Aqua-Vision (An underwater panoramic camera with computer vision and analytics)

In the present social media-bound lifestyle, capturing memories and keeping them accessible is gaining a significant demand globally. For this purpose, a robust, portable camera system for recreational or commercial purposes can be of substantial advantage to society. Aqua-Vision intends to bring an affordable underwater camera system with various innovative features to the hands of consumers. The smart module consists of a waterproof gimbal camera that can be used underwater, providing a hassle-free and reliable user experience and offers rotary motion along two axes. The camera features various general modes like panorama, burst shot, and smart modes using inbuilt computer vision algorithms. The gimbal camera setup can be controlled and switched remotely between all possible modes using a mobile application. All the above features will allow the user to capture photos/videos in any possible setup and use the camera module for various applications. The advent of such innovative, convenient, and robust modules will help cater to the market demands effectively.

Feasibility Research on Fish Pose Estimation Based on Rotating Box Object Detection

A video-based method to quantify animal posture movement is a powerful way to analyze animal behavior. Both humans and fish can judge the physiological state through the skeleton framework. However, it is challenging for farmers to judge the breeding state in the complex underwater environment. Therefore, images can be transmitted by the underwater camera and monitored by a computer vision model. However, it lacks datasets in artificial intelligence and is unable to train deep neural networks. The main contributions of this paper include: (1) the world’s first fish posture database is established. 10 key points of each fish are manually marked. The fish flock images were taken in the experimental tank and 1000 single fish images were separated from the fish flock. (2) A two-stage attitude estimation model is used to detect fish key points. The evaluation of the algorithm performance indicates the precision of detection reaches 90.61%, F1-score reaches 90%, and Fps also reaches 23.26. We made a preliminary exploration on the pose estimation of fish and provided a feasible idea for fish pose estimation.

Feeding preference of herbivorous fish: Family Scaridae

Parrotfish is one of dominant species in Indo-Pacific areas which have 9 genera and 83 species. In ecological perspective, the feeding behaviours of these fish very important, due to control population of algae in coral reef ecosystem. They used their jaw to excavate and scrape alga which living on coral substrata, so sometime resulted on erosion in substrates and coral. The aim of this research to record the diet preference of Scariids fish in NCF Putri Menjangan conservation area, Bali on January to february 2020. Group of Scariids fish was recorded by underwater camera for one minute then the bites scared were calculated manually and photographed. The result of study showed that 10 species from two genera (Chlorurus and Scarus) was dominantly herbivorous fish in this area. The highest number of fish bites at station 1 was obtained from S. qouyi species with a total of 41.27 bpm, while stations 2 and 3 were obtained from S. rivulatus species with a number of 40.96 bpm and 41.59 bpm, respectively. The majority of parrotfish species found chose to forage on dead coral with algae substrates because the water conditions were not optimal for the growth of coral, so many corals died and their skeletons were overgrown by algae.

Optical Design and Optimization with Genetic Algorithm for High-Resolution Optics Applied to Underwater Remote-Sensing

In fields such as biology, archeology, and industry, underwater photogrammetry can be achieved using consumer-grade equipment. However, camera operations underwater differ considerably from those on land because underwater photogrammetry involves different optical phenomena. On the basis of the requirements and specifications of the marine vessel Polaris, we developed a novel underwater camera with prime and zoom lenses and a high resolving power. The camera can be used in the spectrum in shallow water and the blue–green spectrum in deep water. In the past, ordinary cameras would be placed in waterproof airtight boxes for underwater photography. These cameras were not optimized to the underwater spectrum and environment, resulting in no breakthroughs in resolving power. Furthermore, the use of the blue spectrum greatly increases during underwater and particularly deep-water surveying. Chromatic aberration and focus-point displacement generated by the shift from the shallow-water spectrum to the blue–green spectrum in deep water makes universal underwater photography even more difficult. Our proposed optical design aimed to overcome such challenges for the development of a high-resolution underwater surveying camera. We designed a prime lens and a zoom lens. We adopted a waterproof dome window on the outer surface as the basic structure and optimized it in accordance with the conditions of different water depths and spectra to obtain distortion within ±2% and high-resolution underwater imaging quality. For the zoom lens design, we employed a genetic algorithm in Zemax to attenuate chromatic aberration as a kind of extended optimization. This novel optical design that can be used in all waters is expected to greatly reduce the volume and weight of conventional underwater cameras by more than 50% and 60%, respectively, and increase their resolving power by 30–40%.

APPLICATION OF 3D ANALYSIS TECHNOLOGY OF VISION SYSTEM IMAGE IN SPORTS MEDICINE

ABSTRACT Background: Objective: The study of sports biomechanics in sports medicine usually requires a special image analysis system (software) to obtain 3D kinematics data. Taking the swimming project in sports medicine as an example, 3D water images in water have always been relatively complicated and difficult. As light travels in different media, it will refract and reflect. When testing underwater movements, if only a land camera or an underwater camera is used for testing, the error caused by light refraction will be larger, which will affect the accuracy of the test data even more. Methods: Taking breaststroke movement as an example, a three-dimensional measurement method based on the Kwon3D movement analysis system is introduced. This method is different from the simple underwater camera test. It is a three-dimensional test method combining a land camera and an underwater camera. Two underwater cameras and two land cameras were used to simultaneously calibrate the water and underwater space with the same calibration frame in the experiment after analyzing and verifying the accuracy of 3D reconstruction. Results: The comprehensive reconstruction error is small, and the average relative error is less than 1%. Conclusions: The application of three-dimensional image analysis technology of vision systems in sports medicine is reasonable and worth promoting. Level of evidence II; Therapeutic studies - investigation of treatment results.

A comparison of stride parameters and carpal and tarsal joint angles during terrestrial and swimming locomotion in domestic dogs

In recent years, canine hydrotherapy has become increasingly popular to treat a range of conditions despite a lack of empirical evidence. It is currently unclear whether joint angles and limb movements performed by dogs during swimming are quantifiably beneficial for healthy animals. This study investigated the swimming kinematics of healthy dogs to establish baseline data for this activity and compare limb kinematics to that of overground locomotion. Kinematic data were recorded from eight healthy dolichocephalic dogs (mean age: 3.4±2.2) of a variety of breeds. Overground data were collected prior to swimming and consisted of dogs trotting on a flat surface. Swimming data were collected using an underwater camera during a standard hydrotherapy session conducted by a trained canine hydrotherapist. Range of motion, primarily due to an increase in flexion, was significantly greater (P<0.005) during swimming than trotting. Stride length (P<0.001) and frequency (P<0.005) were both significantly reduced in swimming compared to trot. Swimming kinematics recorded in this study are consistent with previously published data on canine aquatic locomotion but differ from those previously reported for water treadmill exercise. This study provides an insight into aquatic locomotion in healthy dogs indicating that range of motion exceeds that of terrestrial gaits. It is unclear whether these changes are beneficial for healthy animals and therefore further research is required to develop evidence-based protocols for industry practice.

The Potential of AFX Iliac Extension in Abdominal Aortic Aneurysms with High Iliac Tortuosity

Background Recently, endovascular aortic aneurysm repair (EVAR) is the most common surgery for abdominal aortic aneurysm (AAA). However, iliac limb complications of EVAR often cause problems in patients with high iliac tortuosity. There is no difference of rate of iliac limb complication among EVAR devices, such as Excluder, Endurant, and Zenith in high iliac tortuosity. But there has been not reported about AFX. Objectives We studied AFX iliac extension as it is the only stent graft with an endoskeletal framework. This study aimed to evaluate the AFX iliac extension patency in a case in vitro and to use it in seven cases of AAA with high iliac tortuosity. Methods The silicon tube inserted in the AFX iliac extension was flexed at 30, 60, 90, and 120 degrees, and the lumen of the iliac extension was monitored using an underwater camera in the circulatory system. During the experiment, the Iwaki Bellows Pump (IWAKI CO., LTD., Tokyo, Japan) produced a pulsating flow. We used this in seven patients with AAA high iliac tortuosity cases between November 2018 and May 2019. Results If the silicon tube inserted in the AFX iliac extension was flexed at 60 and 120 degrees, the stent protruded into the lumen. However, the graft was dilated at all degrees. All seven patients with AFX iliac extension had no complications and a patent iliac artery. Conclusion The AFX iliac extension can reduce iliac limb complications in cases of high iliac tortuosity.

Effectivity of Normal Concrete and Clamshell as Materials of Artificial Pyramid Reef at Pasir Putih Beach, Situbondo - Indonesia

The bivalve anadara grandis is one of the most abundant shells which are easy to find in Indonesian waters. The number of clams consumed is directly proportional to the amount of clamshell waste, which the most part is only disposed into waste. Coral reef has a very important purpose in supporting activities in coastal areas. Artificial reef is a structure that has aim to restore the biological purpose coral reef that have been damaged. This study aims to compare the effectiveness of the use of normal concrete (made from sand, cement dan splits only) than clamshell mixture as materials of artificial reef. A field research was conducted in Pasir Putih, Situbondo, with visual descriptive method (transect with a quadrant of 25 x 25cm) and underwater camera as an aid to facilitate the observation. During the 4-month observation of the drowning, nine types of biotas were found in attaching, with the dominant biota attached to these artificial reef were bivalves, barnacles, and bryozoan. Results show that the total number and density of calcareous biota attached on clamshell concretes are higher than those of standard concretes. So, it could be concluded that the concrete reefs made of clamshells resulted in attachment of biota slightly higher than it of normal concretes and the benefits of both materials can form the coral reef ecosystem well. In particular, the use of artificial reef with a mixture of clamshells is better than normal concrete because its more effective for algae attachment and cheaper because low budget due to the material availability of clamshell presently as damage and wastes in coastal area.

Mapping 3D structure of a Sargassum forest with high-resolution sounding data obtained by multibeam echosounder

Sargassum forests play an important role in coastal waters as habitats for marine organisms, including commercial species. However, human activities have negatively affected their distribution causing a worldwide decline of Sargassum forests. Mapping and monitoring the distribution and biomass of these habitats using acoustic remote sensing techniques is key for their conservation. Nonetheless, most researches based on acoustic remote sensing methods focus on estimations of macrophyte area and its canopy height, and less researches reporting 3D visualization of these habitats. This study demonstrates the use of high-resolution multibeam echosounder (MBES) bathymetric data to visualize the 3D structure of Sargassum forests. Comparing acoustic data and underwater camera photos collected in field surveys, we identified Sargassum individuals as vertical clusters of contiguous sounding points with a base close to the sea bottom in the sounding data of the MBES. Using this criterion, we could distinguish Sargassum echoes, visualize the 3D structure of Sargassum forests and estimate the number of Sargassum individuals in the survey area. Using the relation between thallus length and dry weight of sampled Sargassum plants, standing stock and biomass could be estimated assuming the thallus length was the height of Sargassum plants identified with the MBES.

A low-cost, long-term underwater camera trap network coupled with deep residual learning image analysis

Understanding long-term trends in marine ecosystems requires accurate and repeatable counts of fishes and other aquatic organisms on spatial and temporal scales that are difficult or impossible to achieve with diver-based surveys. Long-term, spatially distributed cameras, like those used in terrestrial camera trapping, have not been successfully applied in marine systems due to limitations of the aquatic environment.Here, we develop methodology for a system of low-cost, long-term camera traps (Dispersed Environment Aquatic Cameras), deployable over large spatial scales in remote marine environments. We use machine learning to classify the large volume of images collected by the cameras. We present a case study of these combined techniques’ use by addressing fish movement and feeding behavior related to grazing halos, a well-documented benthic pattern in shallow tropical reefscapes.Cameras proved able to function continuously underwater at deployed depths (up to 7 m, with later versions deployed to 40 m) with no maintenance or monitoring for over five months, and collected time-lapse images during daylight hours for a total of over 100,000 images. Our ResNet-50-based deep learning model achieved 92.5% overall accuracy in sorting images with and without fish, and diver surveys revealed that the camera images accurately represented local fish communities.The cameras and machine learning classification represent the first successful method for broad-scale underwater camera trap deployment, and our case study demonstrates the cameras’ potential for addressing questions of marine animal behavior, distributions, and large-scale spatial patterns.