:: ICCAS 2015 ::

TB05		[OS] Image based Ambient Intelligence
Time : 13:00~14:30 Room : 105		Chair : Kanghyun Jo (University of Ulsan, )



13:00~13:15	TB05-1

The Car Washing Control Method using 3D Contour Segmentation
Yang Yu(Intelligent Systems Lab, Korea, Republic of ), Laksono Kurnianggoro(Intelligent Systems Lab., Korea, Republic of ), Kanghyun Jo(University of Ulsan, Korea, Republic of )

This paper presents a car washing control method to extract the contour of car in 3D point cloud using techniques in computational geometry. The point set contour extraction method is better than directly dealing with pixels as in traditional contour extraction methods. Depth and height filter is used to remove the background and ground. Two candidate contour points are found by smallest clockwise turn angle from last contour point to this point in two circles. The next contour point is decided by the two turn angles difference.



13:15~13:30	TB05-2

Framework of Real-time Car Detection using Calibrated Camera and LRF
Laksono Kurnianggoro, Kang-Hyun Jo(Intelligent Systems Lab., Korea, Republic of )

This paper proposes a framework for a real-time car detection method using calibrated system of camera and Laser Range Finder (LRF). Car candidates are extracted from the LRF data using a gridding method. A region of interest (ROI) in camera image is generated for each object located in 2D grid using the property of the calibrated camera and LRF system. From each ROI, Histogram of oriented gradient features are extracted and then its dimension is reduced using genetic algorithm approach. Experiments result shows that the proposed framework achieves around 68 fps of processing speed.



13:30~13:45	TB05-3

Localization of Pedestrian Area from Hybrid Camera System
Joko Hariyono, Kanghyun Jo(University of Ulsan, Korea, Republic of )

Accurate pedestrian path prediction and motion estimation are important tasks in the intelligent vehicle domain. The model incorporates the pedestrian pose recognition and lateral speed, motion direction and spatial layout of the environment. Hybrid camera system is performed. A perspective camera is used for pedestrian localization with respect to car speed. And then an omnidirectional camera is used to enlarge field of view of monocular camera. Pedestrians are tracked in 360 degree around the vehicle.



13:45~14:00	TB05-4

Smartphone-based sensory augmentation technology for home-based balance training
Beom-Chan Lee, Alberto Fung(University of Houston, United States)

This paper describes the design and development of a smartphone-based sensory augmentation technology through vibrotactile biofeedback to support home-based balance training for individuals with balance disorders. The smartphone’s application software communicates with the wearable module wirelessly via Bluetooth, provides instructions for a recommended balance training exercises in clinical and/or home-based balance rehabilitation settings, and displays knowledge of results after the completion of the exercise.



14:00~14:15	TB05-5

Pilot Cognitive State Recognition using Wavelet Singular Entropy and Gaussian Process Classification via Full Flight Simulation
Zhengxiang Cai, Qi Wu, Shan Fu, Dan Huang, Biting Yu(Shanghai Jiao Tong University, China)

Cognitive state of human is vital to the man-machine system. This research proposes a method of wavelet singular entropy and Gaussian process classification to recognize the human cognitive state via physiological data during flight simulation. Experiments are implemented in a 6-degree-of-freedom full flight simulator under an emergency flight scenario. Classification results validate the effectiveness of the proposed method. Further analysis suggests a three-channel physiological signal selection to be optimal for classification as a tradeoff of the accuracy and computational cost.



14:15~14:30	TB05-6

A Novel Flag-Language Remote Control Design for a Laparoscopic Camera Holder Using Image Processing
Kateryna Zinchenko, Kai-Tai Song(National Chiao Tung University, Taiwan), Wayne Shi-Wei Huang(Show Chuan Memorial Hospital, Taiwan), Kai-Che Liu(Asian Institute of TeleSurgery, IRCAD, Taiwan)

For robot-assisted solo minimally invasive surgeries, it is crucial to have appropriate methods for robot control. This work presents a design of flag language as a novel human-to-robotThis work presents a design of flag language as a novel human-to-robot communication method based on image processing of the endoscope video during real-time intervention. The proposed system comprises autonomous positioning of endoscope holder combined with recognition of surgeon intention by analyzing surgical instrument postures.