User:Kaiaw

From Robin

(Difference between revisions)
Jump to: navigation, search
(Master's Thesis)
(Master's Thesis)
 
Line 2: Line 2:
''Convolutional networks for road-scene understanding''
''Convolutional networks for road-scene understanding''
-
To make a vehicle drive autonomously, images from color cameras are segmented into seperate regions representing different classes. Pre-trained deep convolutional neural networks is adapted to perform this task by supplementing with road data, and fusing low/high level information from different layers.
+
To make a vehicle drive autonomously, images from color cameras are segmented into seperate regions representing different classes. Pre-trained deep convolutional neural networks is adapted to perform this task by supplementing with road data, and fusing low/high level information from layers of different depth.

Current revision as of 15:07, 11 February 2016

Master's Thesis

Convolutional networks for road-scene understanding

To make a vehicle drive autonomously, images from color cameras are segmented into seperate regions representing different classes. Pre-trained deep convolutional neural networks is adapted to perform this task by supplementing with road data, and fusing low/high level information from layers of different depth.

Personal tools
Front page