Edge-Optimized Vision-Language Models for Underground Infrastructure Assessment

2026-02-03

AI Summary

This work addresses the challenge of automatically generating human-readable defect summaries from visual inspections of underground infrastructure—such as drainage pipes and culverts—on resource-constrained edge devices. The authors propose a two-stage, end-to-end lightweight pipeline: first, an efficient defect segmentation model, RAPID-SCAN, with only 0.64M parameters achieves an F1-score of 0.834; second, a quantized and fine-tuned Phi-3.5 vision-language model produces domain-specific natural language summaries. This study presents the first integration of lightweight segmentation with an edge-optimized vision-language model, introduces the first dedicated dataset with human-verified descriptive annotations, and demonstrates real-time inference on a mobile robotic platform, significantly enhancing both the interpretability and deployment efficiency of intelligent infrastructure assessment systems.

Technology Category

• Computer Vision: Segmentation
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Large language models for search
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Autonomous inspection of underground infrastructure, such as sewer and culvert systems, is critical to public safety and urban sustainability. Although robotic platforms equipped with visual sensors can efficiently detect structural deficiencies, the automated generation of human-readable summaries from these detections remains a significant challenge, especially on resource-constrained edge devices. This paper presents a novel two-stage pipeline for end-to-end summarization of underground deficiencies, combining our lightweight RAPID-SCAN segmentation model with a fine-tuned Vision-Language Model (VLM) deployed on an edge computing platform. The first stage employs RAPID-SCAN (Resource-Aware Pipeline Inspection and Defect Segmentation using Compact Adaptive Network), achieving 0.834 F1-score with only 0.64M parameters for efficient defect segmentation. The second stage utilizes a fine-tuned Phi-3.5 VLM that generates concise, domain-specific summaries in natural language from the segmentation outputs. We introduce a curated dataset of inspection images with manually verified descriptions for VLM fine-tuning and evaluation. To enable real-time performance, we employ post-training quantization with hardware-specific optimization, achieving significant reductions in model size and inference latency without compromising summarization quality. We deploy and evaluate our complete pipeline on a mobile robotic platform, demonstrating its effectiveness in real-world inspection scenarios. Our results show the potential of edge-deployable integrated AI systems to bridge the gap between automated defect detection and actionable insights for infrastructure maintenance, paving the way for more scalable and autonomous inspection solutions.

Problem

• underground infrastructure
• defect summarization
• edge computing
• vision-language model
• autonomous inspection

Innovation

• Edge AI
• Vision-Language Model
• Lightweight Segmentation
• Post-training Quantization
• Autonomous Infrastructure Inspection