Pith Estimation on Tree Log End Images

Decelle, Rémi; Ngo, Phuc; Debled-Rennesson, Isabelle; Mothe, Frédéric; Longuetaud, Fleur

doi:10.1007/978-3-030-76423-4_7

Cited by 3 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To benchmark the proposed framework's performance and evaluate its generalizability, test datasets were also used. These test datasets included 211 cross-sectional images of a parawood log from the same dataset used for training and 65 cross-sectional images of a Douglas fir log from a separate dataset [39]. The Douglas fir log dataset was specifically chosen to test the framework's ability to handle wood logs with different features compared to the training dataset.…”

Section: Methodsmentioning

confidence: 99%

A Framework to Estimate the Key Point Within an Object Based on a Deep Learning Object Detection

Kurdthongmee¹,

Suwannarat²,

Wattanapanich³

2023

HighTech. Innov. J.

View full text Add to dashboard Cite

Automatic identification of key points within objects is crucial in various application domains. This paper presents a novel framework for accurately estimating the key point within an object by leveraging deep neural network-based object detection. The proposed framework is built upon a training dataset annotated with four non-overlapping bounding boxes, one of which shares a coordinate with the key point. These bounding boxes collectively cover the entire object, enabling automatic annotation if region annotations around the key point exist. The trained object detector is then utilized to generate detection results, which are subsequently post-processed to estimate the key point. To validate the effectiveness of the framework, experiments were conducted using two distinct datasets: cross-sectional images of a parawood log and pupil images. The experimental results demonstrate that our proposed framework surpasses previously proposed approaches in terms of precision, recall, F1-score, and other domain-specific metrics. The improvement in performance can be attributed to the unique annotation strategy and the fusion of object detection and key point estimation within a unified deep learning framework. The contribution of this study lies in introducing a novel framework for closely estimating key points within objects based on deep neural network-based object detection. By leveraging annotated training data and post-processing techniques, our approach achieves superior performance compared to existing methods. This work fills a critical gap in the field by integrating object detection and key point estimation, which has received limited attention in previous research. Our framework provides valuable insights and advancements in key point estimation techniques, offering potential applications in precise object analysis and understanding. Doi: 10.28991/HIJ-2023-04-01-08 Full Text: PDF

show abstract

Section: Methodsmentioning

confidence: 99%

A Framework to Estimate the Key Point Within an Object Based on a Deep Learning Object Detection

Kurdthongmee¹,

Suwannarat²,

Wattanapanich³

2023

HighTech. Innov. J.

View full text Add to dashboard Cite

show abstract

“…Nondestructive evaluation of wood is increasingly being used in forestry and forest products research, operations, and manufacturing (Ross and Pellerin 1994;Ross 2015;Schimleck et al 2019). Imaging is one of many nondestructive evaluation tools which has seen extensive use (Evans 1994;Evans et al 1999;Bucur 2003aBucur , 2003bDecellee et al 2019;Wright et al 2019). For example, a major industrial application of imaging is in lumber manufacturing facilities, where the shape and volume of logs is measured using high-resolution laser scanners after debarking (Thomas and Bennett 2014;Sauter et al 2019).…”

Section: Introductionmentioning

confidence: 99%

Image Analysis To Assess Wood Variability In Longleaf Pine Cross-Sectional Disks

Raut,

Dahlen

2023

WFS

View full text Add to dashboard Cite

Image analysis is an important method for rapidly measuring wood property variation, but it is infrequently applied to disks collected from forestry studies. The objective of this study was to compare image-estimated wood and bark volumes and diameters to reference measurements, and to extract more information from the images including the shape (out-of-round index, eccentric pith) and the amount and location of severe compression wood. A total of 1120 disks were cut from multiple height levels of 48 defect-free and 56 defect-containing (forking, excessive sweep, and ramicorn branching) longleaf pine (Pinus palustris) trees from 16 stands across Georgia (U.S.). Disks were machined on one transverse surface using a computer numeric controlled router to prepare a clean surface for imaging. Three images, one under white light, the second under blue light, and the third under blue light with a green longpass filter, were taken for each disk. Volumes and diameters estimated from images were in close agreement with reference methods. Linear models fitted as measured vs image volumes for wood and bark had coefficient of determination (R 2 ) values of .0.99 and 0.96. Linear models fitted as measured vs image diameters had R 2 values of .0.99. Out-of-round index and pith eccentricity values calculated from images showed a moderate positive correlation (R 5 0.43). Algorithms developed were able to correctly identify severe compression wood, but not mild-to-moderate compression wood. Severe compression wood was moderately correlated to out-of-round index (R 5 0.54) and pith eccentricity (R 5 0.48). More than 98% of the disks having severe compression wood came from defect-containing trees.

show abstract

Traceability and quality assessment of Douglas fir (Pseudotsuga menziesii (Mirb.) Franco) logs: the TreeTrace_Douglas database

Longuetaud

Pot

Mothe

et al. 2022

Annals of Forest Science

Self Cite

View full text Add to dashboard Cite

Key messageThe TreeTrace_Douglas database includes images and measurements at several stages of the processing of Douglas fir logs, from sawmill logyard to machine grading and destructive testing of boards, and is suitable for research on quality assessment and traceability. A total of 52 long logs, 156 short logs, 208 wood discs, and 346 boards were analyzed. The image data includes RGB images of log ends and board ends, RGB images and CT slices of strips, and a set of images of the boards (RGB, laser, and X-rays) obtained with an industrial board grading machine. The measurements include wood density, growth ring widths, pith and board location in the logs, heartwood and sapwood areas, mechanical properties of each board obtained by vibratory and static testing, and visual grading of the boards. Dataset is available at https://doi.org/10.15454/YUNEGL and associated metadata are available at https://metadata-afs.nancy.inra.fr/geonetwork/srv/fre/catalog.search#/metadata/d9eef6e4-f195-41f4-b6c2-2ab46adc637e.

show abstract

Pith Estimation on Tree Log End Images

Cited by 3 publications

References 23 publications

A Framework to Estimate the Key Point Within an Object Based on a Deep Learning Object Detection

A Framework to Estimate the Key Point Within an Object Based on a Deep Learning Object Detection

Image Analysis To Assess Wood Variability In Longleaf Pine Cross-Sectional Disks

Traceability and quality assessment of Douglas fir (Pseudotsuga menziesii (Mirb.) Franco) logs: the TreeTrace_Douglas database

Contact Info

Product

Resources

About