Night vision greatly affects the efficiency of our vision which we come across daily. Research work on night vision is very essential to solve the social problems in the present scenario, but there is still a lack of database to do research on night vision using deep-learning technique. Due to poor light the object detection is a very tedious process. To overcome such hardships, we collected the night vision datasets under various conditions. This work is about scene understanding during night-time with IR-cameras. The feature extraction from night videos is mainly affected by wavelength or the intensity of IR, illumination and distance factor. We proposed a novel algorithm exclusively for object detection during night time and we compare our algorithm with various yolo versions and we found that our night vision yolo performs better in detecting various objects like Male, Female, Car, bike, Van, Cycle during night time.
CITATION STYLE
Anandha Murugan, R., Sathyabama, B., Sam Joshuva, S., Kiran, S., & krishna, N. (2020). Scene Understanding in Night-Time Using SSAN Dataset. In Communications in Computer and Information Science (Vol. 1249, pp. 558–568). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-15-8697-2_52
Mendeley helps you to discover research relevant for your work.