TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Neural Network-based Vehicle Image Classification for IoT Devices

Tutkimustuotosvertaisarvioitu

Yksityiskohdat

AlkuperäiskieliEnglanti
OtsikkoThe IEEE International Workshop on Signal Processing Systems
KustantajaIEEE
Sivut148-153
Sivumäärä6
ISBN (elektroninen)978-1-7281-1927-4
DOI - pysyväislinkit
TilaJulkaistu - 2019
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaIEEE International Workshop on Signal Processing Systems -
Kesto: 1 tammikuuta 1900 → …

Julkaisusarja

NimiIEEE International Workshop on Signal Processing Systems
ISSN (elektroninen)2374-7390

Conference

ConferenceIEEE International Workshop on Signal Processing Systems
Ajanjakso1/01/00 → …

Tiivistelmä

Convolutional Neural Networks (CNNs) have previously provided unforeseen results in automatic image analysis and interpretation, an area which has numerous applications in both consumer electronics and industry. However, the signal processing related to CNNs is computationally very demanding, which has prohibited their use in the smallest embedded computing platforms, to which many Internet of Things (IoT) devices belong. Fortunately, in the recent years researchers have developed many approaches for optimizing the performance and for shrinking the memory footprint of CNNs. This paper presents a neural-network-based image classifier that has been trained to classify vehicle images into four different classes. The neural network is optimized by a technique called binarization, and the resulting binarized network is placed to an IoT-class processor core for execution. Binarization reduces the memory footprint of the CNN by around 95% and increases performance by more than 6×. Furthermore, we show that by utilizing a custom instruction ’popcount’ of the processor, the performance of the binarized vehicle classifier can still be increased by more than 2×, making the CNN-based image classifier suitable for the smallest embedded processors.