Figure - available from: Forests
This content is subject to copyright.
(a). Long and short diameter measurement schematic, d1 is the short diameter, and d2 is the long diameter. (b). ZED camera.
Source publication
Wood logs need to be measured for size when passing through customs to verify their quantity and volume. Due to the large number of wood logs needs through customs, a fast and accurate measurement method is required. The traditional log measurement methods are inefficient, have significant errors in determining the long and short diameters of the w...
Similar publications
![Qualitative comparisons on Flickr1024 [26] (top) and Middlebury [24]...](publication/372393471/figure/fig5/AS:11431281188296997@1694571158336/Qualitative-comparisons-on-Flickr1024-26-top-and-Middlebury-24-bottom-for_Q320.jpg)
The increasing trend of binocular imaging in recent years has sparked a surge of interest in stereo image super-resolution. While considerable progress has been made in improving model performance, the potential of single-view and cross-view features remains largely unexplored. To address this, we present a novel network that incorporates both intr...
In stereo vision, depth information relies on the dense registration accuracy of binocular stereo images, and its realtime performance is also significant in many automation applications. Recently, it is still a challenge to balance the efficiency and accuracy. Motivated by this problem, we propose a lightweight 2D guided deformable aggregation(GDA...
Accurate estimation of three-dimensional (3D) information from captured images is essential in numerous computer vision applications. Although binocular stereo vision has been extensively investigated for this task, its reliability is conditioned by the baseline between cameras. A larger baseline improves the resolution of disparity estimation but...
Traditional non-coplanar calibration methods represented by Tsai’s method have many problems, such as insufficient calibration accuracy, inconvenient operation, inaccurate model, etc. This paper proposes a new high-precision non-coplanar calibration method to solve these problems. Like Tsai’s method, the proposed calibration method utilizes a one-d...
Citations
... LiDAR technology uses lasers to measure distance, creating detailed 3D point clouds of the object being measured, which can be incredibly precise for volume calculations [2], and could be applied for autonomous forestry tasks, such as, navigation, tree detection, and species classification [14]. An additional innovative technique is through detection and measurement of diameters using computer vision techniques [15,16]. ...
... Furthermore, a rotation-based diameter search algorithm identifies both long and short diameters. Compared to manual measurements, the proposed method boasts an average diameter error of only 5.3 mm, with individual errors of 5.7 mm for the short diameter and 7.19 mm for the long diameter [16]. ...
... The high box precision and mask precision in the test set (0.928 and 0.875, respectively) indicate strong model performance in identifying and accurately segmenting the log ends. Compared to the tests performed by Lu et al. [15], Yu et al. [16], and Lin et al. [29], our study's segmentation accuracy and detection metrics are competitive, though slightly lower in certain aspects. These discrepancies might be attributed to variations in dataset complexity, as illustrated in Video S1. ...
Accurate timber quantification is essential in forestry and the timber industry, impacting harvest planning, processing, pricing, and overall supply chain management. Traditional methods for estimating the volume of stacked timber, often reliant on manual measurements, are time-consuming and prone to error. This research aims to develop an accurate procedure for estimating the volume of stacked eucalypt timber in yards. The proposed procedure combines automatic log detection and diameter distribution models. Automatic log detection was achieved using advanced computer vision techniques, specifically the You Only Look Once version 9 (YOLOv9) model, which automates the identification and counting of individual logs within a stack. We used stem diameter distribution models to estimate total stack volume based on log counts and probability densities. This approach ensures high accuracy and efficiency, significantly reducing the time and effort required for volume estimation. The dataset used for this study includes diameter measurements from a pre-harvest inventory of eucalypt trees aged 6 and 7 years, alongside videos of stacked timber. The YOLOv9 model was trained to detect logs from these videos, achieving high precision in object detection and segmentation tasks. Performance metrics such as Box Precision, Box Recall, and mean Average Precision (mAP) were used to evaluate the model's effectiveness. The results indicate that the model generalizes well to new data, with high accuracy in both validation and test sets. Among the distribution models evaluated, the generalized extreme value (GEV) distribution provided the best fit for the stem diameter data, allowing for accurate volume predictions. This procedure, which integrates automatic log detection with diameter distribution models, offers a scalable solution applicable to large and complex timber stacks. Finally, a repository was established to allow users to test the proposed method. Future works will focus on refining the model's accuracy and expanding its applicability across different species, forest production and log conditions.
... Subsequently, we employed an improved Cascade Mask R-CNN model to detect the log ends and derive the contour mask. Next, we applied the improved long and short diameter search algorithm [40] to the mask to calculate the long and short diameters of the log end. The outcomes are presented in Figure 11, where the two perpendicular lines correspond to the long and short diameters of the log. ...
... Further details on measurement errors are provided in Table 5. We found a short diameter error of 0.86 cm and a long diameter error of 0.88 cm, which aligns closely with the results from our previous work [40]. The slight increase in error may be attributed to variations in lighting conditions. ...
Logs require multiple verifications to ensure accurate volume and quantity measurements. Log end detection is a crucial step in measuring log volume and counting logs. Currently, this task primarily relies on the Mask R-CNN instance segmentation model. However, the Feature Pyramid Network (FPN) in Mask R-CNN may compromise accuracy due to feature redundancy during multi-scale fusion, particularly with small objects. Moreover, counting logs in a single image is challenging due to their large size and stacking. To address the above issues, we propose an improved log segmentation model based on Cascade Mask R-CNN. This method uses ResNet for multi-scale feature extraction and integrates a hierarchical Convolutional Block Attention Module (CBAM) to refine feature weights and enhance object emphasis. Then, a Region Proposal Network (RPN) is employed to generate log segmentation proposals. Finally, combined with Deep SORT, the model tracks log ends in video streams and counts the number of logs in the stack. Experiments demonstrate the effectiveness of our method, achieving an average precision (AP) of 82.3, APs of 75.3 for small, APm of 70.9 for medium, and APl of 86.2 for large objects. These results represent improvements of 1.8%, 3.7%, 2.6%, and 1.4% over Mask R-CNN, respectively. The detection rate reached 98.6%, with a counting accuracy of 95%. Compared to manually measured volumes, our method shows a low error rate of 4.07%.
... These can present problems of accuracy since they are divided into those that determine the apparent volume and those methods considered exact; the former is the method of special tables and stacking coef-ficient, while the latter is by immersion or xylometer and ponderal or by weighing (Diéguez Aranda et al. 2003) To overcome the drawbacks of manual measurement, automated measurement methods have been proposed, which use photoelectric, optical or laser means to measure the size of the trunk and calculate the volume, such as the use of a cell phone with a rangefinder to measure the wood trunk, where the accuracy of the measurement reached 98.2%, or the use of image segmentation to detect 3D structural information and measure the size of the trunk, whose error was only 4.8% compared to manual measurement. However, obtaining images in a real environment such as a sawmill is difficult as it is complicated to separate the useful elements of the image from the complex background (Yu et al. 2023). Therefore, there is still a need for more accurate, faster, and less costly estimations. ...
Citation: Borrego-Núñez C., López-Serrano P.M., Domínguez-Calleros P.A., Compeán-Aguirre J.L., Carrillo-Parra A. (2024): Use of the threshold segmentation method as an alternative for estimating the volume of forest industry residues. J. For. Sci., 70: 00-00. Abstract: In recent decades, the interest in searching for procedures and strategies to make energetic and economic use of residues from different industries has been an important part of the political agenda. There are several methods to determine the volume of residues from the forestry industry, but they are too time-consuming to apply. The objective of the present study was to establish a simpler and more efficient method to quantify the volume of residues from the forest industry. Ten controlled piles were made with residues from a private sawmill in the city of Durango, Mexico. To calculate the volume, two manual methods and one automatic method were used to calculate the stacking coefficient of the piles, while the water immersion method was used to calculate the real volume. A completely random experimental design was used for the analysis, where an analysis of variance and mean comparisons were performed at a significance level of P ≤ 0.05. The results of the study show that the threshold segmentation method is faster, more practical and efficient than the other methods used. The estimation of the volume of these residues will contribute to generating sustainable alternatives for the development and use of forest industry resources.
To improve the accuracy of volume measurement for irregularly shaped coal gangue, defects in the depth image and various errors in volume measurement are analyzed. The gray difference similarity (Gds) is proposed for pre-classifying defects, and the depth and RGB information are used interactively for adaptive repair. To minimize the impact of abnormal gray distribution and irrelevant information on the repair process, the areas to be repaired are divided into abnormal regions or layers based on gray and distance weights. Taking into account parameters like geometric morphology (GeMo), volume (Ve), and GeMo × Ve, the influence of wrong imaging and gaps is fully considered. The reverse compensation of errors is achieved by applying the principles of mathematical statistics and the nonlinear surface fitting algorithm. The results show that compared with other algorithms, the proposed algorithm has the smallest measurement error of 6.614 % and is not easily affected by external factors.
