Recent years have seen several projects across the globe using drones to detect sharks, including several high profile projects around alerting beach authorities to keep people safe. However, so far many of these attempts have used cloud-based machine learning solutions for the detection component, which complicates setup and limits their use geographically to areas with internet connection. An on-device (or on-controller) shark detector would offer greater freedom for researchers searching for and tracking sharks in the field, but such a detector would need to operate under reduced resource constraints. To this end we look at SSD MobileNet, a popular object detection architecture that targets edge devices by sacrificing some accuracy. We look at the results of SSD MobileNet in detecting sharks from a data set of aerial images created by a collaboration between Cal Poly and CSU Long Beach’s Shark Lab. We conclude that SSD MobileNet does suffer from some accuracy issues with smaller objects in particular, and we note the importance of customized anchor box configuration.
","abstract_html":"<p>Recent years have seen several projects across the globe using drones to detect sharks, including several high profile projects around alerting beach authorities to keep people safe. However, so far many of these attempts have used cloud-based machine learning solutions for the detection component, which complicates setup and limits their use geographically to areas with internet connection. An on-device (or on-controller) shark detector would offer greater freedom for researchers searching for and tracking sharks in the field, but such a detector would need to operate under reduced resource constraints. To this end we look at SSD MobileNet, a popular object detection architecture that targets edge devices by sacrificing some accuracy. We look at the results of SSD MobileNet in detecting sharks from a data set of aerial images created by a collaboration between Cal Poly and CSU Long Beach’s Shark Lab. We conclude that SSD MobileNet does suffer from some accuracy issues with smaller objects in particular, and we note the importance of customized anchor box configuration.</p>","abstract_has_math":false,"creators":["Moore, Daniel"],"institution":null,"degree_name":"MS in Computer Science","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Franz Kurfess","Computer Science","College of Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-12-01T08:00:00Z","date_published":"2020-12-01T08:00:00Z","updated_at":"2026-07-24T01:32:42Z","subjects":["SSD-MobileNet","Sharks","Drones","Object-Detection","Machine-Learning","Computational Engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["10.15368/theses.2020.176"],"render_values":[{"text":"10.15368/theses.2020.176","href":"https://doi.org/10.15368/theses.2020.176","code":true}]}]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/2370","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Franz Kurfess","Computer Science","College of Engineering"]},{"key":"dc:creator","label":"Author","values":["Moore, Daniel"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2021-12-03T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Computer Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["SSD-MobileNet","Sharks","Drones","Object-Detection","Machine-Learning","Computational Engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/2370","10.15368/theses.2020.176"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Recent years have seen several projects across the globe using drones to detect sharks, including several high profile projects around alerting beach authorities to keep people safe. However, so far many of these attempts have used cloud-based machine learning solutions for the detection component, which complicates setup and limits their use geographically to areas with internet connection. An on-device (or on-controller) shark detector would offer greater freedom for researchers searching for and tracking sharks in the field, but such a detector would need to operate under reduced resource constraints. To this end we look at SSD MobileNet, a popular object detection architecture that targets edge devices by sacrificing some accuracy. We look at the results of SSD MobileNet in detecting sharks from a data set of aerial images created by a collaboration between Cal Poly and CSU Long Beach’s Shark Lab. We conclude that SSD MobileNet does suffer from some accuracy issues with smaller objects in particular, and we note the importance of customized anchor box configuration.
"]},{"key":"dc:title","label":"Title","values":["Towards On-Device Detection of Sharks with Drones"]}]}],"canonical_facts":{"dc:contributor":["Franz Kurfess","Computer Science","College of Engineering"],"dc:creator":["Moore, Daniel"],"dc:date.available":["2021-12-03T08:00:00Z"],"dc:description.abstract":["Recent years have seen several projects across the globe using drones to detect sharks, including several high profile projects around alerting beach authorities to keep people safe. However, so far many of these attempts have used cloud-based machine learning solutions for the detection component, which complicates setup and limits their use geographically to areas with internet connection. An on-device (or on-controller) shark detector would offer greater freedom for researchers searching for and tracking sharks in the field, but such a detector would need to operate under reduced resource constraints. To this end we look at SSD MobileNet, a popular object detection architecture that targets edge devices by sacrificing some accuracy. We look at the results of SSD MobileNet in detecting sharks from a data set of aerial images created by a collaboration between Cal Poly and CSU Long Beach’s Shark Lab. We conclude that SSD MobileNet does suffer from some accuracy issues with smaller objects in particular, and we note the importance of customized anchor box configuration.
"],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/2370","10.15368/theses.2020.176"],"dc:subject":["SSD-MobileNet","Sharks","Drones","Object-Detection","Machine-Learning","Computational Engineering"],"dc:title":["Towards On-Device Detection of Sharks with Drones"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["MS in Computer Science"]},"updated_at":"2026-07-24T01:32:42Z"}