Ask Your Question

Ankan's profile - activity

2017-06-13 09:36:55 -0500 answered a question How to identify what's new in image?

Any suggestions?

2017-03-08 05:53:53 -0500 commented question How to identify what's new in image?

Analyzing the object when falling is hard to succeed as first of all the hand of the person who are throwing the trash will be included and then it's hard to get a sharp image. Maybe with a good highspeed camera it would be possible but don't have one.

Maybe it would be possible to follow the trash down and analyse when it's in the bin, but I guess the hand can be the problem if hides the fall.

The best would be if I could mask the new object with a before and after image. It should be possible to filter it in some kind of way as the human eye can see what's new. How do I ignore movements of already throwed trash? I have both depthinfo and rgb image before and after. The depthcamera have no problem with thick objects, but on thinner ... (more)

2017-02-24 07:21:23 -0500 commented answer How do I get the lowest value of all the non zero value pixels?

Thanks! I had to use threshhold to create that mask as I'am using Python but it works great,

2017-02-24 04:46:32 -0500 asked a question How do I get the lowest value of all the non zero value pixels?

How do I get the lowest value of all the non zero value pixels?

2017-02-21 02:33:25 -0500 commented question How to identify what's new in image?

I think you are right. The problem is to get a sharp image while the item is falling with when the camera only make 60fps. But I was thinking if it would be possible to track the falling item to where it lands and then analyse that area.

Else I could use the depth information from the camera (Using realsense SR300) but there is lot of noise from edges that has to be handled when using absdiff.

2017-02-17 02:27:45 -0500 received badge  Enthusiast
2017-02-17 02:27:35 -0500 received badge  Enthusiast
2017-02-14 07:38:25 -0500 asked a question How to identify what's new in image?

I have a camera facing into a trashbin. I want to take a picture of every new threwn item.

To start with I don't realy know what way to go. Take one picture after something is threwn and compare with last taken picture or use live camera stream analyse.

The problem is to mask that new item as some stuff like glassbottles are both transparent and heavy which makes them hard to mask and they often moves other trash little bit. If I have one white item in the trashbin and the new item is also white it's hard to mask that new item by absdiff as the differences is to small. In those cases maybe a edge-detection solution could fix it, but I don't know how to remove edges of all old stuff and only get the edge of the new item, and then mask the area inside.

Any suggestions how to solve this?

2017-02-09 04:58:23 -0500 commented question Depth- och IR-data from RealSense camera (SR300)?

Librealsense looks like Intel Realsense SDK?

2017-02-09 04:35:03 -0500 commented question Depth- och IR-data from RealSense camera (SR300)?

It looks harder to use OpenCV and TensorFlow from C++ than Python. But maybe that is the way I have to go. Python feels much more straightforward.

If I use Python it would be cross-platform. Do I have to compile librealsense for Windows or is there a executable installation?

2017-02-09 03:17:35 -0500 asked a question Depth- och IR-data from RealSense camera (SR300)?

I try to combine a realsense SR300 camera, OpenCV and TensorFlow under Windows.

I can get that RGB stream from the camera when using OpenCV in python on windows. But how do I get the depth and IR image in python or do I have to do it all in c++?

I have found PyRealSense but I don't know how to install it as I have never worked with Python earlier. Is PyRealSense, what I need or what do I need to get this combination with ir and depth to work?

2017-01-20 07:55:16 -0500 received badge  Student (source)
2017-01-20 07:49:34 -0500 asked a question Recognizing 3d scanned objects

There is object recognition based on regular images, but I would like to recognize objects with 3d scanned object information. I think that would make the recognition more trustful or general as the information is in 3D and not only in 2D. A 3d scanned bottle would be recognized as a bottle even if the label is not the same.

Is there any free or commercial applications that can help me with this. I was looking at opencv but I'am not sure if it could help me with this.

I have looked at the Intel RealSense SDK and it gives me object tracking, but it is based on 2d information (image), and if I turn the object to much it would not be recognized.

I hope someone can help me, where to look, or what I need.