Distortion Correction of AUV-acquired Side-Scan Sonar Data

Side scan sonars (SSS) are types of sonars that produce representations of the sea-bed by emitting and receiving acoustic fan-shaped pulses perpendicularly to the motion of the sensor in the water. Generally, SSS are deployed from a towed vehicle pulled from a boat at high speed to avoid oscillatory motions and thus achieve a clean and consistent sea-bed scan. Our approach targets the use of SSSs on small AUVs with limited computing power, and travelling at slow speeds, where the waterfall is directly used for real-time classfication. Due to the increased oscillatory motion, the SSS waterfall tends to have significant distortion, that will preclude the classifier from obtaining correct results. The algorithm described in this paper performs a geometric correction of the sonar scanlines by taking into account the AUV’s change in height, yaw and pitch to calculate correctly their positions on the seabed. The data is mapped into a 2D grid using the scanline intensities to form a mosaic, and the missing mosaic pixels are interpolated using a Gaussian-based kernel. The waterfall is recreated by considering a modified AUV trajectory with smooth changes in heading and a null pitch. The results show a significant improvement in the waterfall output, removing unwanted distortions and displaying the seabed structures with higher geometric consistency. In addition, the concentration of the ping data on the waterfall is constant all around, compared to the varying contribution density in the original one.