment
Williams is encouraged that tech giants like Facebook and Google are even asking questions about ethics and bias in AI. Ideally, the group will help establish new standards for thinking about artificial intelligence, big data, and algorithms that can weed out harmful assumptions and biases. But that’s a mammoth task. As co-chair Eric Horvitz from Microsoft Research put it, the hard work begins now.
https://www.wired.com/2016/09/google-facebook-microsoft-tackle-ethics-ai/
Add a comment...

Post has attachment
Deep Learning is the future of AI?
https://www.youtube.com/watch?v=wofXCQXq1pg
Add a comment...

Post has attachment
To day, the computer vision makes the computer more intelligent. It can recognize any simple object like a car, a building, a cup, etc. In this post, we want to explain how to make the computer recognizes a box. In general, for object detection, we can not use a method simple such as color based, shape based, etc. This project use featured based method for detect object. In particular, we use the Scale-invariant feature transform (SIFT) method for detect the box. How do you think about our method?
http://www.booppey.com/booppey/opencv-object-detection-feature-based/
Add a comment...

Post has attachment
Another article with nice application of machine learning (deep learning) for computer vision.
https://re-work.co/blog/machine-intelligence-carl-vondrick-mit-computer-vision-predictive-intelligence
Add a comment...

Post has attachment
Computer vision and machine learning are not separated. Machine learning helps computer vision method become more intelligent. We can say also that computer vision is a nice application of machine learning?
That is a good article for the relationship of CV and ML!
http://www.computervisionblog.com/2015/03/deep-learning-vs-machine-learning-vs.html
Add a comment...

Post has attachment
The Bebop drone start to fly. Then we click on "stable flying" button. So the drone will locate on this position. That means stable flying. Because normally, the bebop change its position even we don't control.

This is demonstrator of our method. We used template matching method, with featured based. In particular, we used SIFT descriptor for feature extraction and RANSAC. We also use OpenCV on C++ for computer vision. That module is running on our server. Firstly, the drone send camera image to android phone. Then android phone send this image to the server that process image, apply computer vision algorithms and return the result to the phone.
Add a comment...

Post has attachment
The Jumping Sumo drone follow the ball until the ball is in centre of drone's camera. When the ball is out of the screen camera, drone will turn around for fetch ball.
This is demonstrator of our method. We used color detection for detect the ball. We also use OpenCV on C++ for image processing. That module is running on our server. Firstly, the drone send camera image to android phone. Then android phone send this image to the server that process image and return the result to the phone.
Detail of the algorithm: http://www.booppey.com/booppey/opencv-ball-detection-color-based/
Add a comment...
Wait while more posts are being loaded