Two-Stage CNN-Based Wood Log Recognition

Wimmer, Georg; Schraml, Rudolf; Hofbauer, Heinz; Petutschnigg, Alexander; Uhl, Andreas

doi:10.1007/978-3-030-87007-2_9

Cited by 15 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…18 This opens up a new way for the research of target detection and speeds up the substantial progress of target detection.There are two main types of object detection algorithms. The two-stage network using R-CNN 19 as an example first generates the candidate regions, and then classifies and regress the candidate regions. Single-level networks represented by YOLO 15 and Single Shot MultiBox Detector (SSD) 20 directly classify and regression targets.…”

Section: Deep Learning Modelsmentioning

confidence: 99%

An image augmentation‐based ice monitoring method for safe navigation of polar ships

Liang,

Wang,

Zhao

et al. 2024

Quality & Reliability Eng

View full text Add to dashboard Cite

The navigation safety of polar ships depends on accurate monitoring of ice conditions along the route. Complex polar environments but scarce ice datasets pose challenges for deep learning‐based object detection methods. To address this issue, we propose an ice monitoring method based on polar environment adaptive image enhancement. This approach adaptively augments the ice dataset by simulating polar environments such as snowflakes and aurora to improve the training precision of ice detection models in harsh polar environments and meet the needs of safe navigation of polar ships. First, an image augmentation method based on randomly generated snowflake textures is proposed to address the difficulty of covering polar storm scenarios in existing ice datasets, which leads to weak generalization of ice monitoring models. Second, targeting the problem that the boundary between ice and background is confused by aurora phenomena, which severely reduces the ice monitoring accuracy, we propose an image augmentation method based on aurora simulations to improve the ice monitoring performance of trained models under aurora. Finally, an adaptive image augmentation strategy based on the brightness‐contrast threshold is proposed to optimize the snowflake density and aurora intensity in the augmented images to improve the discrimination of ice boundaries. Experimental results demonstrate the effectiveness of the proposed method, which improves the ice state detection accuracy from 0.640 to 0.950, thus providing a reliable guarantee for the safe navigation of polar ships.

show abstract

Section: Deep Learning Modelsmentioning

confidence: 99%

An image augmentation‐based ice monitoring method for safe navigation of polar ships

Liang,

Wang,

Zhao

et al. 2024

Quality & Reliability Eng

View full text Add to dashboard Cite

show abstract

“…In timber identification, convolutional neural networks (CNNs) are employed for crosssection (CS) image classification and feature extraction from timber log images. CNNs eliminate the need for pith position determination and rotational prealignment, performing comparably to traditional methods [65,178]. Various advanced neural networks, including U-Net, Mask R-CNN, RefineNet, and SegNet, are compared for CS segmentation, with U-Net excelling on small datasets and RefineNet on large datasets, while SegNet and Mask R-CNN show varied performance [33].…”

Section: Machine Learning and Computer Visionmentioning

confidence: 99%

Timber Traceability and Sustainable Transportation Management: A Review of Technologies and Procedures

Elias

2024

FWIAFE

View full text Add to dashboard Cite

There has been considerable research on sustainable forest management due to its importance in ensuring the long-term health of the forests and its industries. Traceability is an important tool to ensure that the wood and wood-based products are produced in a legal, sustainable, and ethical manner. Therefore, various technologies were implemented within the supply chain to monitor and trace the wood with the aim of fulfilling the traceability objectives. Using a systematic literature review, this paper provides a comprehensive state-of-the-art on the technologies and procedures used in timber traceability and transportation management. It debates traceability tradition and advanced methods such as smart marking, QR (Quick Response) codes, DNA fingerprinting, smartphone apps, RFID (Radio Frequency Identification), machine learning, and computer vision since these technologies enable the integrity of the supply chain by documenting the source of wood and following up on the wood in all the stages, beginning from the standing tree until the final customer. The paper also reviews the advancements in wood transportation management systems, including spatial databases, GPS (Global Positioning System), and fleet management systems, which ultimately lead to real-time monitoring and optimisation of transportation routes, leading to improved efficiency and minimal environmental impact. The review results acknowledge that financial constraints, infrastructure limitations, data management uncertainties, acceptance and compliance issues, and stakeholder commitment are still challenges to implementing traceability technology in the forestry sector. Moreover, this review not only highlights how traceability systems promote responsible forestry practices, ensure sustainable timber sourcing, and develop supply chain management, but also the advantages of utilising these technological advances at economic, social, and environmental levels.

show abstract

“…The superiority of convolutional neural networks for the identification of log cross-sections over methods adapted from fingerprint or iris recognition techniques was demonstrated in the comparative study by Wimmer et al (2021a).…”

Section: Reuse Potential and Limitsmentioning

confidence: 99%

“…Their main objective was to trace log ends from the forest to the sawmill (Schraml et al 2015). More recently, neural networks were used to perform this task (Wimmer et al 2021a). A second application is to estimate the pith location.…”

Section: Introductionmentioning

confidence: 99%

Traceability and quality assessment of Norway spruce (Picea abies (L.) H.Karst.) logs: the TreeTrace_spruce database

Longuetaud

Schraml

Mothe

et al. 2023

Annals of Forest Science

Self Cite

View full text Add to dashboard Cite

Key message The TreeTrace_spruce database contains images and measurements of 100 Norway spruce (Picea abies (L.) H.Karst.) logs from Northeastern France, each about 4.5 m long. The image database includes RGB images of large and small ends of the logs and hyperspectral and computed tomography (CT) images of wood discs sampled at both log ends. The 100 logs were also fully X-ray scanned with a CT device for roundwoods and their top surface was scanned with a terrestrial LiDAR device. The measurements performed on discs include wood local density, growth ring widths and pith location. This database is complementary to another one (TreeTrace_Douglas) resulting from the same ANR project TreeTrace, but if the objectives are similar, the protocols and conditions of acquisition are not the same for these two databases. TreeTrace_spruce dataset is available at https://doi.org/10.57745/WKLTJI and associated metadata are available at https://metadata-afs.nancy.inra.fr/geonetwork/srv/fre/catalog.search#/metadata/cffee2f1-18e1-4b53-9f5b-6cc4c66f1cb8.

show abstract

Two-Stage CNN-Based Wood Log Recognition

Cited by 15 publications

References 14 publications

An image augmentation‐based ice monitoring method for safe navigation of polar ships

An image augmentation‐based ice monitoring method for safe navigation of polar ships

Timber Traceability and Sustainable Transportation Management: A Review of Technologies and Procedures

Traceability and quality assessment of Norway spruce (Picea abies (L.) H.Karst.) logs: the TreeTrace_spruce database

Contact Info

Product

Resources

About