FED-AT-VIDEO Nets—A Federated Capsule – Self Gated Learning Architecture For The Multi-View Video Summarization Technique

The Visual data collected from a single or the multi-view security camera has exponentially increased. Achieving efficient video summarization has become a vital challenge for constructing video analytics architecture. The effective techniques like video summarising are needed to minimize redundancy and guarantee that only the important facts are presented out of this enormous volume of data. Moreover, these videos contain private information, and security against different intruders has also added fuel to the existing challenges. In the recent years, numerous architectures evolved to achieve a better and more secure Multi-View Summarization (MVS) techniques that aid in better video analytics. Unfortunately, these existing architectures need an illuminated research to eradicate the aforementioned challenges. In this article, Federated Deep Gated Attention Architecture (FDGAA) is proposed for securing MVS by organizing the computing and networking resources of cloud and edge cameras collectively. The proposed architecture is a three-tier framework precisely described as 1) Video Collection Unit (VCU) that collects the videos from the different views of the camera installed. 2) Distributed Training Network (DTN) which consists of federated learning Self-Attention Saliency Gated Recurrent Units (SAS-GRU) in which the training is collaboratively shared among the edges while maintaining video data privacy. 3) Finally the extracted deep features are summarized in the cloud for processing. Using various datasets and NVIDIA Nano Boards as edge nodes, the substantial research is conducted to develop the Google Federated TensorFlow Libraries-based federated learning architecture. The performance was compared with other deep learning-based MVS systems to demonstrate the proposed framework's superiority over the state-of-the-art approaches, the experimental evaluation confirms the superior performance of the suggested model.