|
Analysis of Pedestrian Collision Risk using Fuzzy Inference Model |
|
Joko Hariyono, Laksono Kurnianggoro, Wahyono Wahyono, Kang-Hyun Jo(University of Ulsan, Korea) |
| The aim of this work is to improve driver awareness by proposing a collision risk analysis method. Pedestrian in the scene is observed by sequential frames from monocular camera mounted on the car. Four elements of collision criteria are constructed which are pedestrian walking direction, its velocity, car speed and relative distance of pedestrian. The analysis of collision risk is performed using fuzzy inference method. The performance evaluation shows our proposed method achieved average accuracy 87.5% and it significantly outperforms human perception with more than 25% improvement. |
|
|
Development of multicopter that equipped with semi-auto control |
|
Tatsuya Yamazaki, Wan Azizul, Tadahiro Hasegawa, Shin'ichi Yuta(Shibaura Institute of Technology, Japan) |
| We developed a multicoper that equipped with semi-auto control for infrastructure inspection. The semi-auto multicopter can be controlled by both manual and autonomous pilot. During manual flight operation, it is hard for pilots to understand accurate position between a multicopter and obstacles. Therefore, we developed a collision avoidance function to assist pilots operation, by using a semi-auto control algorithm. The experimental results showed that, a collision avoidance function accurately controlled to avoid from obstacle and keep a constant distance. |
|
|
Dense Optical Flow in Stabilized Scenes for Moving Object Detection from a Moving Camera |
|
Laksono Kurnianggoro(Intelligent Systems Lab., Korea), Ajmal Shahbaz, Kang-Hyun Jo(University of Ulsan, Korea) |
| This paper proposes a method for detecting moving objects appeared in video captured by a moving camera. The proposed method relies on dense optical flow to differentiate moving objects from static background. A stabilization method is incorporated by the mean of global motion extraction, which can be done by analyzing the homography transformation between two consequtive frames. Finally, by applying a threshold on the dense optical flow, the region of moving object is acquired. The proposed method has been evaluated in the experiments and produce satisfying results with 98% accuracy. |
|
|
Fundamental numerical and experimental evaluation of attitude recovery control for a quad tilt rotor UAV against disturbance |
|
Satoko Abiko, Kengo Tashiro(Shibaura Institute of Technology, Japan) |
| This paper presents attitude recovery control for a quad tilt rotor UAV. The quad tilt rotor UAV has ability of flying with completely independent position and attitude control by changing the thrust directions. This type of UAV is expected to perform better response to the disturbance compared to the conventional multi-rotor UAV. This paper proposes disturbance detection method using IMU sensor and develops attitude recovery control against impact disturbance. The numerical simulation and flight experiments were carried out to evaluate the effectiveness of the proposed method. |
|
|
Flight Planning for Photovoltaic-Plant Inspection by Unmanned Aerial Vehicle |
|
Geon-Hee Lee, Seong-Hwan Kim, Hye-Jin Oh, Ji-Won Lee, Kee-Ho Yu(Chonbuk National University, Korea) |
| Photovoltaic-plant is developed rapidly and widely installed for harvesting clean and renewable energy.
Maintenance of photovoltaic is essential to guarantee the performance of photovoltaic, because failures in photovoltaic modules affect electric efficiency significantly. In this paper, we propose defects inspection system of photovoltaic module using drone and thermal camera. The appropriate measurement conditions are considered to obtain the reliable
image of photovoltaic modules. Experimental results of measurement are given and the reliability of measurement was discussed. |
| |