Blob detection algorithm advise

Hi,

I'm having a project which require me to detect pedestrian through visual image. I would like to prototype it with matlab and a normal camera and it should able to perform the function in real time.

Currently i'm still in early stage of development and I understand there are many methods to detect blob or object from a video such as frame based , motion based and even some other algorithms which i not even aware of. Therefore is there anyone who familiar in this can introduce to me all possible methods to do so?

I come across this algorithms which use motion based for detecting human: https://www.mathworks.com/help/vision/examples/motion-based-multiple-object-tracking.html

However, in my project, the background will be constantly changing as well as the pedestrian because the camera will put inside a moving car to detect the pedestrian. Therefore i hope i can see all the possible algorithms first and hope there is an algorithms which can suit inside the project.

Thank you and any help would be appreciated.

Have you taken a look at opencv?

It implements various training algorithms (HAAR, LBP) and some others if I recall correctly.

How long do you have for implementing this and on what kind of platform?

Thanks for the suggestion. However, currently my main concern is to extract the all possible pedestrian blob out of the real time video. And i would like to know some effective way to detect the blobs through real time video. This is due to some algorithms are not suit in the video and extra work need to be done in order to achieve the same result. Once all the blob is detected, the matching part will be done by the trained model. Probably using SVM + some boosting.

I just started on this project in a week time and i would like to implement it with Matlab in window and a normal USB camera first.