Benchmarking deep classifiers on mobile devices for vision-based transportation recognition

Richoz, Sebastien (University of Sussex, Brighton, United Kingdom) ; Perez-Uribe, Andres (School of Management and Engineering Vaud, HES-SO // University of Applied Sciences Western Switzerland) ; Birch, Philip (University of Sussex, Brighton, United Kingdom) ; Roggen, Daniel (University of Sussex, Brighton, United Kingdom)

Vision-based human activity recognition can provide rich contextual information but has traditionally been computationally prohibitive. We present a characterisation of five convolutional neural networks (DenseNet169, MobileNet, ResNet50, VGG16, VGG19) implemented with TensorFlow Lite running on three state of the art Android mobile phones. The networks have been trained to recognise 8 modes of transportation from camera images using the SHL Locomotion and Transportation dataset. We analyse the effect of thread count and back-ends services (CPU, GPU, Android Neural Network API) to classify the images provided by the rear camera of the phones. We report processing time and classification accuracy.


Conference Type:
full paper
Faculty:
Ingénierie et Architecture
School:
HEIG-VD
Institute:
IICT - Institut des Technologies de l'Information et de la Communication
Publisher:
London, United Kingdom, 9-13 September 2019
Date:
2019-09
London, United Kingdom
9-13 September 2019
Pagination:
5 p.
Published in:
UbiComp/ISWC '19 Adjunct: Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2019 ACM International Symposium on Wearable Computers, 9-13 September 2019, London, United Kingdom
Numeration (vol. no.):
pp. 803-807
DOI:
ISBN:
9781450368698
Appears in Collection:



 Record created 2020-05-19, last modified 2020-05-22

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)