TY - GEN
T1 - Embedded multiple object detection based on deep learning technique for advanced driver assistance system
AU - Chang, Fong An
AU - Tsai, Chia Chi
AU - Tseng, Ching Kan
AU - Guo, Jiun-In
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/9/27
Y1 - 2017/9/27
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85034069531&partnerID=8YFLogxK
U2 - 10.1109/MWSCAS.2017.8052888
DO - 10.1109/MWSCAS.2017.8052888
M3 - Conference contribution
AN - SCOPUS:85034069531
T3 - Midwest Symposium on Circuits and Systems
SP - 172
EP - 175
BT - 2017 IEEE 60th International Midwest Symposium on Circuits and Systems, MWSCAS 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 60th IEEE International Midwest Symposium on Circuits and Systems, MWSCAS 2017
Y2 - 6 August 2017 through 9 August 2017
ER -