Limits...
Monocular-Vision-Based Autonomous Hovering for a Miniature Flying Ball.

Lin J, Han B, Luo Q - Sensors (Basel) (2015)

Bottom Line: The position variations between the subsequent frames and the reference image are calculated by comparing their correspondence points.The Kalman filter is used to predict the position of the miniature flying ball to handle situations, such as a lost or wrong frame.The results show that the proposed method can keep the aircraft in a stable hover.

View Article: PubMed Central - PubMed

Affiliation: School of Mechanical Engineering, Beijing Institute of Technology, 5 Zhongguancun South Street, Haidian District, Beijing 100081, China. linjunqin2010@163.com.

ABSTRACT
This paper presents a method for detecting and controlling the autonomous hovering of a miniature flying ball (MFB) based on monocular vision. A camera is employed to estimate the three-dimensional position of the vehicle relative to the ground without auxiliary sensors, such as inertial measurement units (IMUs). An image of the ground captured by the camera mounted directly under the miniature flying ball is set as a reference. The position variations between the subsequent frames and the reference image are calculated by comparing their correspondence points. The Kalman filter is used to predict the position of the miniature flying ball to handle situations, such as a lost or wrong frame. Finally, a PID controller is designed, and the performance of the entire system is tested experimentally. The results show that the proposed method can keep the aircraft in a stable hover.

No MeSH data available.


Related in: MedlinePlus

The flying test on the football field.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4507670&req=5

sensors-15-13270-f008: The flying test on the football field.

Mentions: The performance of the vision-based hovering method is demonstrated using the MFB described in the previous sections. The diameter of the platform is 42 cm, and the total mass is 625 g. The parameters of the selected camera are as follows: the focus length is ; the resolution of CCD is 640 × 480; the size of the CCD is ; all algorithm development is in C++, which utilizes the OpenCV library for feature extraction. The experiment environment is a football field shown in Figure 8. The entire system was evaluated in four parts: (1) evaluating the solution of the system; (2) evaluating the static measurement precision of the system; (3) testing the dynamic hovering precision of the MFB; and (4) testing the robustness of the system.


Monocular-Vision-Based Autonomous Hovering for a Miniature Flying Ball.

Lin J, Han B, Luo Q - Sensors (Basel) (2015)

The flying test on the football field.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4507670&req=5

sensors-15-13270-f008: The flying test on the football field.
Mentions: The performance of the vision-based hovering method is demonstrated using the MFB described in the previous sections. The diameter of the platform is 42 cm, and the total mass is 625 g. The parameters of the selected camera are as follows: the focus length is ; the resolution of CCD is 640 × 480; the size of the CCD is ; all algorithm development is in C++, which utilizes the OpenCV library for feature extraction. The experiment environment is a football field shown in Figure 8. The entire system was evaluated in four parts: (1) evaluating the solution of the system; (2) evaluating the static measurement precision of the system; (3) testing the dynamic hovering precision of the MFB; and (4) testing the robustness of the system.

Bottom Line: The position variations between the subsequent frames and the reference image are calculated by comparing their correspondence points.The Kalman filter is used to predict the position of the miniature flying ball to handle situations, such as a lost or wrong frame.The results show that the proposed method can keep the aircraft in a stable hover.

View Article: PubMed Central - PubMed

Affiliation: School of Mechanical Engineering, Beijing Institute of Technology, 5 Zhongguancun South Street, Haidian District, Beijing 100081, China. linjunqin2010@163.com.

ABSTRACT
This paper presents a method for detecting and controlling the autonomous hovering of a miniature flying ball (MFB) based on monocular vision. A camera is employed to estimate the three-dimensional position of the vehicle relative to the ground without auxiliary sensors, such as inertial measurement units (IMUs). An image of the ground captured by the camera mounted directly under the miniature flying ball is set as a reference. The position variations between the subsequent frames and the reference image are calculated by comparing their correspondence points. The Kalman filter is used to predict the position of the miniature flying ball to handle situations, such as a lost or wrong frame. Finally, a PID controller is designed, and the performance of the entire system is tested experimentally. The results show that the proposed method can keep the aircraft in a stable hover.

No MeSH data available.


Related in: MedlinePlus