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

Research output: Contribution to journalArticlepeer-review

Standard Standard

Automated Video-Based Capture of Crustacean FIsheries Data Using Low-Power Hardware. / Dal Toe, Sebastian Gregory; Neal, Marie; Hold, Natalie et al.
In: Sensors, Vol. 23, No. 18, 7897, 15.09.2023.

Research output: Contribution to journalArticlepeer-review

HarvardHarvard

APA

CBE

MLA

VancouverVancouver

Dal Toe SG, Neal M, Hold N, Heney C, Turner B, McCoy E et al. Automated Video-Based Capture of Crustacean FIsheries Data Using Low-Power Hardware. Sensors. 2023 Sept 15;23(18):7897. doi: https://doi.org/10.3390/s23187897

Author

Dal Toe, Sebastian Gregory ; Neal, Marie ; Hold, Natalie et al. / Automated Video-Based Capture of Crustacean FIsheries Data Using Low-Power Hardware. In: Sensors. 2023 ; Vol. 23, No. 18.

RIS

TY - JOUR

T1 - Automated Video-Based Capture of Crustacean FIsheries Data Using Low-Power Hardware

AU - Dal Toe, Sebastian Gregory

AU - Neal, Marie

AU - Hold, Natalie

AU - Heney, Charlie

AU - Turner, Bex

AU - McCoy, Emer

AU - Iftikhar, Muhammad

AU - Tiddeman, Bernard

PY - 2023/9/15

Y1 - 2023/9/15

N2 - 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

AB - 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

U2 - https://doi.org/10.3390/s23187897

DO - https://doi.org/10.3390/s23187897

M3 - Article

VL - 23

JO - Sensors

JF - Sensors

SN - 1424-8220

IS - 18

M1 - 7897

ER -