Embedded multiple object detection based on deep learning technique for advanced driver assistance system

Fong An Chang, Chia Chi Tsai, Ching Kan Tseng, Jiun-In  Guo

研究成果: Conference contribution同行評審

2 引文 斯高帕斯(Scopus)

摘要

This paper proposes an optimized pedestrian and vehicle detection method based on deep learning technique. We optimize the convolutional neural network architecture by three mainly methods. The first one is the choice of the learning policy. The second one is to simplify the convolutional neural network architecture. The last one is careful choice of training samples. With limited loss of accuracy, we can greatly speed up the original deep learning method coming from CAFFE. The proposed system is developed on PCs and implemented on the platforms of both the PC and embedded systems. We can achieve around 90% accuracy when it is tested on an open-source dataset. On PCs with Intel [email protected] CPU, the proposed design can reach the performance about 720×480 video at 25 frames per second. On the NVIDIA JETSON TX1 embedded system, the proposed design can reach the performance about 720×480 video at 5 frames per second.

原文English
主出版物標題2017 IEEE 60th International Midwest Symposium on Circuits and Systems, MWSCAS 2017
發行者Institute of Electrical and Electronics Engineers Inc.
頁面172-175
頁數4
ISBN(電子)9781509063895
DOIs
出版狀態Published - 27 9月 2017
事件60th IEEE International Midwest Symposium on Circuits and Systems, MWSCAS 2017 - Boston, United States
持續時間: 6 8月 20179 8月 2017

出版系列

名字Midwest Symposium on Circuits and Systems
2017-August
ISSN(列印)1548-3746

Conference

Conference60th IEEE International Midwest Symposium on Circuits and Systems, MWSCAS 2017
國家/地區United States
城市Boston
期間6/08/179/08/17

指紋

深入研究「Embedded multiple object detection based on deep learning technique for advanced driver assistance system」主題。共同形成了獨特的指紋。

引用此