Your browser does not support JavaScript!
資訊系統與應用研究所
[Apr-26] Applied Deep Learning for Autonomous Video Security - A Startup Perspective

Seminar of Institute of Information Systems and Applications

Speaker :

Dr. Ping-Lin Chang

Umbo CV

Topic :

Applied Deep Learning for Autonomous Video Security - A Startup Perspective

Date :

15:30-17:00 Wednesday 26-Apr-2017

Place :

台達館R107Delta Building R107

Host

Prof. Min Sun & Prof. Hao-Chuan Wang

 

Abstract

Deep learning has been shown to achieve astounding results in several computer vision tasks including object detection, semantic segmentation, person recognition and super-resolution. While deep learning for computer vision is still an active research realm and there are many exciting directions to be explored, this talk will mainly focus on sharing the industrial point of view, i.e., how state-of-the-art deep learning techniques can be employed to solve real-world problems and make products with large-scale cloud platforms. Specifically, an autonomous video security system, which is of particular interest of Umbo CV, requires various computer vision algorithms to reach real-time and high-accuracy performance. In this talk, we will have a glance over the devised cloud system and address a number of practical concerns when applying deep learning with a tremendous amount of video data.

Bio

Ping-Lin Chang received a BSc degree from the Department of Engineering Science at the National Cheng Kung University in Taiwan in 2007, and graduated with an Award of Distinction MSc degree in Artificial Intelligence at Electronics and Computer Science at the University of Southampton in the United Kingdom in 2010. He was awarded a robotic vision PhD degree under the supervision of Dr. Eddie Edward and Prof. Andrew Davison at the Department of Computing at Imperial College London in 2015. He worked at the Surgical Robot Vision Group at the Centre for Medical Image Computing (CMIC) and Department of Computer Science at University College London (UCL) under the supervision of Dr. Danail Stoyanov. He is passionate about applying computer vision and machine learning algorithms for solving real-world problems. He is now a co-founder and CTO at Umbo CV, dedicated to the development of autonomous security systems.

All faculties and students are welcome to join.

瀏覽數