Data Optimization Using Edge AI: A Framework for Efficient Real-Time Analytics - A Case Study of IndoAI AI Camera
Abstract: In the era of rapidly expanding smart surveillance systems, AI cameras are pivotal for real-time analytics in applications ranging from security to industrial automation. However, with the increasing number of connected cameras, there is an immense need for efficient data management, especially concerning memory usage, data transmission and cloud dependency. This article explores the integration of Edge Technology in AI surveillance systems, specifically focusing on the optimization of data generated by AI cameras. IndoAI?s AI cameras, equipped with real-time facial recognition, fire detection and vehicle number plate detection, produce large volumes of data that necessitate a scalable, efficient solution. This paper explores a data optimization framework using Edge AI, where data is processed closer to its source- on the AI camera itself - thereby minimizing transmission and reducing reliance on cloud services. The framework leverages edge processing techniques, intelligent compression algorithms and inter-camera communication to reduce redundant data, optimize real-time analytics and ensure efficient network performance. The proposed system is inspired by data optimization techniques used in OTT streaming platforms, particularly in adaptive bitrate streaming, which dynamically adjusts content quality based on bandwidth availability.
Keywords: AI Camera, IndoAI, Data Analytics, Edge AI, Appization, Custom AI Models
How to Cite?: Vivek Gujar, "Data Optimization Using Edge AI: A Framework for Efficient Real-Time Analytics - A Case Study of IndoAI AI Camera", Volume 13 Issue 10, October 2024, International Journal of Science and Research (IJSR), Pages: 577-582, https://www.ijsr.net/getabstract.php?paperid=SR241006200634, DOI: https://dx.doi.org/10.21275/SR241006200634