In the scenario where an underwater vehicle tracks an underwater target, reliable estimation of the target position is required. While USBL measurements provide target position measurements at low but regular update rate, multibeam sonar imagery gives high precision measurements but in a limited field of view. This paper describes the development of the tracking filter that fuses USBL and processed sonar image measurements for tracking underwater targets for the purpose of obtaining reliable tracking estimates at steady rate, even in cases when either sonar or USBL measurements are not available or are faulty. The proposed algorithms significantly increase safety in scenarios where underwater vehicle has to maneuver in close vicinity to human diver who emits air bubbles that can deteriorate tracking performance. In addition to the tracking filter development, special attention is devoted to adaptation of the region of interest within the sonar image by using tracking filter covariance transformation for the purpose of improving detection and avoiding false sonar measurements. Developed algorithms are tested on real experimental data obtained in field conditions. Statistical analysis shows superior performance of the proposed filter compared to conventional tracking using pure USBL or sonar measurements.

Diving is a high-risk activity due to the hazardous environment, dependence on technical equipment for life support, complexity of underwater navigation, and limited monitoring from the surface. This article describes a new concept of using an autonomous surface vehicle (ASV) as a private satellite that tracks divers, thus significantly increasing diving safety. Since the vehicle is above the diver at all times, acoustic communication with the diver interface in the form of an underwater tablet is more efficient and robust, which enhances diver navigation and enables reliable monitoring from the surface. This article focuses on a diver-tracking control structure that uses a diver motion estimator to determine diver position, even in cases when acoustic position measurements are not available.Conducting experiments with divers presents a challenge due to uncertainties, such as those introduced by the environment, unmodeled dynamics, acoustic sensors, and divers themselves (e.g., the emission of air bubbles). A step-by-step experimental plan, which includes a virtual diver (VD), an underwater remotely operated vehicle (ROV), and a human diver, allows the identification of different uncertainties. The results show that the mean tracking error with a VD (influenced only by the environment and unmodeled dynamics) is around 0.5 m; with an ROV (including the influence of acoustic sensor), it is around 1 m; and with a human diver, it is around 1.8 m. These data are validated against ground-truth video imagery.

No abstract

This paper introduces a visual method for diver detection in the context of Human Robot Interaction (HRI). The detection is treated as a classification problem, where a discriminative model is trained by computing image features of the target (diver) and underwater scenery. This type of scenery poses great challenges due to its high variability, as it often presents high illumination changes, scarce features and image distortions. For this reason, it is desirable to represent this type of images with multiple type of complementary features. The system scalability is, however, lowered as the number of features types increase as the amount of data to represent queries and indexes also increases.To remedy this, we modified the Nearest Class Mean Forests (NCMF) method, a variant of Random Forests, to integrate as many features types as desired without concerning about scalability and performance decay. The system outperforms the common generative tracking methods which fail to encompass different type of distortions into one model and ignore background information. And in contrast to tracking methods using acoustic sensors which output a single value (distance to the diver), our approach outputs a region encompassing the diver's body; information that can be further exploited to enhance underwater HRI. Not to mention that camera setups offer higher flexibility in size and energy consumption constraints than acoustic sensors. All of the system's aforementioned capabilities are tested with real-life data obtained from field experiments.978-1-4799-8736-8/15/$31.00 ©2015 IEEE

No abstract