Pregled bibliografske jedinice broj: 1236831
Lightweight convolutional models for real-time dense prediction and forecasting
Lightweight convolutional models for real-time dense prediction and forecasting // AI2Future 2019
Zagreb, Hrvatska, 2019. (pozvano predavanje, nije recenziran, pp prezentacija, stručni)
CROSBI ID: 1236831 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Lightweight convolutional models for real-time dense prediction and forecasting
Autori
Siniša Šegvić
Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, pp prezentacija, stručni
Skup
AI2Future 2019
Mjesto i datum
Zagreb, Hrvatska, 10-11.11.2019
Vrsta sudjelovanja
Pozvano predavanje
Vrsta recenzije
Nije recenziran
Ključne riječi
computer vision
Sažetak
Recent advances in deep convolutional models have caused unprecedented growth of computer vision performance. This has opened exciting applications in the fields of smart vehicles and safe roads. Pixel-level image understanding can be achieved by associating each image window with a meaningful class such as ‘road’, ‘terrain’, ‘sidewalk’ or ‘person’. The resulting semantic map reveals the kind of surface terrain in front of the vehicle, and may be used to recover the traversability map required for motion planning. Depth can be recovered by predicting a disparity field which maximizes similarity between two stereo images.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
POVEZANOST RADA
Projekti:
HRZZ-IP-2013-11-1395 - Detekcija objekata više razreda za pametna vozila i sigurnije ceste (MULTICLOD) (Šegvić, Siniša, HRZZ ) ( CroRIS)
Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb
Profili:
Siniša Šegvić
(autor)
