Pretraga

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

Napredna pretraga

Pregled bibliografske jedinice broj: 1028055

On the Comparison of Classic and Deep Keypoint Detector and Descriptor Methods

Bojanić, David; Bartol, Kristijan; Pribanić, Tomislav; Petković, Tomislav; Diez Donoso, Yago; Salvi Mas, Joaquim
On the Comparison of Classic and Deep Keypoint Detector and Descriptor Methods // 2019 11th International Symposium on Image and Signal Processing and Analysis (ISPA) / Lončarić, Sven ; Bregović, Robert ; Carli, Marco ; Subašić, Marko (ur.).
Dubrovnik: Institute of Electrical and Electronics Engineers (IEEE), 2019. str. 64-69 doi:10.1109/ISPA.2019.8868792 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)

CROSBI ID: 1028055 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
On the Comparison of Classic and Deep Keypoint Detector and Descriptor Methods

Autori
Bojanić, David ; Bartol, Kristijan ; Pribanić, Tomislav ; Petković, Tomislav ; Diez Donoso, Yago ; Salvi Mas, Joaquim

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

Izvornik
2019 11th International Symposium on Image and Signal Processing and Analysis (ISPA) / Lončarić, Sven ; Bregović, Robert ; Carli, Marco ; Subašić, Marko - Dubrovnik : Institute of Electrical and Electronics Engineers (IEEE), 2019, 64-69

ISBN
978-1-7281-3140-5

Skup
11th International Symposium on Image and Signal Processing and Analysis (ISPA 2019)

Mjesto i datum
Dubrovnik, Hrvatska, 23.09.2019. - 25.09.2019

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
keypoint detection, keypoint description, deep learning, benchmark evaluation, average precision

Sažetak
The purpose of this study is to give a performance comparison between several classic hand-crafted and deep keypoint detector and descriptor methods. In particular, we consider the following classical algorithms: SIFT, SURF, ORB, FAST, BRISK, MSER, HARRIS, KAZE, AKAZE, AGAST, GFTT, FREAK, BRIEF and RootSIFT, where a subset of all combinations is paired into detector-descriptor pipelines. Additionally, we analyze the performance of two recent and perspective deep detector-descriptor models, LF- Net and SuperPoint. Our benchmark relies on the HPSequences dataset that provides real and diverse images under various geometric and illumination changes. We analyze the performance on three evaluation tasks: keypoint verification, image matching and keypoint retrieval. The results show that certain classic and deep approaches are still comparable, with some classic detector-descriptor combinations overperforming pretrained deep models. In terms of the execution times of tested implementations, SuperPoint model is the fastest, followed by ORB.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo



POVEZANOST RADA

Projekti:
KK.01.1.1.01.0009 - Napredne metode i tehnologije u znanosti o podatcima i kooperativnim sustavima (EK )
HRZZ-IP-2018-01-8118 - Izračun antropometrijskih mjera pametnim telefonom i tabletom (STEAM) (Pribanić, Tomislav, HRZZ ) ( CroRIS)

Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb

Profili:

Avatar Url Tomislav Petković (autor)

Avatar Url Kristijan Bartol (autor)

Avatar Url Tomislav Pribanić (autor)

Avatar Url David Bojanić (autor)

Poveznice na cjeloviti tekst rada:

doi ieeexplore.ieee.org

Citiraj ovu publikaciju:

Bojanić, David; Bartol, Kristijan; Pribanić, Tomislav; Petković, Tomislav; Diez Donoso, Yago; Salvi Mas, Joaquim
On the Comparison of Classic and Deep Keypoint Detector and Descriptor Methods // 2019 11th International Symposium on Image and Signal Processing and Analysis (ISPA) / Lončarić, Sven ; Bregović, Robert ; Carli, Marco ; Subašić, Marko (ur.).
Dubrovnik: Institute of Electrical and Electronics Engineers (IEEE), 2019. str. 64-69 doi:10.1109/ISPA.2019.8868792 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
Bojanić, D., Bartol, K., Pribanić, T., Petković, T., Diez Donoso, Y. & Salvi Mas, J. (2019) On the Comparison of Classic and Deep Keypoint Detector and Descriptor Methods. U: Lončarić, S., Bregović, R., Carli, M. & Subašić, M. (ur.)2019 11th International Symposium on Image and Signal Processing and Analysis (ISPA) doi:10.1109/ISPA.2019.8868792.
@article{article, author = {Bojani\'{c}, David and Bartol, Kristijan and Pribani\'{c}, Tomislav and Petkovi\'{c}, Tomislav and Diez Donoso, Yago and Salvi Mas, Joaquim}, year = {2019}, pages = {64-69}, DOI = {10.1109/ISPA.2019.8868792}, keywords = {keypoint detection, keypoint description, deep learning, benchmark evaluation, average precision}, doi = {10.1109/ISPA.2019.8868792}, isbn = {978-1-7281-3140-5}, title = {On the Comparison of Classic and Deep Keypoint Detector and Descriptor Methods}, keyword = {keypoint detection, keypoint description, deep learning, benchmark evaluation, average precision}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, publisherplace = {Dubrovnik, Hrvatska} }
@article{article, author = {Bojani\'{c}, David and Bartol, Kristijan and Pribani\'{c}, Tomislav and Petkovi\'{c}, Tomislav and Diez Donoso, Yago and Salvi Mas, Joaquim}, year = {2019}, pages = {64-69}, DOI = {10.1109/ISPA.2019.8868792}, keywords = {keypoint detection, keypoint description, deep learning, benchmark evaluation, average precision}, doi = {10.1109/ISPA.2019.8868792}, isbn = {978-1-7281-3140-5}, title = {On the Comparison of Classic and Deep Keypoint Detector and Descriptor Methods}, keyword = {keypoint detection, keypoint description, deep learning, benchmark evaluation, average precision}, publisher = {Institute of Electrical and Electronics Engineers (IEEE)}, publisherplace = {Dubrovnik, Hrvatska} }

Citati:

    Altmetrijski pokazatelji:


    Podijeli:





    Contrast
    Increase Font
    Decrease Font
    Dyslexic Font
    CROSBI koristi kolačiće (cookies) kako bi poboljšao funkcionalnost stranice.