Method for stereo matching using end-to-end convolutional neural network
AssigneeResearch & Business Foundation Sungkyunkwan University
InventorsJaewook JEON, Phuoc Tien NGUYEN, Jinyoung BYUN
Life of this patent
Estimating the term…
Loading patent…
AssigneeResearch & Business Foundation Sungkyunkwan University
InventorsJaewook JEON, Phuoc Tien NGUYEN, Jinyoung BYUN
Estimating the term…
Disclosed is a stereo matching method for generating a disparity map from a stereo image. The stereo matching method may include obtaining a cost volume by applying a first convolutional neural network (CNN) and a second CNN to a left image and a right image, respectively, wherein the cost volume is determined based on feature maps extracted from the left image and the right image, respectively, performing normalization on the cost volume by applying a third CNN, up-sampling the normalized cost volume, and obtaining a disparity map by applying regression analysis to the up-sampled cost volume.
A stereo matching method for generating a disparity map from a stereo image, comprising:
A stereo matching apparatus comprising:
Dependencies are inferred from the claim text.