Clean-Reference Streaming Detection of Lens Occlusion and Photometric Transitions for Camera Tamper Monitoring

2026-07-16

AI Summary

This work addresses the vulnerability of surveillance cameras to lens occlusion and abrupt illumination changes, which often render captured data unusable and necessitate real-time integrity monitoring with low false-positive rates and diagnostic capability. The authors propose a lightweight streaming detector that compares luminance and local gradient statistics within a sliding window against a clean reference frame. By integrating coarse-grid structured light rejection, rapid brightness variation suppression, and a state-machine decision mechanism, the method enables precise, single-instance alerts for anomalies. A consistency rule based on clean references and a false positive rate (FPR) constraint are introduced to substantially reduce false alarms under complex lighting conditions. Experiments demonstrate an F1 score of 0.800 and balanced accuracy of 0.822 across 320 controlled sequences; under a 5% FPR budget in public audits, it achieves the best partial AUC and reports zero false positives over 9.09 camera-hours of negative testing.

Abstract

A surveillance camera is an image sensor whose silent physical degradation invalidates every downstream consumer of its data. In-situ integrity alarms for such vision sensors require low false-alarm rates, bounded computation, and diagnosable behavior under nuisance illumination changes. This paper studies a deliberately narrow streaming integrity monitor for two low-cost sensor-fault signatures: texture-collapsing lens occlusion and abrupt photometric scene transition. The detector compares sampled luminance and local-gradient statistics with a clean-only sliding reference, applies coarse-grid structured-light rejection and mode/rapid-brightness suppression, and emits at most one notification per tamper episode. We formalize the decision predicates and derive a consistency rule for when rapid-brightness suppression makes the scene-transition path unreachable. On 320 in-scope controlled sequences, the default state machine attains 0.800 F1 and 0.822 balanced accuracy (significantly better paired correctness than the strongest baseline, though the F1 margin is not statistically resolved); on a magnitude-swept public audit it attains the highest partial AUC under a 5\% false-alarm budget, and a separate extended-stress FPR-constrained sweep reaches 0.925 recall at 0.025 false-positive rate. Public Xiph, Bremen IoT, and UHCTD diagnostics show the fixed predicates preserve low false alarms while recall concentrates inside the declared envelope (UHCTD in-scope covered recall 0.667 versus 0.016 out of scope), and a 9.09-camera-hour verified-negative public audit records zero false alarms. The method is best interpreted as an auditable sensor-health subsystem rather than a universal camera-tamper classifier.

Problem

• camera tamper monitoring
• lens occlusion
• photometric transitions
• sensor integrity
• false-alarm rate

Innovation

• streaming integrity monitoring
• lens occlusion detection
• photometric transition
• clean-reference sliding window
• false-alarm suppression