5

Hi I am new to image processing field. My project is to classify the objects in an image/Video. The input is an image/video from surveillance camera. I should classify the objects into three classes. 1) Humans 2) Animals 3) Others (cars). We can consider a fixed background.

Can any one suggest any proven algorithms or papers or opensource code for this purpose? offcourse googling is obvious solution but always an experienced eye is always helpful!

2vision2
  • 4,933
  • 16
  • 83
  • 164
  • 5
    The question you are asking could serve as a PhD thesis topic. It's *way* too broad for StackOverflow. Maybe the digital signal processing stack exchange is better suited for it. – ely Oct 22 '12 at 15:02
  • @EMS I have posted the same in Digital signal processing and here is the link http://dsp.stackexchange.com/questions/4750/classification-of-objects-from-a-video-image-human-animals-otherscars-etc#comment8755_4750 – 2vision2 Oct 23 '12 at 03:45

1 Answers1

13

For your purposes, I think the best option is LatSVM because the authors disponibilizes the implementation in MATLAB and the detector models already trained. The already trained models includes:

  • Aeroplane, Boat, Bus, Car, Bicycle
  • Bottle, TV, Sofa
  • Bird, Cat, Horse, Sheep, Dog
  • etc.

There is also an implementation in OpenCV if you need (found out in this question).

Other Detector Implementations

Give a look at the following surveys in Pedestrian Detection:

  1. Pedestrian Detection: An Evaluation of the State of the Art (2012).
  2. Survey of Pedestrian Detection for Advanced Driver Assistance Systems (2010).

State of Art

  • Pedestrian detection at 100 frames per second. This work proposed by [Benenson et al., 2012] achieves a high detection speed with state-of-art precision [webpage].
  • Object Detection with Discriminatively Trained Part Based Models aka LatSVM Achieved good results on PASCAL 2006, 2007 and 2008. This work doesn't show only for pedestrian detection, but also for cars, cats, horse, sofa etc. You really should give a look at this one [webpage]
  • Human Detection using Partial Least Squares Analysis. [Schwartz et al., 2009] proposed the use of Partial Least Squares analysis which allows to handle high-dimensional space features.

Classical Works

The following works has important contributions and are references in every work of pedestrian detection. HOG feature, Integral Image, and Cascade of Rejection are used by several works, including the one by [Benenson et al., 2012].

  • Histograms of Oriented Gradients for Human Detection
  • Fast Human Detection Using a Cascade of Histograms of Oriented Gradients
Community
  • 1
  • 1
Yamaneko
  • 3,433
  • 2
  • 38
  • 57
  • +1 Thanks for the answer. I have edited my question please have a look. The input may be image or video. – 2vision2 Oct 22 '12 at 15:01
  • give a look at the links I've put in my answer. They also disponibilize their source code. The *Object Detection (...)* already has trained models for what you want. I'll update my answer – Yamaneko Oct 22 '12 at 15:04
  • Thanks a lot!!!!Am waiting for your update. – 2vision2 Oct 22 '12 at 15:13
  • I posted the same in Digital Signal processing in Stack exchange and here is the link. http://dsp.stackexchange.com/questions/4750/classification-of-objects-from-a-video-image-human-animals-otherscars-etc#comment8755_4750 I got a response suggesting http://www.vlfeat.org/. Please have a look and your views and suggestions will be greatfull. – 2vision2 Oct 23 '12 at 03:49
  • Please have a look at my another post also. http://stackoverflow.com/questions/13024141/face-authentication – 2vision2 Oct 23 '12 at 05:55
  • Hi, @user1317084 -- I'll take a look at these questions, maybe I can contribute with something. I could not check them yet because I'm in a rush this week. Thanks for inviting me :) – Yamaneko Oct 24 '12 at 03:13