Scholarlink

<p>Manual grading of round timber is time-consuming and inconsistent, while many automated systems still output opaque quality labels that are difficult to verify against European standards. We present and validate a <i>standards-aligned semantic segmentation dataset</i> of spruce (<i>Picea abies</i>) logs designed to support transparent, rule-based grading. Using close-range photogrammetry, we recorded 1,875 logs and rendered three orthorectified images per log (two end faces, one mantle), yielding 5,625 images. Fourteen grading-relevant features, defined from EN&#xa0;844 terminology and EN&#xa0;1309-3 measurement rules, were annotated by multiple certified graders in a consensus workflow that produces per-pixel confidence. The dataset comprises 17,584 masks with 96,964 connected components and a mean area-weighted pixel-confidence of 91.4%. Reliability (test–retest and split-half), train–test similarity, and distributional realism were quantified from masks alone. Object counts are well described by zero-truncated Conway–Maxwell–Poisson laws, linear sizes by shifted log-normal distributions and shape as well as fractional-area measures by skew exponential power models. Median Kolmogorov–Smirnov and normalized Earth Mover’s Distance values indicate temporal stability and only modest train–test drift. Because mask geometry follows EN&#xa0;1309-3 clauses, segmentation outputs map directly to EN&#xa0;1927-1 decision expressions, enabling transparent acceptance checks. The dataset and analyses support explainable, standards-aligned automation of round timber grading and provide a reproducible basis for benchmarking semantic segmentation models in wood quality inspection.</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

Towards standards-aligned round-timber grading: validation of a semantic segmentation dataset

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月21日

查看全文
  • Lukas Bednar,
  • Filip Hendrichovsky,
  • Alice Motschi,
  • Daniel Soukup,
  • Pauline Meyer-Heye

摘要

Manual grading of round timber is time-consuming and inconsistent, while many automated systems still output opaque quality labels that are difficult to verify against European standards. We present and validate a standards-aligned semantic segmentation dataset of spruce (Picea abies) logs designed to support transparent, rule-based grading. Using close-range photogrammetry, we recorded 1,875 logs and rendered three orthorectified images per log (two end faces, one mantle), yielding 5,625 images. Fourteen grading-relevant features, defined from EN 844 terminology and EN 1309-3 measurement rules, were annotated by multiple certified graders in a consensus workflow that produces per-pixel confidence. The dataset comprises 17,584 masks with 96,964 connected components and a mean area-weighted pixel-confidence of 91.4%. Reliability (test–retest and split-half), train–test similarity, and distributional realism were quantified from masks alone. Object counts are well described by zero-truncated Conway–Maxwell–Poisson laws, linear sizes by shifted log-normal distributions and shape as well as fractional-area measures by skew exponential power models. Median Kolmogorov–Smirnov and normalized Earth Mover’s Distance values indicate temporal stability and only modest train–test drift. Because mask geometry follows EN 1309-3 clauses, segmentation outputs map directly to EN 1927-1 decision expressions, enabling transparent acceptance checks. The dataset and analyses support explainable, standards-aligned automation of round timber grading and provide a reproducible basis for benchmarking semantic segmentation models in wood quality inspection.