I'm working on a C++ project using a ToF camera. The camera is inside a room and has to detect walls, doors or other big planar surfaces. I'm currently using OpenCV but answers using other C++ libaries are also okay. What is a good algorithmn to detect the surfaces, also if they are rotated and aren't facing the camera directly. I've heard things like making a point cloud and using RANSAC. If you suggest me doing that please explain it in detail or provide a resource for explanation, because I don't know much about this topic (I'm a beginner in computer vision).
Thanks for your responses.
Are you familiar with PCL?
This tutorial shows how to find planar segments in a point-cloud using PCL.
Related
You might have seen that option in one of the samsung phone that when a person smile it take the photo. So it somehow detects the smile and the click the photo automatically.I'm trying to create the similar thing on iOS that lets say if the camera detects a chair it clicks the photo.I've searched around and what I found is that there is a library called OpenCV but I'm not sure it'll work with iOS or not. Plus there is a concept of CoreImage in iOS which has something to do with deep understanding of the image. So any idea about this?
openCV For iOS
For detection you can use openCV framework in iOS and the native detection methods. In my application i am using openCV rectangle detection and the scenario is: after taken picture openCV detects rectangle on the image and then makes lines on detected shape, also it can crop the image with basic functionality and as perspective correction.
options: Face Detection, Shape Detection
Native way:
iOS provides us real time detection there are many tutorials how to use them i will link at the end of the thread. Native way also provides us face detection, shape detection and perspective correction.
Coclusion:
Choice is up to you but i prefer native way. remember openCV is written in C++ if you are using swift language you can import openCV in your project and then connect swift to objective-C to call openCV. Using Bridging Headers
Tutorials:
Medium Link 1
Medium Link 2
Toptal Tutorial
How to use OPENCV in iOS
I am working on an app in iOS that will occur an event if camera detects some changes in image or we can say motion in image. Here I am not asking about face recognition or a particular colored image motion, And I got all result for OpenCV when I searched, And I also found that we can achieve this by using gyroscope and accelerometer both , but how??
I am beginner in iOS.So my question is , Is there any framework or any easy way to detect motion or motion sensing by camera.And How to achieve?
For Example if I move my hand before camera then it will show some message or alert.
And plz give me some useful and easy to understand links about this.
Thanx
If all you want is some kind of crude motion detection, my open source GPUImage framework has a GPUImageMotionDetector within it.
This admittedly simple motion detector does frame-to-frame comparisons, based on a low-pass filter, and can identify the number of pixels that have changed between frames and the centroid of the changed area. It operates on live video and I know some people who've used it for motion activation of functions in their iOS applications.
Because it relies on pixel differences and not optical flow or feature matching, it can be prone to false positives and can't track discrete objects as they move in a frame. However, if all you need is basic motion sensing, this is pretty easy to drop into your application. Look at the FilterShowcase example to see how it works in practice.
I don't exactly understand what you mean here:
Here I am not asking about face recognition or a particular colored
image motion, because I got all result for OpenCV when I searched
But I would suggest to go for opencv as you can use opencv in IOS. Here is a good link which helps you to setup opencv in ios.
There are lot of opencv motion detection codes online and here is one among them, which you can make use of.
You need to convert the UIImage ( image type in IOS ) to cv::Mat or IplImage and pass it to the opencv algorithms. You can convert using this link or this.
I'm planning to implement an application with augmented reality features. For one of the features I need an egomotion estimation. Only the camera is moving, in a space with fixed objects (nothing or only small parts will be moving, so that they might be ignored).
So I searched and read a lot and stumbled upon OpenCV. Wikipedia explicitly states that it could be used for egomotion. But I cannot find any documentation about it.
Do I need to implement the egomotion algorithm by myself with OpenCV's object detection methods? (I think it would be very complex, because objects will move in different speed depending on their distance to the camera. And I also need to regard rotations.)
If so, where should I start? Is there a good code example for a Kanade–Lucas–Tomasi feature tracker with support for scaling and rotation?
P.S.: I also know about marker based frameworks like vuforia, but using a marker is something I would like to prevent, as it restricts the possible view points.
Update 2013-01-08: I learned that Egomotion Estimation is better known as Visual Odometry. So I updated the title.
You can find a good implementation of monocular visual odometry based on optical flow here.
It's coded using emgucv (C# opencv wrapper) but you will find no issues on convert it back to pure opencv.
Egomotion (or visual odometry) is usually based on optical flow, and OpenCv has some motion analysis and object tracking functions for computing optical flow (in conjunction with a feature detector like cvGoodFeaturesToTrack()).
This example might be of use.
Not a complete solution, but might at least get you going in the right direction.
I am a new kinect developer and going to develop some application related to face tracking by using kinect v1.5 and XNA Framework in c# platform.
I can successfully get the face points and rectangle points to display in the screen by using the kinect sdk and Basic Effect of XNA 3D drawing.
However, What i want is to get back exactly the same color pixel of the user's face so that I can get mapping of the user's real face to a model.
Is there anybody that can help to answer my question?
Thank you very much!
One of the ways you can achieve this would be by using the RGB (colour) video stream and capturing a still. You can then use C# to enumerate through the X/Y axis of this image to get the colour if required.
The more effcient way however would be to use this still as the texture and "wrap" the 3D model you are creating using it. There is an example provided with the Kinect SDK which does something similar, the sample is called Face Tracking 3D - WPF. I would encourage you to use this as your base porting to XNA and work from there.
I would like some hints, maybe more, on detecting a custom image marker in a real-time video feed. I'm using OpenCV, iPhone and the camera feed.
By custom image marker I'm referring to a predefined image, but it can be any kind of image (not a specific designed marker). For example, it can be a picture of some skyscrapers.
I've already worked with ARTags and understand how they are detected, but how would I detect this custom image and especially find out its position & orientation?
What makes a good custom image to be detected successfully?
Thanks
The most popular markers used in AR are
AR markers (a simple form of QR codes) - those detected by AR tookit & others
QR codes. There are plenty of examples on how to create/detect/read QR.
Dot grids. Similar with the chess grids used in calibration. It seems their detection can be more robust than the classical chess grid. OpenCV has codes related to dot grid detection in the calibration part. Also, the OpenCV codebase offers a good starting point to extract 3D position and orientation.
Chess grids. Similar to dot grids. They were the standard calibration pattern, and some people used them for marker detection of a long time. But they lost their position to dot grids recently, when some people discovered that dots can be detected with better accuracy.
Note:
Grids are symmetrical. I bet you already know that. But that means you will not be able to
recover full orientation data from them. You will get the plane where the grid lies, but nothing more.
Final note:
Code and examples for the first two are easily found on the Internet. They are considered the best by many people. If you decide to use the grid patterns, you have to enjoy some math and image processing work :) And it will take more.
This answer is valid no more since Vuforia is now a paid engine.
I think you should give Vuforia a try. It's a AR engine that can use any image you want as a marker. What makes a good marker for Vuforia is high frequency images.
http://www.qualcomm.com/solutions/augmented-reality
Vuforia is a free to use engine.