Aerospace and Electronic Systems - March 2019 - 28

Robust Cooperative Target Detection for a Vision-Based UAVs Autonomous Aerial Refueling Platform via the Contrast . . .

Figure 12.

Figure 13.

Projection error in the low light condition.

Projection error in the strong light condition.

extracted those cooperative targets with different perspectives and different distances. And the surrounding environmental factors have no influence on the subsequent
operations of vision measurement. In addition, it has great
benefits for the determination of image coordinates of
each marker and can significantly improve the accuracy
and stability of calculating image coordinates. Likewise,
from the results in Figure 9 of the low lighting condition,
we can see that these cooperative targets under different
status have been extracted from those outdoor experiment
images.
The above-mentioned tests demonstrate that the proposed visual detection method based on the CSF of eagle's
eye has following features: 1) in different lighting conditions,
perspectives and distances, the cooperative target can be successfully detected. Thus, this method has a strong adaptability and robustness. 2) It can accurately detect the cooperative
target, eliminating environment factors influence on the
extraction of red marker for our platform. Thereby, it has
strong practicability. It is obvious that our method could
effectively detect and identify the cooperative target in the
presence of the disturbance.
To further verify the reliability and accuracy of the
whole AAR platform, two groups of the different sequence
of 70 frames taken from the low and strong lighting conditions during flight are used. The estimated relative distances
are shown in Figures 10 and 11, and the corresponding
reprojection errors are shown in Figures 12 and 13,
respetctively.
The result shows that the estimation effect in the low
light condition is superior to that in the strong light condition. In low light condition, the reprojection error is less
than 12 pixels, whereas in strong light condition, the value
is 25 pixels. It denotes that illumination changes could
affect the estimation performance and the strong light condition has a worse influence on the pose estimation. It
should be noted that the errors mainly derive from the
28

pose estimation algorithms rather than our proposed target
detection method.

CONCLUSION
In this paper, a robust cooperative target detection method
inspired by contrast sensitivity mechanism of eagle's eye
is proposed to extract the cooperative target, aiming at
reducing the computation load and improving the accuracy of feature extraction. The contrast sensitivity mechanism is simulated based on the attenuation effect of CSF
of an eagle to suppress the texture edges. The comparison
experimental results compared with the Canny edge detection operator demonstrated the excellent performance of
our proposed method in extracting salient contours and
suppressing texture edges. Besides, a binocular visionbased AAR platform for UAV is designed and implemented in this paper. Applying our proposed detection
method to a series of outdoor experiment images captured
from two challenging lighting conditions, the cooperative
targets are successfully extracted while the other disturbance areas are removed dramatically. The outdoor flight
tests are conducted to verify the visual measurement system and the hardware platform. The experimental results
verified the feasibility and effectiveness of our developed
visual measurement algorithms.
In the future, we will focus on the influence of other
factors on the marker detection to further improve the
accuracy of marker detection, like illumination, the image
quality influenced by the motion of tanker UAV.

ACKNOWLEDGMENTS
This work was supported in part by the National Natural
Science Foundation of China under Grant 61425008 and
Grant 91648205, and in part by Aeronautical Science
Foundation of China under Grant 2015ZA51013.

IEEE A&E SYSTEMS MAGAZINE

MARCH 2019

Aerospace and Electronic Systems - March 2019

Table of Contents for the Digital Edition of Aerospace and Electronic Systems - March 2019