Visual analysis of complex fish habitats is an important step towards sustainable fisheries for human consumption and environmental protection. Deep Learning methods have shown great promise for scene analysis when trained on large-scale datasets. However, current datasets for fish analysis tend to focus on the classification task within constrained, plain environments which do not capture the complexity of underwater fish habitats. To address this limitation, we present DeepFish as a benchmark suite with a large-scale dataset to train and test methods for several computer vision tasks. The dataset consists of approximately 40 thousand images collected underwater from 20 habitats in the marine-environments of tropical Australia. The dataset originally contained only classification labels. Thus, we collected point-level and segmentation labels to have a more comprehensive fish analysis benchmark. These labels enable models to learn to automatically monitor fish count, identify their locations, and estimate their sizes. Our experiments provide an in-depth analysis of the dataset characteristics, and the performance evaluation of several state-of-the-art approaches based on our benchmark. Although models pre-trained on ImageNet have successfully performed on this benchmark, there is still room for improvement. Therefore, this benchmark serves as a testbed to motivate further development in this challenging domain of underwater computer vision. Monitoring fish in their natural habitat is an important step towards sustainable fisheries. In the New South Wales state of Australia, for example, fisheries is valued at more than 100 million Australian dollars in 2012-2013 14. Effective monitoring can provide information about which areas require protection and restoration to maintain healthy fish populations for both human consumption and environmental protection. Having a system that can automatically perform comprehensive monitoring can significantly reduce labour costs and increase efficiency. The system can lead to a large positive sustainability impact and improve our ability to maintain a healthy ecosystem. Deep learning methods have consistently achieved state-of-the-art results in image analysis. Many methods based on deep neural networks achieved top performance for a variety of applications, including, ecological monitoring with camera trap data. One reason behind this success is that these methods can leverage largescale, publicly available datasets such as ImageNet 6 and COCO 24 for training before being fine-tuned for a new application. A particularly challenging application involves automatic analysis of underwater fish habitats which demands a comprehensive, accurate computer vision system. Thus, considerable research efforts have been put towards developing systems for the task of understanding complex marine environments and distinguishing between a diverse set of fish species, which are based on publicly available fish datasets 1,3,8,15,35. However, these fish datasets are small and do not fully capture t...
Canopy-forming macroalgae can construct extensive meadow habitats in tropical seascapes occupied by fishes that span a diversity of taxa, life-history stages and ecological roles. Our synthesis assessed whether these tropical macroalgal habitats have unique fish assemblages, provide fish nurseries and support local fisheries. We also applied a meta-analysis of independent surveys across 23 tropical reef locations in 11 countries to examine how macroalgal canopy condition is related to the abundance of macroalgal-associated fishes. Over 627 fish species were documented in tropical 2 | FULTON eT aL. 1 | INTRODUC TI ON Conservation and management of fish biodiversity requires an understanding of the habitats needed to support and replenish all of the species in a region of interest. While some species may be uniquely linked to a certain habitat type, many fish taxa follow a triphasic life cycle, where planktonic larvae settle into an initial habitat before migrating to different habitats as juveniles and/or adults. Moreover, adult fishes often move among habitats over daily or longer time scales to fulfil foraging or reproductive activities. Characterization of a fauna according to surveys within a single habitat type, therefore, can lead to a conclusion that a collection of species are dependent on that habitat type. A wider seascape perspective that tracks the abundance and activities of fishes across different patch habitat types is needed to reveal the full suite of connected habitats that sustain fish populations and com
Climate change is already affecting Arctic species including infectious disease agents and greater changes are expected. Some infectious diseases are already increasing but future changes are difficult to predict because of the complexity of host-agent-environment relationships. However mechanisms related to climate change that will influence disease patterns are understood. Warmer temperatures will benefit free living bacteria and parasites whose survival and development is limited by temperature. Warmer temperatures could promote survivability, shorter development rates and transmission. Insects such as mosquitoes and ticks that transmit disease agents may also benefit from climate change as well as the diseases they spread. Climate change will have significant impacts on biodiversity. Disease agents of species that benefit from warming will likely become more prevalent. Host species stressed by changing environmental conditions may be more vulnerable to disease agents. Warming could lead to increased agriculture and other economic opportunities in the Arctic bringing people, domestic food animals, pets and invasive species and their disease agents into Northern regions. Climate warming may also favor the release of persistent environmental pollutants some of which can affect the immune system and may favor increased rates of some diseases.
To address the problem of post-traumatic stress disorder (PTSD) in severe mental illness, the Trauma Recovery Group, a mixed gender cognitive-behavioral program, was developed and piloted at a community mental health center. The 21-week program includes breathing retraining, education about PTSD, cognitive restructuring, coping with symptoms, and making a recovery plan. Eighty clients were assessed at baseline and 41 provided follow-up data. Retention in the group was good: 59%. Treatment completers improved significantly in PTSD symptoms and diagnosis, depression, and post-traumatic cognitions, but dropouts did not. The results support the feasibility of the program and suggest it produces clinical benefits.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.