Scholarlink

<p>This study presents three algorithmic innovations aimed at optimizing Convolutional Neural Network architectures for automated defect detection in pallet rack inspection scenarios. First, a domain-specific <i>Augmentation Algorithm</i> is introduced to expand the training dataset, mitigate overfitting, and enhance the model’s generalization by emphasizing critical visual features associated with structural defects. Second, a guided <i>CNN Development Mechanism</i> facilitates architectural optimization by systematically refining filter sizes, neuron counts, and convolutional block configurations, enabling high performance with reduced parameter overhead. Third, the proposed <i>PalletDetect Module (PD-M)</i> enhances computational efficiency by adaptively refining feature representations at the input tensor level, reducing complexity while preserving discriminative capacity. These algorithms collectively produce <b>PDNet</b>, a compact CNN that enables real-time pallet racking inspection on resource-constrained edge devices. PDNet achieves an accuracy of 92.07%, with a computational complexity of only 32.31 million multiply–accumulate operations (MMAC) and a compact memory footprint of 31.36&#xa0;MB. Compared to modern lightweight CNNs such as MobileNetV3 and ShuffleNetV2, PDNet offers a superior balance between accuracy, speed, and computational efficiency, demonstrating its potential for real-time industrial inspection applications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

PDNet: a lightweight attention-guided CNN for efficient pallet racking defect detection on edge devices

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月4日

查看全文
  • Rahima Khanam,
  • Muhammad Hussain,
  • Richard Hill

摘要

This study presents three algorithmic innovations aimed at optimizing Convolutional Neural Network architectures for automated defect detection in pallet rack inspection scenarios. First, a domain-specific Augmentation Algorithm is introduced to expand the training dataset, mitigate overfitting, and enhance the model’s generalization by emphasizing critical visual features associated with structural defects. Second, a guided CNN Development Mechanism facilitates architectural optimization by systematically refining filter sizes, neuron counts, and convolutional block configurations, enabling high performance with reduced parameter overhead. Third, the proposed PalletDetect Module (PD-M) enhances computational efficiency by adaptively refining feature representations at the input tensor level, reducing complexity while preserving discriminative capacity. These algorithms collectively produce PDNet, a compact CNN that enables real-time pallet racking inspection on resource-constrained edge devices. PDNet achieves an accuracy of 92.07%, with a computational complexity of only 32.31 million multiply–accumulate operations (MMAC) and a compact memory footprint of 31.36 MB. Compared to modern lightweight CNNs such as MobileNetV3 and ShuffleNetV2, PDNet offers a superior balance between accuracy, speed, and computational efficiency, demonstrating its potential for real-time industrial inspection applications.