Pregled bibliografske jedinice broj: 829354
Performance of compressive sensing image reconstruction for search and rescue
Performance of compressive sensing image reconstruction for search and rescue // IEEE geoscience and remote sensing letters, 13 (2016), 11; 1739-1743 doi:10.1109/LGRS.2016.2606767 (međunarodna recenzija, članak, znanstveni)
CROSBI ID: 829354 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Performance of compressive sensing image reconstruction for search and rescue
Autori
Musić, Josip ; Marasović, Tea ; Papić, Vladan ; Orović, Irena ; Stanković, Srdjan
Izvornik
IEEE geoscience and remote sensing letters (1545-598X) 13
(2016), 11;
1739-1743
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni
Ključne riječi
compressed sensing ; Image reconstruction ; image quality ; Object detection ; search and rescue ; unmanned aerial vehicles
Sažetak
In the paper, the system combining compressive sensing based image reconstruction and object detection algorithm is introduced. The use of compressive sensing is a promising approach for search and rescue applications since it highly reduces amount of data that needs to be transmitted. However, the high quality reconstruction of such images is a challenging task due to the complexity of structures and number of tiny details, possibly being the objects of interest. Hence, the performance of image reconstruction is evaluated in terms of the missing data amount and object detection quality. Object detection is performed by applying two- stage data segmentation algorithm based on mean shift clustering. The results quality is measured using structural similarity index and PSNR.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika, Računarstvo, Temeljne tehničke znanosti
POVEZANOST RADA
Ustanove:
Fakultet elektrotehnike, strojarstva i brodogradnje, Split
Citiraj ovu publikaciju:
Časopis indeksira:
- Current Contents Connect (CCC)
- Web of Science Core Collection (WoSCC)
- Science Citation Index Expanded (SCI-EXP)
- SCI-EXP, SSCI i/ili A&HCI
- Scopus