Dataset: filename, 68.46 KB Access Condition: Open access Description: Annotated thermal images for class Person (English)
Please login to the repository to save this object to your list.
Cite this document
Ivašić Kos, M., Krišto, M. & Pobar, M. (2020). UNIRI - Thermal image dataset - UNIRI-TID [Data set]. https://urn.nsk.hr/urn:nbn:hr:195:416494.
Ivašić Kos, Marina, et al. UNIRI - Thermal image dataset - UNIRI-TID. Odjel za informatiku Sveučilišta u Rijeci, 2020. 13 Nov 2024. https://urn.nsk.hr/urn:nbn:hr:195:416494.
Ivašić Kos, Marina, Mate Krišto, and Miran Pobar. 2020. UNIRI - Thermal image dataset - UNIRI-TID. Odjel za informatiku Sveučilišta u Rijeci. https://urn.nsk.hr/urn:nbn:hr:195:416494.
Ivašić Kos, M., Krišto, M. and Pobar, M. 2020. UNIRI - Thermal image dataset - UNIRI-TID. Odjel za informatiku Sveučilišta u Rijeci. [Online]. [Accessed 13 November 2024]. Available from: https://urn.nsk.hr/urn:nbn:hr:195:416494.
Ivašić Kos M, Krišto M, Pobar M. UNIRI - Thermal image dataset - UNIRI-TID. [Internet]. Odjel za informatiku Sveučilišta u Rijeci: PGŽ, Rijeka, HR; 2020, [cited 2024 November 13] Available from: https://urn.nsk.hr/urn:nbn:hr:195:416494.
M. Ivašić Kos, M. Krišto and M. Pobar, UNIRI - Thermal image dataset - UNIRI-TID, Odjel za informatiku Sveučilišta u Rijeci, 2020. Accessed on: Nov 13, 2024. Available: https://urn.nsk.hr/urn:nbn:hr:195:416494.
The dataset contains thermal images extracted from videos that simulate illegal movements around the border and in protected areas. Videos are recorded at night in clear weather, rain, and in the fog, at different ranges, and with different movement types – running, walking, and sneaking.
From all recordings, about 20 minutes of material from the clear weather scenario, 13 minutes from the fog scenario, and about 15 minutes from rainy weather were selected for further processing and frames extracted from the video. Of all the frames, 6,111 were selected to include different weather conditions and were manually annotated. Due to different weather conditions, the set contained 2663 frames taken in clear weather conditions, 1,135 frames of fog and 2,313 rain frames.
Number: IP-2016-06-8345 Title (english): Automatic recognition of actions and activities in multimedia content from the sports domain Acronym: RAASS Leader: izv. prof. dr. sc. Marina Ivašić-Kos Jurisdiction: Croatia
Project
Number: uniri-drustv-18-222 1385 Title (croatian): Automatsko raspoznavanje sportskih tehnika kod mladih sportaša i rekreativaca u svrhu usvajanja motoričkih vještina i usavršavanje stila Leader: Marina Ivašić-Kos Jurisdiction: Croatia Funding stream: UNIRI projekti