Abstract:
Nowadays, there is no place where security cameras (CCTV) are not used. Security cameras play a huge role in solving criminal cases. However, a lot of time is spent examining these camera recordings. This situation causes incidents not to be resolved and delays. This delay can cause many problems. Software is needed to help analyze videos so that incidents can be resolved faster. To meet this need, studies are being carried out on software that will automatically cut unnecessary parts of the videos and present only the important moments in summary form. These studies aim to make the incident easier to solve and to resolve the incident more quickly by removing unnecessary information from the videos. This study aims to summarize security camera recordings with machine learning, using efficient algorithms that can work on devices with low processing power such as embedded systems. Within the scope of the study, an experimental environment was created by installing a security camera system. Fast and effective video summarization algorithms have been developed on videos collected in different scenarios. New approaches called hopscotch and lens algorithms have been introduced for video processing. These approaches are aimed to obtain rapid results by applying them to security camera videos. It is thought that the developed video summarization approaches will lead to the creation of applicable prototypes on embedded cards such as Raspberry Pi. Real-time results were obtained with our approaches applied to images.
