how to plot speed graph from centroid of the detected object in image processing ?

3 visualizzazioni (ultimi 30 giorni)
Dear All,
i would like to plot the speed of the detected object moving only in the x direction in real time.(Not y direction) so i have tried with the following code but didn't get the appropriate solution. please find the attached code and graph i have sending with this file. the graph is not correct because i didnt understant how to implement the following formula
speed= distance/ time,
how can i modified the attached code to display the detected object and speed of moving object from centroid only in the x-direction as in the attached figure in real time.
hope for your appropriate solution.
Thank you.

Risposta accettata

Image Analyst
Image Analyst il 14 Mag 2016
Add a third axes control. Then get the object alone by cropping it from the entire image using the object's bounding box and the imcrop() function. Then display the cropped image in the third axes.
  4 Commenti
Biswas Lohani V K
Biswas Lohani V K il 15 Mag 2016
The information that you provided was also very useful and i am using that as well.
Now my concern is , actually i know theoretically how to calculate velocity and acceleration from the distance & time.
Speed = Distance/ time & Acceleration = Speed/ time
But honestly i didn't understand how to apply these formula in Matlab to get the Speed and acceleration in real time.
If you don't mind could you please try to explain with MATLAB command. This might be the simple question but i am struggling to get the appropriate result.
Here is the work up to the date, where the graph are not accurate.
If you don't mind, I would like to request to give idea with Matlab code.
Thank you.
Image Analyst
Image Analyst il 15 Mag 2016
Let's assume 1 object. For each frame you should calculate the centroid location. So now you have x and y vectors. You can also keep distance, speed, and acceleration arrays in your loop over frames.
thisDistance = sqrt((x(frame)-x(frame-1)^2+(y(frame)-y(frame-1))^2);
distance(frame) = distance(frame-1) + thisDistance;
frameTime = toc;
speed(frame) = thisDistance / frameTime; % Frame time is like 1/10 or /130 of a second or whatever. use tic and toc to get exact time.
accel(frame) = (speed(frame) - speed(frame-1)) / frameTime;
and so on.

Accedi per commentare.

Più risposte (0)

Community Treasure Hunt

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

Start Hunting!

Translated by