Automated Video-Based Capture of Crustacean Fisheries Data Using Low-Power Hardware.

This work investigates the application of Computer Vision to the problem of the automated counting and measuring of crabs and lobsters onboard fishing boats. The aim is to provide catch count and measurement data for these key commercial crustacean species. This can provide vital input data for stock assessment models, to enable the sustainable management of these species. The hardware system is required to be low-cost, have low-power usage, be waterproof, available (given current chip shortages), and able to avoid over-heating. The selected hardware is based on a Raspberry Pi 3A+ contained in a custom waterproof housing. This hardware places challenging limitations on the options for processing the incoming video, with many popular deep learning frameworks (even light-weight versions) unable to load or run given the limited computational resources. The problem can be broken into several steps: (1) Identifying the portions of the video that contain each individual animal; (2) Selecting a set of representative frames for each animal, e.g, lobsters must be viewed from the top and underside; (3) Detecting the animal within the frame so that the image can be cropped to the region of interest; (4) Detecting keypoints on each animal; and (5) Inferring measurements from the keypoint data. In this work, we develop a pipeline that addresses these steps, including a key novel solution to frame selection in video streams that uses classification, temporal segmentation, smoothing techniques and frame quality estimation. The developed pipeline is able to operate on the target low-power hardware and the experiments show that, given sufficient training data, reasonable performance is achieved.

Donsol: an important reproductive habitat for the world's largest fish Rhincodon typus?

Little is known about the reproductive ecology of the whale shark Rhincodon typus. On 15 March 2020, a free-swimming neonate whale shark was found in the shallow, coastal waters of Donsol, Philippines. The total length of the male shark was 60 cm, falling within the species known size-at-birth. This is the third occurrence of neonatal whale sharks reported in the area, and coupled with the occurrence of juveniles and adults, and anecdotal mating and precopulatory behaviour reported herein, the importance of the site for this endangered species is highlighted.

Feeding the world's largest fish: highly variable whale shark residency patterns at a provisioning site in the Philippines.

Provisioning wildlife for tourism is a controversial yet widespread practice. We analysed the residency patterns of juvenile whale sharks (Rhincodon typus) in Oslob, Philippines, where provisioning has facilitated a large shark-watching operation since 2011. We identified 208 individual sharks over three years, with an average of 18.6 (s.d. = 7.8, range = 6-43) individuals sighted per week. Weekly shark abundance varied seasonally and peak-season abundance (approx. May-November) increased across years. Whale sharks displayed diverse individual site visitation patterns ranging from a single visit to sporadic visits, seasonal residency and year-round residency. Nine individuals became year-round residents, which represents a clear response to provisioning. The timing of the seasonal peak at Oslob did not align with known non-provisioned seasonal aggregations elsewhere in the Philippines, which could suggest that seasonal residents at Oslob exploit this food source when prey availability at alternative sites is low. Since prolonged residency equates to less time foraging naturally, provisioning could influence foraging success, alter distributions and lead to dependency in later life stages. Such impacts must be carefully weighed against the benefits of provisioning (i.e. tourism revenue in a remote community) to facilitate informed management decisions.

Learning from a provisioning site: code of conduct compliance and behaviour of whale sharks in Oslob, Cebu, Philippines.

While shark-based tourism is a rapidly growing global industry, there is ongoing controversy about the effects of provisioning on the target species. This study investigated the effect of feeding on whale sharks (Rhincodon typus) at a provisioning site in Oslob, Cebu, in terms of arrival time, avoidance and feeding behaviour using photo-identification and focal follows. Additionally, compliance to the code of conduct in place was monitored to assess tourism pressure on the whale sharks. Newly identified sharks gradually arrived earlier to the provisioning site after their initial sighting, indicating that the animals learn to associate the site with food rewards. Whale sharks with a long resighting history showed anticipatory behaviour and were recorded at the site on average 5 min after the arrival of feeder boats. Results from a generalised linear mixed model indicated that animals with a longer resighting history were less likely to show avoidance behaviour to touches or boat contact. Similarly, sequential data on feeding behaviour was modelled using a generalised estimating equations approach, which suggested that experienced whale sharks were more likely to display vertical feeding behaviour. It was proposed that the continuous source of food provides a strong incentive for the modification of behaviours, i.e., learning, through conditioning. Whale sharks are large opportunistic filter feeders in a mainly oligotrophic environment, where the ability to use novel food sources by modifying their behaviour could be of great advantage. Non-compliance to the code of conduct in terms of minimum distance to the shark (2 m) increased from 79% in 2012 to 97% in 2014, suggesting a high tourism pressure on the whale sharks in Oslob. The long-term effects of the observed behavioural modifications along with the high tourism pressure remain unknown. However, management plans are traditionally based on the precautionary principle, which aims to take preventive actions even if data on cause and effect are still inconclusive. Hence, an improved enforcement of the code of conduct coupled with a reduction in the conditioning of the whale sharks through provisioning were proposed to minimise the impacts on whale sharks in Oslob.