Various underwater studies using underwater sonar sensors are actively in progress. However, unlike the ground, the underwater has a lot of noise. So it is difficult to accurately recognize the underwater environment. The final purpose of this study is to improve the efficiency of the underwater environment recognition using the underwater sonar sensor by developing a filtering algorithm that removes noise and expresses the object from the underwater sonar image captured by the underwater sonar sensor. To develop a filtering algorithm, convolutional calculations were used with three types of filters. This paper is about the case study that conducted to set the parameters of ‘Gabor Filter’ suitable for underwater sonar image during the design process of filtering algorithm. As a result, it was possible to find the most suitable ‘Gabor Filter’ parameters for underwater sonar images. And it showed high accuracy with a binary map of obstacles created by hand using the naked eye. Through this study, it can be utilized not only as a binary map of real-time obstacles, but also as an algorithm for generating object masks in underwater sonar images for deep learning.

수심이 깊은 바다 속을 광학 카메라로 촬영하는 경우 영상 왜곡이 일어날 수 있다. 이런 문제는 해수와 각종 부유물로 인 해 태양광이 충분히 전달되지 않아 발생하게 된다. 특히, 수심에 따라 녹색과 청색 계열의 색상이 지나치게 강조되는 색상의 왜곡과 해수에 의한 빛의 굴절과 부유물로 인한 경계선 부분에서의 왜곡현상이 발생한다. 이와 같은 왜곡들로 인하여 수중영상의 전반적인 화질이 저하된다. 본 논문에서는 정박 중인 선박의 하부를 촬영한 수중영상을 대상으로 영상분석을 수행한다. 그 결과를 기반으로 색 상을 보정하고, 윤곽선을 강조하는 기법을 제안한다. 실험결과 제안한 기법을 적용할 경우 원본 수중영상의 유효 윤곽선 보다 3.39 % 정도 윤곽선의 수가 증가하는 결과를 얻을 수 있었다. 또한, 정량적인 평가와 함께 주관적인 화질평가를 병행한 결과 색상 보정과 함 께 객체의 경계부분이 명확해지는 것을 확인할 수 있었다. 본 논문에서 제안한 수중영상의 색상 보정과 윤곽선 강조 기법은 향후 수 중영상 촬영이 필요한 여러 분야에 응용될 수 있을 것으로 사료된다.

In the ground environment, mobile robot research uses sensors such as GPS and optical cameras to localize surrounding landmarks and to estimate the position of the robot. However, an underwater environment restricts the use of sensors such as optical cameras and GPS. Also, unlike the ground environment, it is difficult to make a continuous observation of landmarks for location estimation. So, in underwater research, artificial markers are installed to generate a strong and lasting landmark. When artificial markers are acquired with an underwater sonar sensor, different types of noise are caused in the underwater sonar image. This noise is one of the factors that reduces object detection performance. This paper aims to improve object detection performance through distortion and rotation augmentation of training data. Object detection is detected using a Faster R-CNN.

In this paper we present (1) analysis of imaging sonar measurement for two-view relative pose estimation of an autonomous vehicle and (2) bundle adjustment and 3D reconstruction method using imaging sonar. Sonar has been a popular sensor for underwater application due to its robustness to water turbidity and visibility in water medium. While vision based motion estimation has been applied to many ground vehicles for motion estimation and 3D reconstruction, imaging sonar addresses challenges in relative sensor frame motion. We focus on the fact that the sonar measurement inherently poses ambiguity in its measurement. This paper illustrates the source of the ambiguity in sonar measurements and summarizes assumptions for sonar based robot navigation. For validation, we synthetically generated underwater seafloor with varying complexity to analyze the error in the motion estimation.

This paper proposes an underwater localization algorithm using probabilistic object recognition. It is organized as follows; 1) recognizing artificial objects using imaging sonar, and 2) localizing the recognized objects and the vehicle using EKF(Extended Kalman Filter) based SLAM. For this purpose, we develop artificial landmarks to be recognized even under the unstable sonar images induced by noise. Moreover, a probabilistic recognition framework is proposed. In this way, the distance and bearing of the recognized artificial landmarks are acquired to perform the localization of the underwater vehicle. Using the recognized objects, EKF-based SLAM is carried out and results in a path of the underwater vehicle and the location of landmarks. The proposed localization algorithm is verified by experiments in a basin.