The convolutional neural network (CNN) has achieved extraordinary performance in image classification. However, the implementation of such architecture on embedded platforms is a big challenge task due to the computing resource constraint issue. This paper concentrates on optimization of CNN on embedded platforms with a case study of pedestrian detection in ADAS. The main contribution of this proposed CNN is its ability to run pedestrian classification task in real time with high accuracy based on a platform with ARM embedded. The CNN model has been trained with GPU locally and then transformed into an efficient implementation on embedded platforms. The efficient implementation uses dramatically small network scale and a lightweight CNN is obtained. Specifically, parameters of the network are compressed by adopting integer weights to reduce computational complexity. Meanwhile, other optimizations have also been proposed to adapt the general ARM processor architecture. Finally, a robust and efficient CNN architecture is executed to run pedestrian detection algorithm in real time. The embedded platform employs a 1GHz Cortex-A53 ARMv8 based CPU. The network performs nearly 200 regions of interest detection per second with 97% accuracy by using a single core of Cortex-A53 in real traffic scene.
Real-time Pedestrian Detection using Convolutional Neural Network on Embedded Platform
Sae International Journal of Passenger Cars- Electronic and Electrical Systems
Sae Int. J. Passeng. Cars – Electron. Electr. Syst
SAE-TONGJI 2016 Driving Technology of Intelligent Vehicle Symposium ; 2016
2016-09-14
6 pages
Aufsatz (Konferenz)
Englisch
Real-time Pedestrian Detection using Convolutional Neural Network on Embedded Platform
British Library Conference Proceedings | 2016
|Real-time Pedestrian Detection Using LIDAR and Convolutional Neural Networks
British Library Conference Proceedings | 2006
|Pedestrian Detection with Deep Convolutional Neural Network
British Library Conference Proceedings | 2015
|Pedestrian Detection with Convolutional Neural Networks
British Library Conference Proceedings | 2005
|