Ask Your Question

2hochn's profile - activity

2014-01-22 09:01:52 -0500 asked a question Detect elipse/oval shape in Black and White image

I want to detect dark foot-shapes in a picture. Shapes on noisy background

For this i want to start of by using a treshhold and search the resulting picture for shapes of the correct size.

After the Tresholding, the dark shapes are (most of the time) pretty good recognizable. My Question is: What is the best/fastest way to detect the shapes? Related Question

A few remarks: First i used findContours and used contourArea to get the size of the shapes. This works fairly well. I thought that it might speed things up to use Connected Component Labeling while simultaneously computing the size of the regions i find. After i was done computing this, i found the paper "A linear-time component-labeling algorithm using contour tracing technique", that claims, that it's much faster to compute only the contours instead of the CC-labeling. Now I'm wondering, what Algorithm findContours in OpenCV uses and what algorithm i should use.

2014-01-22 07:59:49 -0500 received badge  Self-Learner (source)
2014-01-22 07:30:23 -0500 answered a question Camera suggestion

Just to let you know: I will buy the Logitech c920 and hopefully succeed in adjusting the focus point. Tutorial on Youtube This will cost me ~80€.

A "professional camera" 1.3mp, color, 60fps without lens would have cost ~330€.

Hopefully i will remember to write when it arrives and is used about my experience.

2014-01-07 06:55:42 -0500 received badge  Student (source)
2014-01-07 06:37:12 -0500 asked a question Camera suggestion

For a University Project i have to film a semi-transparent Window, detect certain shapes and send the results to another computer. (Example Picture at bottom of post) The detection is done with c++ using OpenCV in Win7.

I think the simplest solution is to connect the camera directly to a computer and do the Computation on the machine. I need to have at least 25fps, a resolution of 1280 x 1024 would probably be enough for the detection.

I am relativly free in the decision which camera i want to use. Can you suggest a camera that works well with OpenCV and is easy to use?

This Question has been asked a few times, but most of it has no answer or is old:

Recommended HD camera (Best thread i found. suggests logitech quickcam 9000 pro, not on market anymore)

Which Machine Vision Vendor provides OpenCV support (General Advice not sure what to make of it)

Which Camera for body detection (2010, no clear answer)

OpenCV Webcam Compability (2011)

List of compatible camera tested with opencv (dead link, no copy found yet)

Industrial Camera in Python (no answer and not what i need)

Example Picture taken with Samsung Galaxy S2

2013-11-29 04:04:22 -0500 asked a question windows tutorial outdated?

The Windows Tutorial explains how to add librarys:

The names of the libraries are as follow:

    opencv_(The Name of the module)(The version Number of the library you use)d.lib

A full list, for the latest version would contain:

    opencv_core231d.lib
    opencv_imgproc231d.lib
    [...]

shouldn't those be "opencv_core247d.lib", opencv_imgproc247d.lib, ect?

Thanks so much for the Tutorial btw, it is a great help. btw: The link to "Path Editor" in "Set the OpenCV enviroment variable and add it to the systems path" is probably down for good.