Cascading multi-agent anomaly detection in surveillance systems via vision-language models and embedding-based classification
This work addresses the challenge of reconciling real-time performance with semantic interpretability in surveillance systems, representing an incremental improvement by combining existing paradigms into a more efficient and scalable architecture.
The paper tackled the problem of intelligent anomaly detection in dynamic visual environments by introducing a cascading multi-agent framework that unifies reconstruction-based models, object detectors, and vision-language systems, achieving a threefold reduction in latency compared to direct vision-language inference while maintaining high perceptual fidelity (PSNR = 38.3 dB, SSIM = 0.965).
Intelligent anomaly detection in dynamic visual environments requires reconciling real-time performance with semantic interpretability. Conventional approaches address only fragments of this challenge. Reconstruction-based models capture low-level deviations without contextual reasoning, object detectors provide speed but limited semantics, and large vision-language systems deliver interpretability at prohibitive computational cost. This work introduces a cascading multi-agent framework that unifies these complementary paradigms into a coherent and interpretable architecture. Early modules perform reconstruction-gated filtering and object-level assessment, while higher-level reasoning agents are selectively invoked to interpret semantically ambiguous events. The system employs adaptive escalation thresholds and a publish-subscribe communication backbone, enabling asynchronous coordination and scalable deployment across heterogeneous hardware. Extensive evaluation on large-scale monitoring data demonstrates that the proposed cascade achieves a threefold reduction in latency compared to direct vision-language inference, while maintaining high perceptual fidelity (PSNR = 38.3 dB, SSIM = 0.965) and consistent semantic labeling. The framework advances beyond conventional detection pipelines by combining early-exit efficiency, adaptive multi-agent reasoning, and explainable anomaly attribution, establishing a reproducible and energy-efficient foundation for scalable intelligent visual monitoring.