RISE: Real-time Image Processing for Spectral Energy Detection and Localization

TL;DR

RISE is a software system that enables real-time spectrum sensing by treating spectrograms as images and applying image processing techniques, achieving high detection accuracy and low latency for spectrum sharing.

Contribution

The paper introduces RISE, a novel real-time spectrum sensing system that combines image processing methods with multi-threaded architecture for efficient signal detection and localization.

Findings

Achieves 80.42% detection probability at IoU 0.4

Sustains 3.2 Gbps input rate for 100 MHz bandwidth

Outperforms Searchlight and DeepRadar in latency and IoU

Abstract

Energy detection is widely used for spectrum sensing, but accurately localizing the time and frequency occupation of signals in real-time for efficient spectrum sharing remains challenging. To address this challenge, we present RISE, a software-based spectrum sensing system designed for real-time signal detection and localization. RISE treats time-frequency spectrum plots as images and applies adaptive thresholding, morphological operations, and connected component labeling with a multi-threaded architecture. We evaluate RISE using both synthetic data and controlled over-the-air (OTA) experiments across diverse signal types. Results show that RISE satisfies real-time latency constraints while achieving a probability of detection of 80.42% at an intersection-over-union (IoU) threshold of 0.4. RISE sustains a raw I/Q input rate of 3.2 Gbps for 100 MHz bandwidth sensing with time and frequency resolutions of 10.24 us and 97.6 kHz, respectively. Compared to Searchlight, a representative energy-based method, RISE achieves 20.51x lower latency and 22.31% higher IoU. Compared to machine learning baselines, RISE improves IoU by 56.02% over DeepRadar while meeting the real-time deadline, which a GPU-accelerated U-Net exceeds by 213.38x.