FCM-RT: Real-Time Feature Coding for Machines

Abstract:

As numerous edge devices start implementing intelligent components, the challenges of energy consumption, bandwidth efficiency, and privacy gain significance. One proposed solution relies on the paradigm of split inference, which optimizes the delegation of the computational load between edge and remote devices. We developed and implemented the standard-compliant split inference system with an encoder and decoder capable of real-time streaming and processing. Our system outperforms state-of-the-art video compression implementations by an average of 83% bitrate reduction, while preserving privacy. We demonstrate the system's real-time performance on consumer devices, with interactive visualizations of object detection and segmentation, incorporating real-time metrics. Demo video:  https://youtu.be/bmCbUo_ZWWU

Authors:

Perera Ashan, Eimon Md Eimran Hossain, Merlos Juan. Adzic Velibor, Kalva Hari and Furht Borko

Conference / Journal

InProceedings of the 33rd ACM International Conference on Multimedia 2025 Oct 27 (pp. 13525-13527)