mmAnomaly: Leveraging Visual Context for Robust Anomaly Detection in the Non-Visual World with mmWave Radar

View PDF HTML (experimental)

Abstract:mmWave radar enables human sensing in non-visual scenarios-e.g., through clothing or certain types of walls-where traditional cameras fail due to occlusion or privacy limitations. However, robust anomaly detection with mmWave remains challenging, as signal reflections are influenced by material properties, clutter, and multipath interference, producing complex, non-Gaussian distortions. Existing methods lack contextual awareness and misclassify benign signal variations as anomalies. We present mmAnomaly, a multi-modal anomaly detection framework that combines mmWave radar with RGBD input to incorporate visual context. Our system extracts semantic cues-such as scene geometry and material properties-using a fast ResNet-based classifier, and uses a conditional latent diffusion model to synthesize the expected mmWave spectrum for the given visual context. A dual-input comparison module then identifies spatial deviations between real and generated spectra to localize anomalies. We evaluate mmAnomaly on two multi-modal datasets across three applications: concealed weapon localization, through-wall intruder localization, and through-wall fall localization. The system achieves up to 94% F1 score and sub-meter localization error, demonstrating robust generalization across clothing, occlusions, and cluttered environments. These results establish mmAnomaly as an accurate and interpretable framework for context-aware anomaly detection in mmWave sensing.

Comments: Accepted at the 24th ACM/IEEE International Conference on Embedded Artificial Intelligence and Sensing Systems (SenSys 2026)

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Signal Processing (eess.SP)

Cite as: arXiv:2604.00382 [cs.CV]

(or arXiv:2604.00382v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2604.00382

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Tarik Reza Toha [view email] [v1] Wed, 1 Apr 2026 02:07:57 UTC (2,001 KB)