Vision-Based Obstacle Avoidance for Small Drone using Monocular Camera

Nhair, Retaj Raheem; Al-Assadi, Tawfiq A.

doi:10.1088/1757-899x/928/3/032048

Cited by 6 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, the optical flow method has poor ability in detecting the appearance of the frontal obstacle [10,11]. [12] uses edge detection to detect the free zones in flying environment. However, this method will be less reliable if the environment is fully textured.…”

Section: Related Workmentioning

confidence: 99%

Sudden Obstacle Appearance Detection by Analyzing Flow Field Vector for Small-Sized UAV

Ramli

Shamsudin²,

Yaakub³

2021

PAAT

View full text Add to dashboard Cite

Achieving a reliable obstacle detection and avoidance system that can provide an effective safe avoidance path for small unmanned aerial vehicle (UAV) is very challenging due to its physical size and weight constraints. Prior works tend to employ the vision based-sensor as the main detection sensor but resulting to high dependency on texture appearance while not having a distance sensing capabilities. The previous system only focused on the detection of the static frontal obstacle without observing the environment which may have moving obstacles. On the other hand, most of the wide spectrum range sensors are heavy and expensive hence not suitable for small UAV. In this work, integration of different based sensors was proposed for a small UAV in detecting unpredictable obstacle appearance situation. The detection of the obstacle is accomplished by analysing the flow field vectors in the image frames sequence. The proposed system was evaluated by conducting the experiments in a real environment which consisted of different configuration of the obstacles. The results from the experiment show that the success rate for detecting unpredictable obstacle appearance is high which is 70% and above. Even though some of the introduced obstacles are considered to have poor texture appearances on their surface, the proposed obstacle detection system was still able to detect the correct appearance movement of the obstacles by detecting the edges.

show abstract

Section: Related Workmentioning

confidence: 99%