We propose SURF-LSTM, a low complexity deep architecture to learn image absolute pose (position and orientation) in indoor environments using SURF descriptors and recurrent neural networks. Given the strongest SURF features descriptors of an input image, we use 2 layers of bidirectional long short term memory (LSTM) to model the sequential relation between them to learn the 6 degrees of freedom absolute pose in an arbitrary reference frame. In addition to achieving competitive performance compared to existing image localization methods, our system can be trained in less than 10 minutes instead of hours by the state of the art. It requires as small as 0.0128 MB to save the image frame rather than 0.08 MB compared to other methods that use the cropped images and the weights file needs 1.5 MB of storage compared to 100 MB of other methods which leads to significant time and space efficiency.
SURF-LSTM: A Descriptor Enhanced Recurrent Neural Network For Indoor Localization
2020-11-01
1140318 byte
Conference paper
Electronic Resource
English
LSTM recurrent neural network assisted aircraft stall prediction for enhanced situational awareness
ArXiv | 2020
|Exploring LSTM based recurrent neural network for failure time series prediction
British Library Online Contents | 2018
|