Boosting AI Reliability with an FSM-Driven Streaming Inference Pipeline: An Industrial Case
This addresses reliability issues for industrial AI applications, particularly in construction monitoring, but is incremental as it builds on existing object detection with added FSM guidance.
The paper tackles the problem of AI unreliability in industrial applications by proposing a streaming inference pipeline that combines object detection with a Finite State Machine to incorporate prior knowledge, achieving superior performance and robustness on a real-world excavator workload counting task with over 7,000 images and 300 workloads.
The widespread adoption of AI in industry is often hampered by its limited robustness when faced with scenarios absent from training data, leading to prediction bias and vulnerabilities. To address this, we propose a novel streaming inference pipeline that enhances data-driven models by explicitly incorporating prior knowledge. This paper presents the work on an industrial AI application that automatically counts excavator workloads from surveillance videos. Our approach integrates an object detection model with a Finite State Machine (FSM), which encodes knowledge of operational scenarios to guide and correct the AI's predictions on streaming data. In experiments on a real-world dataset of over 7,000 images from 12 site videos, encompassing more than 300 excavator workloads, our method demonstrates superior performance and greater robustness compared to the original solution based on manual heuristic rules. We will release the code at https://github.com/thulab/video-streamling-inference-pipeline.