Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 1159254

Detection of humans in drone images for search and rescue operations


Nayee, Dousai; Lončarić, Sven
Detection of humans in drone images for search and rescue operations // 2021 3rd Asia Pacific Information Technology Conference (APIT 2021)
New York (NY): Association for Computing Machinery (ACM), 2021. pp. 69-75, 6 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


CROSBI ID: 1159254 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Detection of humans in drone images for search and rescue operations

Autori
Nayee, Dousai ; Lončarić, Sven

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

ISBN
978-1-4503-8810-8

Skup
2021 3rd Asia Pacific Information Technology Conference (APIT 2021)

Mjesto i datum
Bangkok, Tajland, 15.01.2021. - 17.01.2021

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
deep-learning, human detection, HERIDAL dataset, search and rescue operation

Sažetak
Object detection has solved many problems in different applications like monitoring security, search and rescue operations, semantic segmentation, autonomous driving and so on. Despite this huge success rate in normal ground captured images, it is still a challenging task to detect humans or any other objects from the UAV(Unmanned Aerial Vehicle) captured images due to a few challenges like pose and scale variations, weather conditions, artefacts like people wearing hats, varying attitude and camouflaged environment. In this paper, we propose a novel approach for the detection of humans in aerial images, for search and rescue operations. This method explains how to train the existing high-resolution aerial database of HERIDAL. The EfficientDET deep neural network is trained using a newly generated database to solve the human detection problem. To the best of our knowledge, the proposed method has achieved the best accuracy of 93.29% mAP compared to all existing methods. The proposed method has been compared to the system used by Croatian Mountain search and rescue (SAR) teams (IPSAR) and also with the state-of-art proposed HERIDAL database paper which is based on extracting the salient features, which has slightly worse result compared to the results of this paper.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo, Informacijske i komunikacijske znanosti



POVEZANOST RADA


Projekti:
EK-H2020-764951 - Uronjene vizualne tehnologije za sigurnosno kritične aplikacije (ImmerSAFE) (Lončarić, Sven, EK ) ( CroRIS)

Profili:

Avatar Url Sven Lončarić (autor)

Avatar Url Nayee Dousai (autor)

Poveznice na cjeloviti tekst rada:

Pristup cjelovitom tekstu rada doi.org

Citiraj ovu publikaciju:

Nayee, Dousai; Lončarić, Sven
Detection of humans in drone images for search and rescue operations // 2021 3rd Asia Pacific Information Technology Conference (APIT 2021)
New York (NY): Association for Computing Machinery (ACM), 2021. pp. 69-75, 6 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
Nayee, D. & Lončarić, S. (2021) Detection of humans in drone images for search and rescue operations. U: 2021 3rd Asia Pacific Information Technology Conference (APIT 2021).
@article{article, author = {Nayee, Dousai and Lon\v{c}ari\'{c}, Sven}, year = {2021}, pages = {6}, chapter = {pp. 69-75}, keywords = {deep-learning, human detection, HERIDAL dataset, search and rescue operation}, isbn = {978-1-4503-8810-8}, title = {Detection of humans in drone images for search and rescue operations}, keyword = {deep-learning, human detection, HERIDAL dataset, search and rescue operation}, publisher = {Association for Computing Machinery (ACM)}, publisherplace = {Bangkok, Tajland}, chapternumber = {pp. 69-75} }
@article{article, author = {Nayee, Dousai and Lon\v{c}ari\'{c}, Sven}, year = {2021}, pages = {6}, chapter = {pp. 69-75}, keywords = {deep-learning, human detection, HERIDAL dataset, search and rescue operation}, isbn = {978-1-4503-8810-8}, title = {Detection of humans in drone images for search and rescue operations}, keyword = {deep-learning, human detection, HERIDAL dataset, search and rescue operation}, publisher = {Association for Computing Machinery (ACM)}, publisherplace = {Bangkok, Tajland}, chapternumber = {pp. 69-75} }




Contrast
Increase Font
Decrease Font
Dyslexic Font