{"id":198,"date":"2025-12-28T16:25:35","date_gmt":"2025-12-28T15:25:35","guid":{"rendered":"https:\/\/vision.inf.uniri.hr\/?page_id=198"},"modified":"2026-01-20T15:09:57","modified_gmt":"2026-01-20T14:09:57","slug":"smartseaguard-project-info","status":"publish","type":"page","link":"https:\/\/vision.inf.uniri.hr\/?page_id=198","title":{"rendered":"SmartSeaGuard – Project Info"},"content":{"rendered":"\n

Code: <\/strong>uniri-mzi-25-10
Acronim<\/strong>: SmartSeaGuard
Project Title: <\/strong>SmartSeaGuard: Intelligent system for coastal surveillance and increasing safety at sea
Project Title (hr): <\/strong>SmartSeaGuard: Inteligentni sustav za nadzor priobalja i pove\u0107anje sigurnosti na moru
Project manager: <\/strong>prof. dr. sc. Marina Iva\u0161i\u0107 Kos prof. mat. i inf.
Project starts: <\/strong>01. 10. 2025.
Duration: <\/strong>48 Months
<\/p>\n\n\n\n

Project abstract:<\/strong>
The SmartSeaGuard project aims to enhance the work of rescue services, which play a crucial role in preserving human lives and ensuring safety at sea and in coastal areas.<\/p>\n\n\n\n

Numerous people are involved in maritime accidents, primarily due to drowning caused by a combination of negligence, lack of swimming skills, and risky behavior. Swimmers, divers, and individuals using inflatables, paddleboards, or jet skis are particularly vulnerable. They often venture far from the shore, exposing themselves to dangers such as collisions with vessels. Falls into the water and inability to return due to exhaustion, disorientation, or adverse weather conditions like strong winds, currents, and waves are also common. Safety is further compromised by high-speed navigation near the shore, which can lead to accidents involving swimmers, destabilization of smaller vessels, or collisions under conditions of reduced visibility and bad weather.<\/p>\n\n\n\n

Maritime rescue services play an essential role in ensuring safety through monitoring, accident prevention, search and rescue operations, as well as ecological protection of coastal areas. Effective rescue operations require accurate situation assessment and rapid intervention to increase the chances of saving lives while preserving the safety of rescuers.<\/p>\n\n\n\n

The SmartSeaGuard project focuses on applying new technologies such as artificial intelligence and computer vision to assist rescue services in timely interventions. During the project, robust models for automatic detection of individuals in the sea and vessels will be developed to alert potentially dangerous situations, such as people who have drifted too far from shore or are in restricted access areas, as well as vessels gliding too close to shore. By integrating various algorithms such as anomaly detection and motion analysis, models for detecting drowning<\/p>\n\n\n\n

victims and rare events will also be developed. To improve model robustness under adverse weather conditions, nighttime settings, and poor visibility\u2014common factors in maritime accidents\u2014multimodal models utilizing thermal cameras will be created.<\/p>\n\n\n\n

The goal is to provide an innovative and practical solution to assist rescue services in maritime interventions. The prototype will be optimized for edge computing applications such as smart surveillance cameras on the coast and drones, thereby enhancing rescue capacities and efficient resource management, particularly in areas with high tourist activity.<\/p>\n\n\n\n

Project abstract(hr):<\/strong>
Projekt SmartSeaGuard ima za cilj unaprijediti rad spasila\u010dke slu\u017ebe koja ima klju\u010dnu ulogu u o\u010duvanju ljudskih \u017eivota i sigurnosti na moru i obalnom podru\u010dju.<\/p>\n\n\n\n

Brojni ljudi stradavaju u morskim nesre\u0107ama, ponajvi\u0161e zbog utapanja uzrokovanog kombinacijom nepa\u017enje, nepoznavanja plivanja i rizi\u010dnog pona\u0161anja. Posebno su ugro\u017eeni pliva\u010di, ronioci te osobe na napuhancima, supovima ili skuterima. Oni se \u010desto udaljavaju od obale i izla\u017eu opasnosti sudara s plovilima. \u010cesti su i padovi u vodu i nemogu\u0107nost povratka zbog iscrpljenosti, dezorijentiranosti ili nepovoljnih vremenskih uvjeta poput jakog vjetra, struja i valova. Sigurnost dodatno ugro\u017eava plovidba velikom brzinom blizu obale koja mo\u017ee uzrokovati nesre\u0107e s pliva\u010dima, destabilizaciju manjih plovila ili sudare u uvjetima smanjene vidljivosti i lo\u0161eg vremena.<\/p>\n\n\n\n

Spasila\u010dka slu\u017eba na moru ima va\u017enu ulogu u o\u010duvanju sigurnosti kroz nadzor, prevenciju nesre\u0107a te traganje i spa\u0161avanje osoba, kao i ekolo\u0161ku za\u0161titu priobalja. U spasila\u010dkim aktivnostima va\u017ena je dobra procjena situacije i brza intervencija kako bi se pove\u0107ala \u0161ansa za spa\u0161avanje \u017eivota ali i o\u010duvala sigurnost spasioca.<\/p>\n\n\n\n

Projekt SmartSeaGuard usmjeren je na primjenu novih tehnologija kao \u0161to su umjetna inteligencija i ra\u010dunalni vid za pomo\u0107 Spasila\u010dkim slu\u017ebama u pravovremenim intervencijama. Tijekom projekta razvit \u0107e se robusni modeli automatske detekcije osoba u moru i plovila koji \u0107e alarmirati potencijalno opasne situacije kao \u0161to su osobe koje su se odmakle predaleko od obale ili se nalaze u podru\u010dju s ograni\u010denjem pristupa, te plovila koja glisiraju preblizu obale. Dodatnom integracijom razli\u010ditih algoritama kao \u0161to je detekciju anomalija i analiza pokreta razviti \u0107e se modeli za detekciju utopljenika i rijetkih doga\u0111aja. Radi pove\u0107anja robusnosti modela na lo\u0161e vremenske uvjete, no\u0107 i slabu vidljivost kada se nesre\u0107e na moru naj\u010de\u0161\u0107e i doga\u0111aju, razvit \u0107e se multimodalni modeli koji koriste termalnu kameru.<\/p>\n\n\n\n

Cilj je ponuditi inovativno i prakti\u010dno rje\u0161enje za pomo\u0107 spasila\u010dkoj slu\u017ebi u intervencijama na moru te \u0107e se prototip optimizirati za rubno ra\u010dunarstvo kao \u0161to je instalacija na pametne nadzorne kamere na obali ili dron \u010dime \u0107e se unaprijediti i pove\u0107ati spasila\u010dki kapaciteti i racionalno raspolaganje resursima, posebno u podru\u010dju s jakim turisti\u010dkim prometom.<\/p>\n\n\n\n

Project Goal: <\/strong>
Develop a prototype of an AI-based system to assist rescue services and port authorities

Specific Goals:<\/strong>
1. Develop multimodal computer vision models for detecting vessels and people at sea in different imaging conditions to support
sea rescue services
2. Develop algorithms for determining the speed and distance of detected vessels from the shore
3. Develop a methodology for detecting rare events and anomalies at sea (such as sharks, capsized boats, drowning people)<\/p>\n\n\n\n

Team Members:<\/strong>
Izv. prof. dr. sc. Miran Pobar
Dino Ladavac<\/p>\n\n\n\n

Doctoral Students:<\/strong>
Goran Paulin
Kristina Host
Ivan Vrsalovi\u0107
Domagoj Palini\u0107<\/p>\n\n\n\n

External Collaborators<\/strong>
Prof. dr. sc. Jordi Gonzales Sabate, Computer Vision Center (CVC), Universitat Aut\u00f2noma de Barcelona (UAB)
Doc. Dr. sc. Aleksandar Vorkapi\u0107, pomorac, upravitelj stroja
Dr. sc. Sa\u0161a Sambolek, ravnatelj SS Tin Ujevi\u0107, Kutina
<\/strong><\/p>\n","protected":false},"excerpt":{"rendered":"

Code: uniri-mzi-25-10Acronim: SmartSeaGuardProject Title: SmartSeaGuard: Intelligent system for coastal surveillance and increasing safety at seaProject Title (hr): SmartSeaGuard: Inteligentni sustav za nadzor priobalja i pove\u0107anje sigurnosti na moruProject manager: prof. dr. sc. Marina Iva\u0161i\u0107 Kos prof. mat. i inf.Project starts: 01. 10. 2025.Duration: 48 Months Project abstract:The SmartSeaGuard project aims to enhance the work of […]<\/p>\n","protected":false},"author":2,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-198","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/vision.inf.uniri.hr\/index.php?rest_route=\/wp\/v2\/pages\/198","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/vision.inf.uniri.hr\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/vision.inf.uniri.hr\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/vision.inf.uniri.hr\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/vision.inf.uniri.hr\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=198"}],"version-history":[{"count":3,"href":"https:\/\/vision.inf.uniri.hr\/index.php?rest_route=\/wp\/v2\/pages\/198\/revisions"}],"predecessor-version":[{"id":213,"href":"https:\/\/vision.inf.uniri.hr\/index.php?rest_route=\/wp\/v2\/pages\/198\/revisions\/213"}],"wp:attachment":[{"href":"https:\/\/vision.inf.uniri.hr\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=198"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}