some good resources

UC Berkeley Computer Vision Group 

Contour detection and image segmentation resources

• A large dataset of natural images that have been manually segmented. The human annotations serve as ground truth for learning grouping cues as well as a benchmark for comparing different segmentation and boundary detection algorithms.
  
• The most recent algorithms our group has developed for contour detection and image segmentation.
  
• Performance evaluation of the leading computational approaches to grouping.

http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/resources.html

BGSLibrary

用于图像背景提取的C++库，实现了很多种背景提取算法。提供源代码，可以嵌入的其他C++程序中，也提供了一个MFC程序，方便交互使用。

https://github.com/andrewssobral/bgslibrary

List of the algorithms available in BGSLibrary

• Basic methods, mean and variance over time:
• • Static Frame Difference
• • Frame Difference
• • Weighted Moving Mean
• • Weighted Moving Variance
• • Adaptive Background Learning
• • Adaptive-Selective Background Learning
• • (1) Temporal Mean
• • (1) Adaptive Median of McFarlane and Schofield (1995) (paper)
• • (1) Temporal Median of Cucchiara et al (2003) and Calderara et al (2006) (paper1) (paper2) (paper3)

• Fuzzy based methods:

• • (2) Fuzzy Sugeno Integral (with Adaptive-Selective Update) of Hongxun Zhang and De Xu (2006) (paper)
• • (2) Fuzzy Choquet Integral (with Adaptive-Selective Update) of Baf et al (2008) (paper)
• • (3) Fuzzy Gaussian of Laurence Bender (adapted version of Wren (1997) with Sigari et al (2008) approach) (paper)

• Statistical methods using one gaussian:

• • (1) Gaussian Average of Wren (1997) (paper)
• • (3) Simple Gaussian of Benezeth et al (2008) (paper)

• Statistical methods using multiple gaussians:

• • (1) Gaussian Mixture Model of Stauffer and Grimson (1999) (paper)
• • (0) Gaussian Mixture Model of KadewTraKuPong and Bowden (2001) (paper)
• • (0) Gaussian Mixture Model of Zivkovic (2004) (paper1) (paper2)
• • (1) Gaussian Mixture Model of Zivkovic (2004)
• • (3) Gaussian Mixture Model of Laurence Bender (implements the classic GMM with Mahalanobis distance) (paper)

• Type-2 Fuzzy based methods:

• • (2) Type-2 Fuzzy GMM-UM of Baf et al (2008) (paper)
• • (2) Type-2 Fuzzy GMM-UV of Baf et al (2008) (paper)
• • (2) Type-2 Fuzzy GMM-UM with MRF of Zhao et al (2012) (paper1) (paper2)
• • (2) Type-2 Fuzzy GMM-UV with MRF of Zhao et al (2012) (paper1) (paper2)

• Statistical methods using color and texture features:

• • (1) Texture BGS of Heikkila et al. (2006) (paper)
• • (8) Texture-Based Foreground Detection with MRF of Csaba Kertész (2011) (paper)
• • (4) Multi-Layer BGS of Jian Yao and Jean-Marc Odobez (2007) (paper)
• • (10) MultiCue BGS of SeungJong Noh and Moongu Jeon (2012) (paper)

• Non-parametric methods:

• • (5) Pixel-Based Adaptive Segmenter (PBAS) of Hofmann et al (2012) The PBAS algorithm was removed from BGSLibrary because it is based on patented algorithm ViBE. (paper)
• • (0) GMG of Godbehere et al (2012) (paper)
• • (6) VuMeter of Goyat et al (2006) (paper)
• • (7) KDE of Elgammal et al (2000) (paper)
• • (9) IMBS of Domenico Bloisi and Luca Iocchi (2012) (paper)

• Eigenspace-based methods:

• • (1) Eigenbackground / SL-PCA of Oliver et al (2000) (paper)

• Neural and neuro-fuzzy methods:

• • (3) Adaptive SOM of Maddalena and Petrosino (2008) (paper)
• • (3) Fuzzy Adaptive SOM of Maddalena and Petrosino (2010) (paper)

List of the algorithms available in BGSLibrary

• Basic methods, mean and variance over time:
• • Static Frame Difference
• • Frame Difference
• • Weighted Moving Mean
• • Weighted Moving Variance
• • Adaptive Background Learning
• • Adaptive-Selective Background Learning
• • (1) Temporal Mean
• • (1) Adaptive Median of McFarlane and Schofield (1995) (paper)
• • (1) Temporal Median of Cucchiara et al (2003) and Calderara et al (2006) (paper1) (paper2) (paper3)

• Fuzzy based methods:

• • (2) Fuzzy Sugeno Integral (with Adaptive-Selective Update) of Hongxun Zhang and De Xu (2006) (paper)
• • (2) Fuzzy Choquet Integral (with Adaptive-Selective Update) of Baf et al (2008) (paper)
• • (3) Fuzzy Gaussian of Laurence Bender (adapted version of Wren (1997) with Sigari et al (2008) approach) (paper)

• Statistical methods using one gaussian:

• • (1) Gaussian Average of Wren (1997) (paper)
• • (3) Simple Gaussian of Benezeth et al (2008) (paper)

• Statistical methods using multiple gaussians:

• • (1) Gaussian Mixture Model of Stauffer and Grimson (1999) (paper)
• • (0) Gaussian Mixture Model of KadewTraKuPong and Bowden (2001) (paper)
• • (0) Gaussian Mixture Model of Zivkovic (2004) (paper1) (paper2)
• • (1) Gaussian Mixture Model of Zivkovic (2004)
• • (3) Gaussian Mixture Model of Laurence Bender (implements the classic GMM with Mahalanobis distance) (paper)

• Type-2 Fuzzy based methods:

• • (2) Type-2 Fuzzy GMM-UM of Baf et al (2008) (paper)
• • (2) Type-2 Fuzzy GMM-UV of Baf et al (2008) (paper)
• • (2) Type-2 Fuzzy GMM-UM with MRF of Zhao et al (2012) (paper1) (paper2)
• • (2) Type-2 Fuzzy GMM-UV with MRF of Zhao et al (2012) (paper1) (paper2)

• Statistical methods using color and texture features:

• • (1) Texture BGS of Heikkila et al. (2006) (paper)
• • (8) Texture-Based Foreground Detection with MRF of Csaba Kertész (2011) (paper)
• • (4) Multi-Layer BGS of Jian Yao and Jean-Marc Odobez (2007) (paper)
• • (10) MultiCue BGS of SeungJong Noh and Moongu Jeon (2012) (paper)

• Non-parametric methods:

• • (5) Pixel-Based Adaptive Segmenter (PBAS) of Hofmann et al (2012) The PBAS algorithm was removed from BGSLibrary because it is based on patented algorithm ViBE. (paper)
• • (0) GMG of Godbehere et al (2012) (paper)
• • (6) VuMeter of Goyat et al (2006) (paper)
• • (7) KDE of Elgammal et al (2000) (paper)
• • (9) IMBS of Domenico Bloisi and Luca Iocchi (2012) (paper)

• Eigenspace-based methods:

• • (1) Eigenbackground / SL-PCA of Oliver et al (2000) (paper)

• Neural and neuro-fuzzy methods:

• • (3) Adaptive SOM of Maddalena and Petrosino (2008) (paper)
• • (3) Fuzzy Adaptive SOM of Maddalena and Petrosino (2010) (paper)

A good blog about computer graphics 

http://www.morethantechnical.com/

比较全面的3D数据处理建模等链接收集

http://www.pclcn.org/bbs/forum.php?mod=viewthread&tid=666

SIGGRAPH 2014 papers

http://kesen.realtimerendering.com/sig2014.html

SIFT flow的作者Ce Liu的主页

http://people.csail.mit.edu/celiu/

Learning to Detect a Salient Object

Matlab implementation of a Salient Object Detector

http://www.cs.unc.edu/~vicente/code.html