Question

Closed. This question is seeking recommendations for books, tools, software libraries, and more. It does not meet Stack Overflow guidelines. It is not currently accepting answers.

We don’t allow questions seeking recommendations for books, tools, software libraries, and more. You can edit the question so it can be answered with facts and citations.

Closed 7 years ago.

Improve this question

I m looking to do some image processing in Java and I ll be developing in Ubuntu with Eclipse. So here is my objective:

From a greyscale image, I would like to be able to detect certain sized objects and draw a rectangular frame around them. However, the catch is that this image is captured from a thermal imaging camera so to detect body heat the pixels will have a value within a certain range. After detecting all the objects in the image, I will need to count them, but that s later.

So here s my challenge. Which tools/apis/open classes can I use to do something like this. I looked around and found some basic manipulations such as rotate, crop, resize. But haven t really found anything I can use.

Where should I look/start?

thanks a lot in advance

Answer 1

ImageJ is very useful: http://rsbweb.nih.gov/ij/

Although ImageJ is set up as a GUI, you can use it as a library too (I do that too)

You ll have to search for a proper object detection plugin (but there are some floating around...)

good luck! Eelco

Answer 2

On this page you can find open-source tool for image processing and image mining: http://spl.utko.feec.vutbr.cz/en/image-processing-extension-for-rapidminer-5

Answer 3

This article fully explains the algorithm you re looking for, and the accompanying source code is here. You can see it in action in this video.

(Disclaimer: I m the author; but I do think this is very useful, and have successfully used the algorithm a lot myself.)

The algorithm tracks moving objects, finds their bounding rectangle (which the application draws), counts the number of pixels in each objects, correlates them throughout frames as the same object (with an int ID). You may need to do a trival conversion of your grayscale image to RGB (by copying the gray values to all three channels) since the algorithm was designed for color input.

When it comes to commercial computer vision applications, OpenCV and the Point Cloud Library aka PCL are your best friends. And articles like the one linked explains how to use tools like OpenCV to accomplish full stack motion tracking. (The pure Java implementation shows how it works down to the individual pixels.)

友情链接