Micro-aerial vehicles(MAVs)find it extremely difficult to navigate in GNSS-denied indoor staircase environments with obstructed Global navigation satellite system(GNSS)signals.To avoid hitting both static and moving o...Micro-aerial vehicles(MAVs)find it extremely difficult to navigate in GNSS-denied indoor staircase environments with obstructed Global navigation satellite system(GNSS)signals.To avoid hitting both static and moving obstacles,MAV must estimate its position and heading in the staircase indoor scenes.In order to detect vanishing points and estimate heading for MAV navigation in a staircase environment,five different input colour space image frames—namely RGB image into a grayscale image and RGB image into hyper-opponent colour space—O1,O2,O3,and Sobel R channel image frames—have been used in this work.To determine the position and direction of the MAV,the Hough transform technique and K-means clustering algorithm have been incorporated for line and vanishing point recognition in the staircase image frames.The position of the vanishing point detected in the staircase image frames indicates the position of the MAV(Centre,left or right)in the staircase.In addition,to compute the heading of MAV,the Euclidean distance between the staircase picture centre,mid-pixel coordinates at the image’s last row,and the detected vanishing point pixel coordinates in the succeeding staircase image frames are used.The position and heading measurement can be utilised to send the MAV a suitable control signal and align it at the centre of the staircase when it deviates from the centre.The integrated Hough transform technique and K-means clustering-based vanishing point detection are suitable for real-time MAV heading measurement using the O2 channel staircase image frames for indoor MAVs with a high accuracy of±0.15°when compared to the state-of-the-art grid-based vanishing point detection method heading accuracy of±1.5°.展开更多
文摘Micro-aerial vehicles(MAVs)find it extremely difficult to navigate in GNSS-denied indoor staircase environments with obstructed Global navigation satellite system(GNSS)signals.To avoid hitting both static and moving obstacles,MAV must estimate its position and heading in the staircase indoor scenes.In order to detect vanishing points and estimate heading for MAV navigation in a staircase environment,five different input colour space image frames—namely RGB image into a grayscale image and RGB image into hyper-opponent colour space—O1,O2,O3,and Sobel R channel image frames—have been used in this work.To determine the position and direction of the MAV,the Hough transform technique and K-means clustering algorithm have been incorporated for line and vanishing point recognition in the staircase image frames.The position of the vanishing point detected in the staircase image frames indicates the position of the MAV(Centre,left or right)in the staircase.In addition,to compute the heading of MAV,the Euclidean distance between the staircase picture centre,mid-pixel coordinates at the image’s last row,and the detected vanishing point pixel coordinates in the succeeding staircase image frames are used.The position and heading measurement can be utilised to send the MAV a suitable control signal and align it at the centre of the staircase when it deviates from the centre.The integrated Hough transform technique and K-means clustering-based vanishing point detection are suitable for real-time MAV heading measurement using the O2 channel staircase image frames for indoor MAVs with a high accuracy of±0.15°when compared to the state-of-the-art grid-based vanishing point detection method heading accuracy of±1.5°.
