Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Robert Westendorp"'
Publikováno v:
IEEE Access, Vol 8, Pp 59750-59759 (2020)
Convolutional neural network (CNN) is a powerful tool for many data applications. However, its high dimension nature, large network size and computational complexity, and the need of large amount of training data make it challenging to be used in edg
Externí odkaz:
https://doaj.org/article/c6fe520da7334391a4ae22298f700fe3
Publikováno v:
IEEE Sensors Journal. 20:6160-6169
This paper proposes a semi-sequential probabilistic model (SSP) that applies an additional short term memory to enhance the performance of the probabilistic indoor localization. The conventional probabilistic methods normally treat the locations in t
Publikováno v:
IEEE Internet of Things Journal. 6:10639-10651
This paper proposes recurrent neuron networks (RNNs) for a fingerprinting indoor localization using WiFi. Instead of locating user's position one at a time as in the cases of conventional algorithms, our RNN solution aims at trajectory positioning an
Autor:
Tyler Reese, Minh Tu Hoang, Yizhou Zhu, Tao Lu, Brosnan Yuen, Robert Westendorp, Xiaodai Dong, Michael Xie
Publikováno v:
IEEE Sensors Journal. 18:10208-10216
This paper proposes a soft range limited K nearest neighbours (SRL-KNN) localization fingerprinting algorithm. The conventional KNN determines the neighbours of a user by calculating and ranking the fingerprint distance measured at the unknown user l
Publikováno v:
VTC-Fall
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 im
Publikováno v:
VTC-Fall
Image based localization is a key block of visual simultaneous localization and mapping (SLAM) system where image data is used to localize the camera relative to an arbitrary reference frame. Although finding the location from one image or between tw
Publikováno v:
VTC-Fall
Neural networks-based camera pose estimation systems rely on fine tuning very large networks to regress the camera position and orientation with very complex training procedure. In this paper, we explore the following question: do we need to fine tun
Publikováno v:
PACRIM
Adding an image descriptor to the input significantly enhances the performance of a convolutional neural network. By incorporating Speeded Up Robust Feature (SURF) descriptors for indoor localization applications, we report a simpler convolutional ne