R&D for Autonomous Driving with Realtime Embedded Deep Learning
‘Real-time Embedded Deep Learning for Autonomous Lane Change System of Autonomous Driving’ project sponsored and selected by ‘LSautomotive’ (http://www.e2festa.kr/exhibition02.asp)
Devised a hardware system(NVIDIA Jetson TX2 + Raspberry Pi 3 Model B + Bluetooth Speaker) with developing softwares which can notify driver about possibilities of changing(transferring) lane from current driving state, only with side-mirror Camera’s real-time streaming video so that can replace the future cars' side-mirror by installing small camera on each side.
Applied Embedded Deep Learning (based on Fully-Convolutional Network Alexnet-Cityscapes-HD model) for car and traffic Image Classification, training from NVIDIA DIGITS and Caffe2. Real-time image snapshots validation process was held on NVIDIA Jetson TX2, which has an ability of performing embedded GPU CUDA-processing power on Neural Networks with low power(voltage) source(12v usage as like standard cars).
Implemented C++ CUDA programming and Python OpenCV image processing for ROI segmentation, with sub-processing sound notification process
VIP briefing in Engineering Education Festa 2017 and Press @ http://www.honam.co.kr/read.php3?aid=1510239600539545228
http://www.e2festa.kr/exhibition02.asp
http://www.e2festa.kr/exhibition02.asp http://www.e2festa.kr/exhibition02.asp http://www.e2festa.kr/exhibition02.asp http://www.e2festa.kr/exhibition02.asp http://www.e2festa.kr/exhibition02.asp http://www.e2festa.kr/exhibition02.asp http://www.e2festa.kr/exhibition02.asp http://www.e2festa.kr/exhibition02.asp http://www.e2festa.kr/exhibition02.asp http://www.e2festa.kr/exhibition02.asp http://www.e2festa.kr/exhibition02.asp http://www.e2festa.kr/exhibition02.asp http://www.e2festa.kr/exhibition02.asp http://www.e2festa.kr/exhibition02.asp http://www.e2festa.kr/exhibition02.asp
.jpg?raw=true){kind=link}
.png?raw=true){kind=link}
.png?raw=true){kind=link}
.png?raw=true){kind=link}
.png?raw=true){kind=link}
.png?raw=true){kind=link}
.png?raw=true){kind=link}
.png?raw=true){kind=link}
.png?raw=true){kind=link}
.png?raw=true){kind=link}
.png?raw=true){kind=link}
.png?raw=true){kind=link}
.png?raw=true){kind=link}
.jpg?raw=true){kind=link}
.jpg?raw=true){kind=link}
R&D via NVIDIA Jetson TX2, Raspberry Pi 3 with CUDA programming, Caffe2, NVIDIA DIGITS, Python OpenCV
Safety system for transferring a lane
http://www.e2festa.kr/exhibition02.asp http://www.e2festa.kr/exhibition02.asp http://www.e2festa.kr/exhibition02.asp http://www.e2festa.kr/exhibition02.asp http://www.e2festa.kr/exhibition02.asp http://www.e2festa.kr/exhibition02.asp
