Detection of Toy Soldiers Taken from a Bird’s Perspective Using Convolutional Neural Networks (CROSBI ID 683399)
Prilog sa skupa u časopisu | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Sambolek, Saša ; Ivašić-Kos, Marina
engleski
Detection of Toy Soldiers Taken from a Bird’s Perspective Using Convolutional Neural Networks
This paper describes the use of two different deep-learning approaches for object detection to recognize a toy soldier. We use recordings of toy soldiers in different poses under different scenarios to simulate the appearance of persons on footage taken by drones. Recordings from a bird’s eye view are today widely used in the search for missing persons in non-urban areas, border control, animal movement control, and the like. We have compared the single-shot multi-box detector (SSD) with the MobileNet or Inception V2 as a backbone, SSDLite with MobileNet and Faster R- CNN combined with Inception V2 and ResNet50. The results show that Faster R-CNN detects small objects such as toy soldiers more successfully than SSD, and the training time of Faster R-CNN is much shorter than that of SSD.
Object detectors ; SSD ; Faster R-CNN
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
13-26.
2019.
nije evidentirano
objavljeno
10.1007/978-3-030-33110-8_2
Podaci o matičnoj publikaciji
Communications in computer and information science
Gievska, S. ; Madjarov, G.
Springer
978-3-030-33109-2
1865-0929
Podaci o skupu
11th International Conference ICT Innovations
poster
17.10.2019-19.10.2019
Ohrid, Sjeverna Makedonija
Povezanost rada
Informacijske i komunikacijske znanosti, Računarstvo