How to run Hough transform in real time?

13 ビュー (過去 30 日間)
engineer
engineer 2019 年 11 月 13 日
コメント済み: engineer 2019 年 11 月 22 日
Hi everybody
I would like to detect single object (circular) from the video in real time. I would like to do this by using Matlab. I am aware that Hough transform is a solution for this.
My question: Can I do this by using Hough transform in real time ( up to like 10 to 15 fps)? Is there any other method that you can suggest me?
Thanks!

採用された回答

Prabhan Purwar
Prabhan Purwar 2019 年 11 月 22 日
Hi,
You may make use of GPU accelerated Hough transform algorithm to detect a circular object in the acceptance rate of 7 fps (real-time).
GPU Accelerated Hough Transform involves the following process:
The image taken from the webcam is preprocessed with a Median filter followed by Sobel edge detection and a thinning algorithm. Then, a Generalized Hough Transform is performed using a custom, user-defined shape.
Object Detection can be classified into three broad categories:
(1) Image processing/Computer Vision - Color Thresholding, Blob Analysis, Histogram of Gradients, Speeded-Up Robust Features.
(2) Machine Learning- Cascade Object Detector (Viola-Jones Algorithm), Aggregate Channel Features (ACF)
(3) Deep Learning - YOLO v2, R-CNN, Fast R-CNN and Faster R-CNN
Refer to the following links for further information:
  1 件のコメント
engineer
engineer 2019 年 11 月 22 日
Thank you very much. I will look into the links you provided.

サインインしてコメントする。

その他の回答 (0 件)

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by