Survey of Quantization Techniques for On-Device Vision-based Crack Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Yuxuan, Martinez-Rau, Luciano Sebastian, Vu, Quynh Nguyen Phuong, Oelmann, Bengt, Bader, Sebastian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908458460119040
author Zhang, Yuxuan
Martinez-Rau, Luciano Sebastian
Vu, Quynh Nguyen Phuong
Oelmann, Bengt
Bader, Sebastian
author_facet Zhang, Yuxuan
Martinez-Rau, Luciano Sebastian
Vu, Quynh Nguyen Phuong
Oelmann, Bengt
Bader, Sebastian
contents Structural Health Monitoring (SHM) ensures the safety and longevity of infrastructure by enabling timely damage detection. Vision-based crack detection, combined with UAVs, addresses the limitations of traditional sensor-based SHM methods but requires the deployment of efficient deep learning models on resource-constrained devices. This study evaluates two lightweight convolutional neural network models, MobileNetV1x0.25 and MobileNetV2x0.5, across TensorFlow, PyTorch, and Open Neural Network Exchange platforms using three quantization techniques: dynamic quantization, post-training quantization (PTQ), and quantization-aware training (QAT). Results show that QAT consistently achieves near-floating-point accuracy, such as an F1-score of 0.8376 for MBNV2x0.5 with Torch-QAT, while maintaining efficient resource usage. PTQ significantly reduces memory and energy consumption but suffers from accuracy loss, particularly in TensorFlow. Dynamic quantization preserves accuracy but faces deployment challenges on PyTorch. By leveraging QAT, this work enables real-time, low-power crack detection on UAVs, enhancing safety, scalability, and cost-efficiency in SHM applications, while providing insights into balancing accuracy and efficiency across different platforms for autonomous inspections.
format Preprint
id arxiv_https___arxiv_org_abs_2502_02269
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Survey of Quantization Techniques for On-Device Vision-based Crack Detection
Zhang, Yuxuan
Martinez-Rau, Luciano Sebastian
Vu, Quynh Nguyen Phuong
Oelmann, Bengt
Bader, Sebastian
Computer Vision and Pattern Recognition
Machine Learning
Structural Health Monitoring (SHM) ensures the safety and longevity of infrastructure by enabling timely damage detection. Vision-based crack detection, combined with UAVs, addresses the limitations of traditional sensor-based SHM methods but requires the deployment of efficient deep learning models on resource-constrained devices. This study evaluates two lightweight convolutional neural network models, MobileNetV1x0.25 and MobileNetV2x0.5, across TensorFlow, PyTorch, and Open Neural Network Exchange platforms using three quantization techniques: dynamic quantization, post-training quantization (PTQ), and quantization-aware training (QAT). Results show that QAT consistently achieves near-floating-point accuracy, such as an F1-score of 0.8376 for MBNV2x0.5 with Torch-QAT, while maintaining efficient resource usage. PTQ significantly reduces memory and energy consumption but suffers from accuracy loss, particularly in TensorFlow. Dynamic quantization preserves accuracy but faces deployment challenges on PyTorch. By leveraging QAT, this work enables real-time, low-power crack detection on UAVs, enhancing safety, scalability, and cost-efficiency in SHM applications, while providing insights into balancing accuracy and efficiency across different platforms for autonomous inspections.
title Survey of Quantization Techniques for On-Device Vision-based Crack Detection
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2502.02269