TY  - RPRT
ID  - SisLab3197
UR  - https://eprints.uet.vnu.edu.vn/eprints/id/eprint/3197/
A1  - Nguyen, Huu Nhat Minh
A1  - Phan, Xuan Hieu
A1  - Tran, Quoc Long
Y1  - 2018/12//
N2  - With the growth of Artificial intelligence and Machine learning, the amount of research for autonomous vehicle is also growing nonstop. But a self-driving system is far too complex with the hardware integration, LiDAR and RADAR involvement, how exactly are these machine learning algorithms being applied, where can a machine learning researcher start to research self-driving car. This report will cover how traditional machine learning methods and state of the are deep learning (semantic segmentation, convolutional neural network - CNN) are being applied to build autonomous cars. The algorithm uses image processing techniques to label lane pixels, classical machine learning and Histogram of Oriented Gradient (HOG) to label vehicle and street sign pixels. Then the data is used to train a semantic segmentation network to extract features for a final CNN to combine with the original image and predict driving command.
PB  - VNU-UET
VL  - TR2018-FIT-05
M1  - technical_report
TI  - Deep learning based detection of vehicles, lane and street sign for behavior cloning in autonomous car
AV  - public
EP  - 8
ER  -