This paper suggests features for depth image. It said when using HOG with depth images, much improved performance can be made which out-performs standard HOG.
The below is the impressive statements.
Two baseline features were used for comparison: standard HOG over the calculated RGB grayscale image itself and HOG using the depth map as a grayscale image. Both of these were intended as baselines, and HOG over the RGB grascale is the only feature in this paper that directly incorporates numerical color data.
'Papers > Machine learning' 카테고리의 다른 글
supervised vs. unsupervised vs. reenforcement learning (0) | 2016.03.18 |
---|---|
Business travel for caipt 2015 (0) | 2015.07.02 |
Depth Kernel Descriptors for Object Recognition (0) | 2015.05.13 |
A Case Study of Mobile based Object recognition by BOF Model (0) | 2015.05.09 |
Case study of depth image processing (0) | 2015.05.08 |