Apparatus and method for processing image data
AssigneeNokia Technologies Oy
InventorTinghuai WANG
Life of this patent
Estimating the term…
Abstract
Apparatus for processing image data associated with at least one input image, including a convolutional neural network, CNN, -based encoder configured to provide a plurality of hierarchical feature maps based on the image data, a decoder configured to provide output data based on the plurality of feature maps, wherein the decoder includes a convolutional long short-term memory, Conv-LSTM, module configured to sequentially process at least some of the plurality of hierarchical feature maps.
Claims13
Apparatus for processing image data associated with at least one input image, comprising:
- at least one processor;
- and
- at least one memory including computer program;
- the at least one memory and the computer program configured to, with the at least one processor, cause the apparatus at least to implement a convolutional neural network (CNN),-based encoder configured to provide a plurality of hierarchical feature maps based on said image data, a decoder configured to provide output data based on said plurality of feature maps, wherein said decoder comprises a convolutional long short-term memory (Conv-LSTM) module configured to sequentially process at least some of said plurality of hierarchical feature maps.
Method of operation an apparatus for processing image data associated with at least one input image, the method comprising:
- first providing, a convolutional neural network (CNN)-based encoder, a plurality of hierarchical feature maps based on said image data;
- and second providing, using a decoder, output data based on said plurality of feature maps, the second providing including sequentially processing at least some of said plurality of hierarchical feature maps using a convolutional long short-term memory module (Conv-LSTM).
The method according 7, comprising:
- further performing, based on the output data, one of dense prediction, or sparse prediction.
Dependencies are inferred from the claim text.