We consider the challenge of tracking and estimating the size of a single submerged target in a high reverberant underwater environment using a single active acoustic transceiver. This problem is common for a multitude of applications, ranging from the security and safety needs of tracking submerged vehicles and scuba divers, to environmental research and management implications such as the monitoring of pelagic fauna. Considering that the target can be either slow (e.g., a scuba diver) or fastmoving (e.g., a shark), we avoid continuous signalling, and rely on the emission of wideband pulses whose reflection pattern are evaluated and reshaped in a time-distance matrix. As opposed to common approaches that track targets through template matching or by using tracking filters, we avoid making difficult assumptions about the target's reflection patterns or motion type, and instead perform probabilistic tracking using a constraint Viterbi algorithm, whereby detection is determined based on maximum likelihood criterion. In this process, we use the expectation-maximization (EM) approach to manage stationary reflections through distribution analysis, which otherwise may be misidentified as targets. Based on the tracked path, we then evaluate the target's size. To test our approach, we performed extensive simulations as well as eight sea experiments in different environmental settings to track both a scuba diver and a sandbar shark (Carcharhinus plumbeus). The simulation results show a tracking performance that is close to the Cramér-Rao lower bound, and the experiment results show a good trade-off between detection rate and false alarm rate for a low signal-to-clutter ratio of 5 [dB], and average tracking error of 1.5 [m] and 6.5 [m] in the detections of a scuba diver and sandbar shark, respectively. For reproducibility, we share our sea experiment data.
Streptococcus agalactiae is one of the most important fish pathogenic bacteria as it is responsible for epizootic mortalities in both wild and farmed species. S. agalactiae is also known as a zoonotic agent. In July 2018, a stranded wild sandbar shark (Carcharhinus plumbeus), one of the most common shark species in the Mediterranean Sea, was found moribund on the seashore next to Netanya, Israel, and died a few hours later. A post-mortem examination, histopathology, classical bacteriology and advanced molecular techniques revealed a bacterial infection caused by S. agalactiae, type Ia-ST7. Available sequences publicly accessible databases and phylogenetic analysis suggest that the S. agalactiae isolated in this case is closely related to fish and human isolates. To the best of our knowledge, this is the first description of a fatal streptococcosis in sandbar sharks.
The automatic classification of fish species appearing in images and videos from underwater cameras is a challenging task, albeit one with a large potential impact in environment conservation, marine fauna health assessment, and fishing policy. Deep neural network models, such as convolutional neural networks, are a popular solution to image recognition problems. However, such models typically require very large datasets to train millions of model parameters. Because underwater fish image and video datasets are scarce, non-uniform, and often extremely unbalanced, deep neural networks may be inadequately trained, and undergo a much larger risk of overfitting. In this paper, we propose small convolutional neural networks as a practical engineering solution that helps tackle fish image classification. The concept of “small” refers to the number of parameters of the resulting models: smaller models are lighter to run on low-power devices, and drain fewer resources per execution. This is especially relevant for fish recognition systems that run unattended on offshore platforms, often on embedded hardware. Here, established deep neural network models would require too many computational resources. We show that even networks with little more than 12,000 parameters provide an acceptable working degree of accuracy in the classification task (almost 42% for six fish species), even when trained on small and unbalanced datasets. If the fish images come from videos, we augment the data via a low-complexity object tracking algorithm, increasing the accuracy to almost 49% for six fish species. We tested the networks with images obtained from the deployments of an experimental system in the Mediterranean sea, showing a good level of accuracy given the low quality of the dataset.
species co-occurred and share the study site, their finerscale associations revealed temporal partitioning between species and species assortment in sandbar sharks. The multi-species network was also structured by sex. The difference between species may indicate separate strategies and temporal niche partitioning at the aggregation site. The particularly warmer temperatures (~ 5-10 °C warmer) caused by the electric power plant suggest that female dusky sharks follow the thermal niche-fecundity hypothesis by selecting warmer waters to optimize gestation, while male sandbar sharks socialize at the site. This study represents the first attempt to examine the finescale structure of a mixed-species aggregation of sharks and provides new insights into the shark's social structures through tolerance of each other and social-niche partitioning in this mixed-species aggregation.
Streptococcosis is an infectious bacterial disease of both homeotherms and poikilotherms. Among the Streptococcus species that infect marine animals, Streptococcus agalactiae has the broadest host spectrum, including different aquatic organisms in freshwater and marine environments. The common dolphin (Delphinus delphis) is categorized as Endangered in the Mediterranean Sea. There are few reports of a streptococcal infection of D. delphis, caused by Streptococcus phocae and Streptococcus iniae. Here we report the isolation and identification of S. agalactiae in a stranded, wild male common dolphin that was found dead in September 2020 on the seashore next to the city of Bat-Yam, Israel. The carcass was fresh with a moderate nutritional status and with no apparent fishing gear or other anthropogenic-related signs. A post-mortem examination did not reveal an apparent cause of death, but further laboratory analysis demonstrated a S. agalactiae bacterial presence in urine, lungs and pericardial fluid that was characterized as type Ia-ST7 by whole genome sequencing. Interestingly, this isolate was found to be almost identical to another isolate recently recovered from a wild sandbar shark (Carcharhinus plumbeus) in the same area in Israel, the eastern Mediterranean Sea.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.