Log pile measurement through 3D modeling

Kruglov, Artem; Evgenia, Shishko

doi:10.1109/tsp.2017.8075983

Cited by 7 publications

(7 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although this method attains some appealing results, the computational complexity is high and is affected by lighting conditions. In [20], the authors introduced an improved fast radial symmetry algorithm for log detection. The watershed algorithm and Stoer-Wagner algorithm were applied on the identified log edges to discard wrong targets and realize wood counting and segmentation.…”

Section: A Image Processing Methodsmentioning

confidence: 99%

Research on Volume Measurement of Logs Based on Embedded Application

Zheng

Zhang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Spurred by the worldwide concern for forest protection and the increased log sales, most countries have standardized log volume calculations to avoid excessive timber and protect buyers. However, log volume is currently manually measured, suffering from high labor costs, low measurement progress, and imposing significant measurement errors. Thus, automatically obtaining the volumetric data of logs is a convenient and quick solution. Therefore, this work proposes a Mask Region Convolutional Neural Networkbased (R-CNN) algorithm for Logs volume measurement, named Wood Mask (WM) R-CNN. Specifically, we employ the Res2Net structure as the backbone to obtain receptive fields that exceed the input feature size, thus improving our model's multi-scale information fusion ability. Additionally, WM R-CNN relies on the Path Aggregation Feature Pyramid Network's (PAFPN's) path enhancement structure, shortening the low-level feature map's propagation path and improving the wood contour segmentation accuracy. Extensive experiments on the Vehicle-mounted Dense Logs (VMDL) dataset demonstrate that WM R-CNN affords a highly appealing segmentation accuracy for small, medium, and large wood, improving the corresponding mAP indicators against current methods by 2.0%, 1.2%, and 4.4%, respectively. Furthermore, a quantitative method based on TensorRT compresses the proposed model to deploy the WM R-CNN to mobile embedded devices. However, to compensate for the quantization loss, we introduce the expansion convolution operation method to manipulate the mask map and control the volume calculation error of all logs on a vehicle within 1%. The experiments reveal that the proposed method offers an appealing performance, verifying the algorithm's effectiveness and implementation ability on mobile terminals.

show abstract

Section: A Image Processing Methodsmentioning

confidence: 99%

Research on Volume Measurement of Logs Based on Embedded Application

Zheng

Zhang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Chen Guanghua et al [11] proposed a fast detection algorithm for wood diameter grade based on binocular vision, which segmented the wood section area from the picture by dynamic threshold segmentation algorithm, and then used the least squares method to fit the wood contour to get the diameter-related parameters, which can measure the wood diameter grade at any distance, but the segmentation of the wood contour area is not accurate. In the literature [12][13][14], Kruglov A et al proposed three methods for wood testing: Firstly, the 3D modeling technology was used to obtain the 3D information of wood piles and combined with the mean clustering algorithm, Delaunay triangulation algorithm and watershed algorithm to carry out the wood volume measurement experiments, respectively, and the final measurement results were compared with the manual measurement results, with an average error of 9.2%. Secondly, an improved radially symmetric target detection algorithm is obtained by the combination of the Stoer-Wagner algorithm and the watershed algorithm, which can be adjusted to the contour of the detected wood section and accurately segment the target region.…”

Section: Figure 1 Manual Sortingmentioning

confidence: 99%

Automatic Sorting System for Wood Diameter Grades

Liu,

Kong,

Zheng

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Wood is one of the energy sources for sustainable development, which is closely related to our life. In the wood production process, it will be sorted according to different diameter grade is an essential link, at present the wood sorting work mainly rely on manual completion, not only low efficiency, high cost, and can not meet the automated era of production needs. In this paper, a wood diameter level automatic sorting system is designed, first of all, using computer vision technology to measure the diameter of the wood section in real time, then the diameter data is transmitted to the PLC control system, and finally the PLC control system pushes out the wood in the specified position, realizing the automated on-line sorting of wood. In addition, a wood diameter measurement method based on deep learning combined with binocular vision is proposed, which can quickly and accurately recognize the diameter of each piece of wood, and provides a solid foundation for the efficient performance of the automatic wood diameter grade sorting system. The experimental results show that the measurement method proposed in this paper has high robustness and the maximum error is within 5mm, which meets the accuracy requirements needed for sorting, and the sorting system can sort 10 pieces of wood per minute on average, which greatly improves the efficiency of wood sorting and reduces the labor workload and cost, and the research design is of great significance to the wood production and manufacturing industry.

show abstract

“…Using log pile photogrammetry, this algorithm deviated from the measurement manual piece-by-piece method by less than 9.2%. (Kruglov and Shishko 2017). Although it is possible to estimate conversion factors using this software, it was not the primary purpose of its development.…”

Section: Direct Estimationmentioning

confidence: 99%

“…The first 3D simulation model was successfully developed in 2017 to measure roundwood stacks' volume (Kruglov and Shishko 2017). However, that simulation model did not allow the analysis of the influencing parameters on the conversion factors.…”

Section: Application Of 3d Simulation Modelsmentioning

confidence: 99%

Estimation of conversion factors for wood stacks in landings and their influencing parameters: a comprehensive literature review for America and Europe

Miguel-Díez¹,

Purfürst²,

Acuña³

et al. 2023

Silva Fenn

View full text Add to dashboard Cite

In commercial transaction of stacked roundwood, the estimation of the stack net volume plays a key role. One generalized method to determine the net volume is using conversion factors that relate the gross and net volumes. In this literature review the developed methods to estimate the conversion factors as well as their influencing parameters were analyzed based on 153 references from America and Europe. According to the results, 48 different methods (including their variants) for estimating the conversion factors were developed. The newest methods enabled their accurate determination inexpensively, e.g., photo-optical methods or 3D simulation models. The analyzed references revealed that 30 parameters influence the conversion factors. Based on this comprehensive review, each stakeholder involved in the roundwood supply chain can know which method is used for estimating the conversion factors in the analyzed territories and which influencing parameters should be considered when purchasing roundwood in order to accurately assess the solid wood content in the stacks.

show abstract

Log pile measurement through 3D modeling

Cited by 7 publications

References 4 publications

Research on Volume Measurement of Logs Based on Embedded Application

Research on Volume Measurement of Logs Based on Embedded Application

Automatic Sorting System for Wood Diameter Grades

Estimation of conversion factors for wood stacks in landings and their influencing parameters: a comprehensive literature review for America and Europe

Contact Info

Product

Resources

About