The utilization of stationary underwater cameras is a modern and well-adapted approach to provide a continuous and cost-effective long-term solution to monitor underwater habitats of particular interest. A common goal of such monitoring systems is to gain better insight into the dynamics and condition of populations of various marine organisms, such as migratory or commercially relevant fish taxa. This paper describes a complete processing pipeline to automatically determine the abundance, type and estimate the size of biological taxa from stereoscopic video data captured by the stereo camera of a stationary Underwater Fish Observatory (UFO). A calibration of the recording system was carried out in situ and, afterward, validated using the synchronously recorded sonar data. The video data were recorded continuously for nearly one year in the Kiel Fjord, an inlet of the Baltic Sea in northern Germany. It shows underwater organisms in their natural behavior, as passive low-light cameras were used instead of active lighting to dampen attraction effects and allow for the least invasive recording possible. The recorded raw data are pre-filtered by an adaptive background estimation to extract sequences with activity, which are then processed by a deep detection network, i.e., Yolov5. This provides the location and type of organisms detected in each video frame of both cameras, which are used to calculate stereo correspondences following a basic matching scheme. In a subsequent step, the size and distance of the depicted organisms are approximated using the corner coordinates of the matched bounding boxes. The Yolov5 model employed in this study was trained on a novel dataset comprising 73,144 images and 92,899 bounding box annotations for 10 categories of marine animals. The model achieved a mean detection accuracy of 92.4%, a mean average precision (mAP) of 94.8% and an F1 score of 93%.

Fish stocks are among the most endangered components of marine ecosystems. To minimize threats to marine ecosystems and ensure natural and sustainable resource use, monitoring systems must be placed in oceans and seas. The Underwater Fish Observatory (UFO) and the UFOTriNet are two projects initiated by several researchers from marine biology, engineering and industry in Germany between the years 2014 and 2016 and between 2019 and 2023, respectively. The systems collect abiotic as well as camera and sonar data to count fish stocks. This work proposes a method for robust fish counting using sonar data. Activity segmentation as well as object tracking are important steps to successfully accomplish this task. Background subtraction is often used as pre-processing step for stationary fixed sonars. Our proposed method improves this step using band-pass filtering. For the segmentation step, our method utilizes a simple Gaussian distribution model with positional covariances calculated directly on the intensity image. The tracking step is implemented using a classic Kalman Filter that estimates velocity and position of each object in Cartesian coordinates. The sonar detections in the close range of the observable area are compared to the camera detections for validation. Also automatic parameter optimization is used to maximize correlation with camera detections. Additionally, the proposed method is applied to the Caltech Fish Counting Dataset and compared with a deep learning method based on YOLOv5.

The mobile autonomous underwater system (MAUS) aims to create next-generation vehicles, focusing on improved intelligence, mission operations, and application scenarios. Accordingly, two types of autonomous underwater vehicles (AUVs) have been developed to operate and collaborate in various applications. The first AUV, named “Hansel,” has hovering capabilities and is tailored to tasks, such as object inspection and detection. The second AUV, called “Gretel,” has going capabilities and is suitable for tasks, such as seafloor mapping. The two AUV types are equipped with different sensors, allowing them to perform distinct tasks simultaneously as a team. The going AUV has a robust navigation system that includes an inertial navigation system, an ultra-short baseline unit, and a Doppler velocity log for dead reckoning. In contrast, the hovering AUV only has a low-cost micro-electro-mechanical system. Gretel's navigation unit improves Hansel's navigation, along with data transfer between the vehicles. The AUVs rely on a hybrid communication system that integrates acoustic, inductive, and optical links to combine the strengths of each technology. To accomplish their individual goals, the AUVs participate in joint mission planning, utilizing a variety of sensors and tasks that are specific to each AUV. This approach is commonly referred to as multiheterogeneous AUV swarm technology. The multiheterogeneous concept developed in the MAUS project was experimentally validated in Kiel Fjord, located in the southwest Baltic Sea, and in La Spezia, Mediterranean Sea.

In this work, a low-cost low-power navigation solution for autonomous underwater vehicles is introduced utilizing a Micro-Electro-Mechanical System (MEMS) inertial sensor and an ultra short baseline (USBL) system. The complete signal processing is implemented on a cheap 16-bit fixed-point arithmetic microcontroller. For data fusion and calibration, an error state Kalman filter in square root form is used, which preserves stability in case of rounding errors. To further reduce the influence of rounding errors, a stochastic rounding scheme is applied. The USBL measurements are integrated using tightly coupled data fusion by deriving the observation functions separately for range, elevation, and azimuth angles. The effectiveness of the fixed point implementation with stochastic rounding is demonstrated on a simulation, and the the complete setup is tested in a field test. The results of the field test show an improved accuracy of the tightly coupled data fusion in comparison with loosely coupled data fusion. It is also shown that the applied rounding schemes can bring the fixed-point estimates to a near floating point accuracy.

The multi-layer vector approximate message passing algorithm is applied to the problem of channel estimation in underwater acoustic communication addressing the estimation of time-varying channel characteristics. A pre-trained artificial neural network is used as prior for the channel estimation. The communication receiver is designed as a factor graph with a low-density parity check decoder as factor node. The performance of the proposed communication scheme is evaluated by comparing the bit error rates with classical communication schemes. The bit error rate is significantly decreased on strongly time-varying channels. Different datasets are compared for training the channel estimator.