A detection method based on sonar image for underwater pipeline tracker

The surveillance and inspection of underwater pipelines are carried out by operators who drive a remotely operated underwater vehicle (ROV) with camera mounted on it. However in very turbid water, the camera can not capture any scene, even with auxiliary high-intensity light. In this case the optical detection devices are unable to complete the surveillance task. In recent years, forward looking sonar is widely applied to the underwater inspection, which is not subject to the influence of light and turbidity. So it is suitable for the inspection of pipelines. But the dynamic change of ROV by the water flow will lead to the target to escape from the sonar image easily. In addition, the sonar image is with high noise and low contrast. It is difficult for the operator to identify the pipeline from the images. Moreover, the surveillance of underwater pipelines is tedious and time consuming and it is easy to make mistakes due to the fatigue and distraction of the operator. Therefore, the study focuses on developing image processing algorithms to detect the pipeline automatically. By using the proposed image processing method, firstly the images are enhanced using the Gabor filter. And then these images are applied for an edge detector. Finally the parameters of the pipeline are calculated by Hough transform. To reduce the search area, the Kalman filter is explored to predict the parameters of the pipeline on the next image. And the experiment is shown the vision system is available to the surveillance of underwater pipelines.