Image Captioning for Spatially Rotated Images in Video Surveillance Applications Using Neural Networks

Autor:	M Nivedita, Asnath Victy Phamila Y
Rok vydání:	2021
Předmět:	Artificial Intelligence Control and Systems Engineering ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Software Information Systems
Zdroj:	International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems. 29:193-209
ISSN:	1793-6411 0218-4885
Popis:	Video Surveillance has become an essential tool in the Security industry because of the sophisticated and fool-proof technology. Recent developments in image recognition and captioning have enabled us to adopt these technologies in the field of video surveillance. The biggest problem in image captioning is that it is variant on the rotation angle of the image. Different angles of the same image generate different captions. We aim to address and eliminate the rotation variance of image captioning. We have implemented a custom image rotation network using a Convolutional Neural Network (CNN). The input image is rotated to the original angle using this network and passed on to the image captioning. The caption of the image is generated and sent to the user for the situation analysis.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::9bfe459ba9c0399d272b0a5640f6b403 https://doi.org/10.1142/s0218488521400110 Zobrazit plný text záznamu