Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 4 years ago.
Improve this question
I have an image processing project, clearly the title reveals what it is.
Assume I have a camera on top of the one of the traffic lights beside a four way in a heavy crowded city. The project should get the recorded video from that camera.
Identify the cars on the scene and track their movements.
for the tracking part I believe Lucas Kanade with pyramids or even Lucas Kanade Tomasi would be sufficient.
But before tracking I should Identify the cars coming into the scene. I wonder how I can do that. I mean how I can distinguish between people/trees/building/... and cars.
what should I do for identifying ?
I want you to be kind enough with me and share your ideas.
thanks.
I detected contours and filtered them by size. That worked for me using the same video available on the link posted by GiLevi (http://www.behance.net/gallery/Vehicle-Detection-Tracking-and-Counting/4057777). You could also perform background sutraction, and detect blobs, on the foreground mask; again filtering by size, so as to differentiate from cars, people etc.
Related
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 1 year ago.
Improve this question
I'm using YOLO to detect people in a video stream from camera and would like to "map" founded bonding boxes onto 2D plan of the room.
Could you please give me a hint which algorithms might be used for it?
The idea is shown on the picture from the github repository, but I need not to measure distance but "project" an object position on 2D map of the room
https://github.com/sassoftware/iot-tracking-social-distancing-computer-vision
Using 3D cameras or just 2 regular ones might help a lot as well
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 3 years ago.
Improve this question
I wrote a 2d simulation (very similar to the Atari- OpenAi games) in pygame, which I need for an reinforcement learning project. I'd like to train a neural network using mainly image data, i.e. screenshots of the pygame gameboard.
I am able to make those screenshots, but:
- Is possible to gather this image data - or, more precisely, the
corresponding rgb image matrix - also without rendering the whole
playing ground to the screen?
As I figured out there is the possibility to do such in pyglet ... But I would like to avoid to rewrite the whole simulation.
Basically, yes. You don't have to actually draw anything to the screen surface.
Once you have a Surface, you can use methods like get_at, the PixelArray module or the surfarray module to access the RGB(A)-values of each pixel.
Closed. This question is opinion-based. It is not currently accepting answers.
Want to improve this question? Update the question so it can be answered with facts and citations by editing this post.
Closed 3 years ago.
Improve this question
I am working on image segmentation and object detection and I think they do the same thing (they both localize and recognize objects in the raw picture). Is there any benefit in using object detection at all cause deeplab_V3+ do the job with better performance than any other object detection algorithms?
you can look at deeplab_V3+ demo in here
In object detection, the method localizes and classifies the object in the image based on bounding box coordinates. However, in image segmentation, the model also detects the exact boundaries of the object, which usually makes it a bit slower. They both have their own uses. In many applications (e.g. face detection), you only want to detect some specific objects in images and don't necessarily care about the exact boundaries of them. But in some applications (e.g. medical images), you want the exact boundaries of a tumor for example. Also we can consider the process of preparing the data for these tasks:
classification: we only provide a label for each image
localization: we provide a bounding box (4 elements) for each image
detection: we should provide a bounding box and a label for each object
segmentation: we need to define the exact boundaries of each object (semantic segmentation)
So for segmentation, more work is required both in providing the data and in training a (encoder-decoder) model, and it depends on your purpose of the task.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 7 years ago.
Improve this question
I'm trying to implement an algorithm detecting and counting number of hairs. The main idea is described as below:
Enhance Image by applying Contrast Stretching.
Segment image.
Do thinning segmented image.
Detect Line by HoughLine Transform and Relaxation.
The implementation is based on Opencv/C++. However, since Thinning algorithm doesn't perform accurately, it leads to wrong result when I apply HoughLine, especially in case of overlap or touching hair. Moreover HoughLine is sensitive with parameters. If you have other ideas, please help me. Thank you very much.
Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 5 years ago.
Improve this question
Is it possible to use a couple of webcams (or any camera for that matter) to get the x, y and z co-ordinates of an object and then track them perhaps using OpenCV as it moves around a room.
I'm thinking of it in relation to localising and then controling an RC helicopter.
Yes. You need to detect points on both images simultaneously and then match the pairs that correspond to the same point in the scene. This way you will have the same point represented by different coordinate spaces (camera 1 and camera 2).
You can start here.
If using depth sensor is acceptable then you can take a look at how ReconstructMe does it. Otherwise take a look at this google search.