Edge-Based Standing-Water Detection via FSM-Guided Tiering and Multi-Model Consensus

TL;DR

This paper introduces an edge computing system using FSM-guided tiering and multi-model consensus for accurate, energy-efficient standing-water detection in agriculture, adaptable to connectivity and compute constraints.

Contribution

It presents a novel deployed architecture combining adaptive inference tiering, sensor fusion, and multi-model ensemble for improved flood detection in agricultural fields.

Findings

Improves flood detection accuracy over static baselines.

Reduces energy consumption compared to always-offload policies.

Maintains bounded tail latency in real-world deployment.

Abstract

Standing water in agricultural fields threatens vehicle mobility and crop health. This paper presents a deployed edge architecture for standing-water detection using Raspberry-Pi-class devices with optional Jetson acceleration. Camera input and environmental sensors (humidity, pressure, temperature) are combined in a finite-state machine (FSM) that acts as the architectural decision engine. The FSM-guided control plane selects between local and offloaded inference tiers, trading accuracy, latency, and energy under intermittent connectivity and motion-dependent compute budgets. A multi-model YOLO ensemble provides image scores, while diurnal-baseline sensor fusion adjusts caution using environmental anomalies. All decisions are logged per frame, enabling bit-identical hardware-in-the-loop replays. Across ten configurations and sensor variants on identical field sequences with frame-level ground truth, we show that the combination of adaptive tiering, multi-model consensus, and diurnal sensor fusion improves flood-detection performance over static local baselines, uses less energy than a naive always-heavy offload policy, and maintains bounded tail latency in a real agricultural setting.