Object Recognition Review

I. The history of recognition

II. The process of object recognition

http://vision.stanford.edu/teaching/cs131_fall1617/lectures/lecture17_intro_objrecog_cs131.pdf

Step 1. Image features

Step 2. Learning

A. Classification

There are many methods to choose from:

• K-nearest neighbor

• SVM

• Neural networks

• Naïve Bayes

• Bayesian network

• Logic regression

• Randomized Forests

• Boosted Decision Trees

• RBMs

• Etc.

III. Typical Method

A. Bags of Features

http://www.cs.cornell.edu/courses/cs4670/2015sp/lectures/lec35_reco3_web.pdf

(1) Origin

Texture recognition:

• Texture is characterized by the repetition of basic elements or textons

• For stochastic textures, the identity of the textons, not their spatial arrangement, matters
Julesz, 1981; Cula & Dana, 2001; Leung & Malik 2001; Mori, Belongie & Malik, 2001; Schmid 2001; Varma & Zisserman, 2002, 2003; Lazebnik, Schmid & Ponce, 2003

Bag-of-words models:

Orderless document representation: frequencies of words from a dictionary. Salton & McGill (1983)

(2) Outline

Step 2: Using K-means clustering

Step 4: K nearest neighbors

B. CNN(Convolutional Neural Network)

http://cs231n.github.io/convolutional-networks/#overview

IV. Data Set

A. Pedestrian

http://ieeexplore.ieee.org.libproxy.sdsu.edu/stamp/stamp.jsp?arnumber=5975165&tag=1

  1. Caltech Pedestrian data set
    P. Dolla´r, C. Wojek, B. Schiele, and P. Perona, “Pedestrian Detection: A Benchmark,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2009.
  2. ETH:
    A. Ess, B. Leibe, and L. Van Gool, “Depth and Appearance for Mobile Scene Analysis,” Proc. IEEE Int’l Conf. Computer Vision, 2007.
  3. TUB-Brussels
    C. Wojek, S. Walk, and B. Schiele, “Multi-Cue Onboard Pedestrian Detection,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2009
  4. Daimler
    M. Enzweiler and D.M. Gavrila, “Monocular Pedestrian Detection: Survey and Experiments,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 31, no. 12, pp. 2179- 2195, Dec. 2009.
  5. INRIA
    N. Dalal and B. Triggs, “Histograms of Oriented Gradients for Human Detection,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2005.

B. Vehicle