目標檢測方法__第一版
這篇寫在兩年前!!!
目標檢測問題,對應英文:Target Detection
下面是解決這類問題的state-of-the-art方法的基本介紹:
https://www.zhihu.com/question/34223049
https://zhuanlan.zhihu.com/p/21533724
http://zhangliliang.com/2015/05/19/paper-note-object-proposal-review-pami15/
http://people.eecs.berkeley.edu/~rbg/index.html
https://zhuanlan.zhihu.com/p/21412911
http://blog.cvmarcher.com/posts/2015/05/17/multi-region-semantic-segmentation-aware-cnn/
最早的方法是:Appearance-based methods,這種方法是我們理解一個目標最直接的方式,比如RGB顏色分布,形狀大小,位置方向等等;比如Halcon中的各種Region Selection方法。
傳統的邊緣匹配,滑窗,灰度匹配,梯度匹配,直方圖及改進的直方圖算法匹配,Large modelbases等。
模板匹配,我覺得模板匹配應該是基於Appearance-based methods的,具體我不熟:
http://www.opencv.org.cn/opencvdoc/2.3.2/html/doc/tutorials/imgproc/histograms/template_matching/template_matching.html
http://blog.csdn.net/zouxy09/article/details/8549743
http://www.halcon.com/download/reference/create_template.html
然後便是Feature-based methods
對於傳統的方法,其對應經典特征的基本介紹:
Hog:
http://blog.csdn.net/zouxy09/article/details/7929348
http://blog.csdn.net/abcjennifer/article/details/7365651
http://www.cnblogs.com/tornadomeet/archive/2012/08/15/2640754.html
https://github.com/DaHoC/trainHOG
https://github.com/ivanaslamov/hog_sse
Sift:
http://blog.csdn.net/abcjennifer/article/details/7639681
SURF:
https://zh.wikipedia.org/wiki/%E5%8A%A0%E9%80%9F%E7%A8%B3%E5%81%A5%E7%89%B9%E5%BE%81
這些特征OpenCV中都有:
https://www.zhihu.com/question/24038129
DPM算法:
https://www.zhihu.com/question/29300042
http://blog.csdn.net/ttransposition/article/details/12966521
http://blog.csdn.net/ttransposition/article/details/41806601
https://github.com/rbgirshick/voc-dpm
最後便是深度學習了
其他的一些背景資料:
http://blog.cvmarcher.com/posts/2015/06/02/The-Role-of-Features-Algorithms-and-Data-in-Visual-Recognition/
https://en.wikipedia.org/wiki/Outline_of_object_recognition
https://zhuanlan.zhihu.com/p/21344595?refer=xlvector
人臉識別(人臉識別可以推廣到各種物體識別),下面是傳統的,OpenCV裏有的方法:
http://blog.csdn.net/smartempire/article/details/21406005
http://blog.csdn.net/smartempire/article/details/23249517
http://blog.csdn.net/smartempire/article/details/23377385
未完待續...
目標檢測方法__第一版