Browsing by Author "Chang, Fong-An"

Now showing 1 - 2 of 2

A Smart Surveillance System with Multiple People Detection, Tracking, and Behavior Analysis
(2016)
Yang, Chia-Jui
;
Chou, Ting
;
Chang, Fong-An
;
Chang Ssu-Yuan
;
Guo, Jiun-In
This paper proposes an intelligence surveillance system in indoor environments, which support the functions of people detection, people tracking, and behavior analysis. Strong variation of lightness by switching lights and frequent crossing of people are two major design challenges of the proposed system, which will decrease the detection accuracy. Therefore, we propose a mechanism of updating background to react to the variation of lightness. Moreover, the ORB descriptor is added to be a unique feature of identifying people. It can make people tracking more precise during crossing. The proposed system is developed on PCs and implemented on embedded systems. On PCs with Intel i7@3.4GHz CPU running with a single core, we can reach the performance about D1 video at 22 fps. On an embedded system with ARM CortexA9@ 1.0GHz, we can achieve the performance about D1 video at 8 fps.
Embedded Multiple Object Detection Based on Deep Learning Technique for Advanced Driver Assistance System
(2017-01-01)
Chang, Fong-An
;
Tsai, Chia-Chi
;
Tseng, Ching-Kan
;
Guo, Jiun-In
;
電子工程學系及電子研究所
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 i7@3.5GHz CPU, the proposed design can reach the performance about 720x480 video at 25 frames per second. On the NVIDIA JETSON TX1 embedded system, the proposed design can reach the performance about 720x480 video at 5 frames per second.