crta
Hrvatska znanstvena Sekcija img
bibliografija
3 gif
 Naslovna
 O projektu
 FAQ
 Kontakt
4 gif
Pregledavanje radova
Jednostavno pretraživanje
Napredno pretraživanje
Skupni podaci
Upis novih radova
Upute
Ispravci prijavljenih radova
Ostale bibliografije
Slični projekti
 Bibliografske baze podataka

Pregled bibliografske jedinice broj: 474496

Zbornik radova

Autori: Jurić-Kavelj, Srećko; Petrović, Ivan
Naslov: Experimental comparison of AdaBoost algorithms applied on Leg Detection with Different Range Sensor Setups
Izvornik: 19th International Workshop on Robotics in Alpe-Adria-Danube Region – RAAD 2010 / Anikó Szakál (ur.). - Budimpešta : IEEE , 2010. 267-272 (ISBN: 978-1-4244-6884-3).
Skup: 19th IEEE International Workshop on Robotics in Alpe-Adria-Danube Region
Mjesto i datum: Budimpešta, Mađarska, 23-25.06.2010.
Ključne riječi: AdaBoost; 2D range; legs; SICK; Hokuyo
Sažetak:
When tracking people or other moving objects with a mobile robot, detection is the first and most critical step. At first most researchers focused on the tracking algorithms, but recently AdaBoost (supervised machine learning technique) was used for people legs detection in 2D range data. The results are promising, but it is unclear if the obtained classifier could be used on the data from another sensor. As it would be a huge inconvenience having to train a classifier for every sensor (setup), we set out to find if, and when is a classifier trained on one sensor setup transferable to another sensor setup. We tested two sensors in five different setups. In total, we acquired 2455 range scans. Experiments showed that the classifier trained on noisier sensor data performed better at classification of data coming from other sensor setups. Classifiers trained on less noisy data were shown to be overconfident, and performed poorly on noisy data. Furthermore, experiments showed that classifiers learned on ten times smaller datasets performed as good as classifiers trained on larger datasets. Since AdaBoost is a supervised learning technique, obtaining same classifier efficiency with significantly smaller dataset means less hand labeling of the data for the same results.
Vrsta sudjelovanja: Predavanje
Vrsta prezentacije u zborniku: Cjeloviti rad (više od 1500 riječi)
Vrsta recenzije: Međunarodna recenzija
Projekt / tema: 036-0363078-3018, 036-0361621-3012
Izvorni jezik: ENG
Kategorija: Znanstveni
Znanstvena područja:
Elektrotehnika,Računarstvo,Temeljne tehničke znanosti
Puni text rada: 474496.45_raad2010.pdf (tekst priložen 5. Srp. 2010. u 11:12 sati)
URL Internet adrese: http://conf.uni-obuda.hu/raad2010/
Upisao u CROSBI: jks@fer.hr (jks@fer.hr), 25. Lip. 2010. u 13:29 sati



Verzija za printanje   za tiskati


upomoc
foot_4