Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding
Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding
深度學習思想越來越火,在今年的CVPR 2015 文章中相關文章就有20多篇,可見是很火的。近期在做關於語義切割和場景解析的內容,看到這篇文章後也是很高興。
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 at the Computer Vision Group, University of Jena.
文章說能夠在Windows、Mac和Linux系統上很好的執行,又能夠支持OpenCL、Intel MKL , AMD ACML 來並行計算加速。看起來還真不錯!
官方源代碼地址:
[ CN24 ]
接下來先上實驗結果:
實驗環境[ubuntu 15.04]。臨時沒實用GPU加速
代碼程序文件夾:
執行後的結果:
單張圖片測試結果,左側是語義切割後的結果,右側是真實的測試圖。
沒實用GPU加速,果然處理一張圖片還是挺慢的,耗時還是挺多的,例如以下圖所看到的:
以下就是摸索代碼。下一節會繼續分享學習過程,謝謝!
Convolutional Patch Networks with Spatial Prior for Road Detection and Urban Scene Understanding