<abstract xmlns="http://www.w3.org/1999/xhtml"><p>This work proposes a deep neural net (DNN) that accomplishes the reliable visual recognition of a chosen object captured with a webcam and moving in a 3D space. Autoencoding and substitutional reality are used to train a shallow net until it achieves zero tracking error in a discrete ambient. This trained individual is set to work in a real world closed loop system where images coming from a webcam produce displacement information for a moving region of interest (ROI) inside the own image. This loop gives rise to an emergent tracking behavior which creates a self-maintain flow of compressed space-time data. Next, short term memory elements are set to play a key role by creating new representations in terms of a space-time matrix. The obtained representations are delivery as input to a second shallow network which acts as “recognizer”. A noise balanced learning method is used to fast train the recognizer with real-world images, giving rise to a simple and yet powerful robotic eye, with a slender neural processor that vigorously tracks and recognizes the chosen object. The system has been tested with real images in real time.</p></abstract>

This work proposes a deep neural net (DNN) that accomplishes the reliable visual recognition of a chosen object captured with a webcam and moving in a 3D space. Autoencoding and substitutional reality are used to train a shallow net until it achieves zero tracking error in a discrete ambient. This trained individual is set to work in a real world closed loop system where images coming from a webcam produce displacement information for a moving region of interest (ROI) inside the own image. This loop gives rise to an emergent tracking behavior which creates a self-maintain flow of compressed space-time data. Next, short term memory elements are set to play a key role by creating new representations in terms of a space-time matrix. The obtained representations are delivery as input to a second shallow network which acts as “recognizer”. A noise balanced learning method is used to fast train the recognizer with real-world images, giving rise to a simple and yet powerful robotic eye, with a slender neural processor that vigorously tracks and recognizes the chosen object. The system has been tested with real images in real time.

A Novel Deep Neural Network that Uses Space-Time Features for Tracking and Recognizing a Moving Object

Department of Software Innovation, Farmaenlace, Quito

Department of Energy and Mechanics, Universidad de las Fuerzas Armadas ESPE Latacunga

Journal of Artificial Intelligence and Soft Computing Research

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

This work proposes a deep neural net (DNN) that accomplishes the reliable visual recognition of a chosen object captured with a webcam and moving in a 3D...

A Novel Deep Neural Network that Uses Space-Time Features for Tracking and Recognizing a Moving Object

Publié en ligne: 23 févr. 2017

Pages: 125 - 136

DOI: https://doi.org/10.1515/jaiscr-2017-0009

Mots clés
deep architectures, deep learning, artificial vision

© 2017 Academy of Management (SWSPiZ), Lodz

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

A Novel Deep Neural Network that Uses Space-Time Features for Tracking and Recognizing a Moving Object

Publié en ligne: 23 févr. 2017

Pages: 125 - 136

DOI: https://doi.org/10.1515/jaiscr-2017-0009

Mots clésdeep architectures, deep learning, artificial vision

© 2017 Academy of Management (SWSPiZ), Lodz

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Mots clés
deep architectures, deep learning, artificial vision