Discussion

SementicSegmentation.org

resource

http://cs.nyu.edu/~ccouprie/code.html

cpp implementation

https://github.com/cvjena/cn24

CN24 is a complete semantic segmentation framework using fully convolutional networks. It supports a wide variety of platforms (Linux, Mac OS X and Windows) and libraries (OpenCL, Intel MKL, AMD ACML…) while providing dependency-free reference implementations. The software is developed in the Computer Vision Group at the University of Jena.

http://ivrl.epfl.ch/research/superpixels

这个是用来取super pixel的

http://www.codeproject.com/Articles/751744/Image-Segmentation-using-Unsupervised-Watershed-Al

这个也是cpp的，还是unsupervise，不过不知道行不行

视频的肯定没法用，视频是连续的图片没错，但是街景数据集里的图片并不连续啊。。。。。

"数据集有这样几个都比较好用，KITTI，CBCL StreetScenes Challenge Framework，谷歌街景的一个数据集"

deeplab的caffe model没法直接用原生的caffe编译出来的运行。
应该是因为它们加上了自己的代码字段。