TY - JOUR
T1 - Evaluation Method of Deep Learning-Based Embedded Systems for Traffic Sign Detection
AU - Lopez-Montiel, Miguel
AU - Orozco-Rosas, Ulises
AU - Sanchez-Adame, Moises
AU - Picos, Kenia
AU - Ross, Oscar Humberto Montiel
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2021
Y1 - 2021
N2 - Traffic Sign Detection (TSD) is a complex and fundamental task for developing autonomous vehicles; it is one of the most critical visual perception problems since failing in this task may cause accidents. This task is fundamental in decision-making and involves different internal conditions such as the internal processing system or external conditions such as weather, illumination, and complex backgrounds. At present, several works are focused on the development of algorithms based on deep learning; however, there is no information on a methodology based on descriptive statistical analysis with results from a solid experimental framework, which helps to make decisions to choose the appropriate algorithms and hardware. This work intends to cover that gap. We have implemented some combinations of deep learning models (MobileNet v1 and ResNet50 v1) in a combination of the Single Shot Multibox Detector (SSD) algorithm and the Feature Pyramid Network (FPN) component for TSD in a standardized dataset (LISA), and we have tested it on different hardware architectures (CPU, GPU, TPU, and Embedded System). We propose a methodology and the evaluation method to measure two types of performance. The results show that the use of TPU allows achieving a processing training time 16.3 times faster than GPU and better results in terms of precision detection for one combination.
AB - Traffic Sign Detection (TSD) is a complex and fundamental task for developing autonomous vehicles; it is one of the most critical visual perception problems since failing in this task may cause accidents. This task is fundamental in decision-making and involves different internal conditions such as the internal processing system or external conditions such as weather, illumination, and complex backgrounds. At present, several works are focused on the development of algorithms based on deep learning; however, there is no information on a methodology based on descriptive statistical analysis with results from a solid experimental framework, which helps to make decisions to choose the appropriate algorithms and hardware. This work intends to cover that gap. We have implemented some combinations of deep learning models (MobileNet v1 and ResNet50 v1) in a combination of the Single Shot Multibox Detector (SSD) algorithm and the Feature Pyramid Network (FPN) component for TSD in a standardized dataset (LISA), and we have tested it on different hardware architectures (CPU, GPU, TPU, and Embedded System). We propose a methodology and the evaluation method to measure two types of performance. The results show that the use of TPU allows achieving a processing training time 16.3 times faster than GPU and better results in terms of precision detection for one combination.
KW - Traffic sign detection
KW - autonomous vehicles
KW - computer vision
KW - deep learning
KW - digital systems
KW - embedded systems
KW - hardware acceleration
UR - http://www.scopus.com/inward/record.url?scp=85111005316&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2021.3097969
DO - 10.1109/ACCESS.2021.3097969
M3 - Artículo
AN - SCOPUS:85111005316
SN - 2169-3536
VL - 9
SP - 101217
EP - 101238
JO - IEEE Access
JF - IEEE Access
M1 - 9490209
ER -