基于机器视觉的刨花板表面缺陷检测系统

针对目前国内人造板企业在板面缺陷检测仍然依靠人工的情况,开发基于机器视觉技术的刨花板表面缺陷自动检测系统。利用工业相机采集板材表面图像,使用C++、OpenCV、JAI_SDK类库和MFC多线程技术实现缺陷检测算法,通过计算机串口与生产线控制系统通信。系统运行稳定、缺陷定位准确、参数配置灵活,检测效果和检测速度可满足连续压机生产线在线检测要求。     

木质板材表面缺陷自动检测技术研究

木质板材表面缺陷检测系统采用高亮光源提供照明,线阵CCD相机实时获取其表面图像,利用工控机在线处理数据并根据板材缺陷的检测分析选择相应的生产工艺和加工方法,以提高木材的出材率和生产的自动化程度。该系统可完整提取板材表面缺陷,利用改进的差影法对图像进行分割,以便对图像特征进行提取。实验表明,该数据处理方法能够准确地提取板材表面缺陷的信息。     

基于机器视觉的锯材表面缺陷检测系统设计

锯材表面缺陷对锯材的质量和性能有着重要的影响。设计了基于机器视觉的锯材表面缺陷自动检测系统和计算机软件检测识别方法,确定了主要参数。通过对锯材表面图像的主要缺陷进行统计分析,综合评价整根锯材。检测系统的硬件主要由传送机构、电控系统、图像采集控制、分等系统等部分组成。软件主要由图像采集、图像处理、缺陷统计分析等部分组成。     

基于深度学习特征和非线性支持向量机的板材表面缺陷识别方法

深度学习是一种有效的特征学习方法,具有很强的自主学习能力。研究了基于深度学习特征与非线性支持向量机(NSVM)分类算法相结合的板材表面缺陷识别方法。首先,针对深度学习模型需要海量训练数据的特性,使用旋转剪切的方法对采集到的原始板材表面缺陷图像进行数据扩增;其次,使用扩增后的板材表面缺陷图像数据集对笔者提出的深度卷积神经网络(CNN)模型进行训练,并使用训练好的网络提取不同种类缺陷图像的深度特征;然后,为了消除深度特征中的冗余数据,并增强数据的表达能力,运用基于1范数的非贪婪主成分分析(Non-greedy PCA-L1)算法对板材的深层语义特征进行特征降维和特征增强;最后,运用增强后的深度特征训练NSVM模型,并使用训练好的NSVM模型对原始板材表面缺陷图像的测试集进行分类。实验结果表明,笔者提出的识别方法具有较好的鲁棒性和实用性,可取得目前较好的分类效果,针对结疤、压痕和无损3种板材表面缺陷识别率可达99%以上。     

基于高斯混合模型的青梅表面缺陷检测识别技术

目前青梅的缺陷识别检测仍然依靠人工挑选方式来完成,但人工挑选方式受工作经验、劳动强度等因素制约,已经难以适应产业的发展。为有效提高青梅表面缺陷检测的自动化程度和检测精度,本试验应用机器视觉技术针对青梅表面的缺陷检测展开研究。通过搭建青梅表面图像静态采集系统,采用图像处理软件HALCON对青梅表面进行了单通道灰度图像提取、图像滤波、灰度二值化及特征提取等预处理操作,实现了对青梅表面图像的去背景化,并利用去边缘法在青梅H通道分量图像中成功提取到青梅表面缺陷。最后采用高斯混合模型构建青梅表面缺陷检测分类器,并创建了一套基于机器视觉的青梅表面缺陷检测系统。具体选取了348张青梅缺陷图像作为训练测试样本,其中78%的图像作为训练集,22%的图像作为测试集,结果表明:该分类器对青梅溃烂、伤疤、雨斑缺陷的检测准确率分别为100%,97.22%,92.31%,对完好青梅检测准确率为94.44%,验证了将高斯混合模型应用在青梅缺陷检测方面的有效性。     

基于Faster R-CNN的实木板材缺陷检测识别系统

我国木材资源有限,为了提高木材的利用率,采用机器视觉来实现木材缺陷快速而稳定的检测,不仅可以克服人工检测的低效率和木材缺陷识别的低准确率,而且对提高木材加工企业的智能化水平具有重要意义。为了高效、快速、准确地进行无损检测,采用深度学习方法,建立了一种基于快速深度神经网络的实木板材缺陷识别模型。首先采用Resnet V2结构对采集到的实木板材缺陷图像进行特征提取,然后应用该模型对节子、孔洞等实木板材缺陷进行训练学习,最后构建了Faster R-CNN检测框架,并使用tensorflow开发平台对节子、孔洞等实木板材缺陷进行预测输出。具体选取了2 000块杉木样本,通过旋转对原始的实木板材图像进行数据扩充,扩充后图像的80%作为训练集,20%作为验证集来进行仿真。仿真结果表明,该模型对实木板材节子缺陷检测正确率为98%,对实木板材孔洞缺陷检测正确率为95%,验证了将深度学习算法应用于实木板材缺陷检测中的有效性。     

基于YOLOv4的结构用锯材表面缺陷识别

结构用锯材在使用之前进行表面质量评价、分级,对于提高木材的综合利用率具有重要作用。综合利用机器视觉技术和深度学习方法,选取国内常用的云杉结构用锯材作为研究对象,通过工业相机采集结构用锯材表面主要缺陷(节子、虫眼、裂纹),并对锯材主要缺陷进行数字化评价分析。先通过自主搭建的机器视觉图像采集装置,采集100块结构锯材正反面表面图像,共获取表面缺陷图像1 450张,其中活节缺陷图像550张、死节缺陷图像320张、裂纹缺陷图像295张、虫眼缺陷图像285张;随后搭建基于YOLOv4的深度学习缺陷检测识别框架,对缺陷图像中80%的图像进行训练,剩余20%用于测试。试验结果表明,基于YOLOv4的深度学习缺陷检测识别框架,能有效识别并准确定位锯材表面缺陷的类型和位置,平均识别率96.7%,其中活节缺陷识别率100%、死节缺陷识别率97.5%、裂纹缺陷识别率90%、虫眼缺陷识别率96.7%,可满足生产应用需求。     

机器视觉在单板缺陷检测中的应用

单板是胶合板制造的主要原料。为了实现单板表面缺陷检测技术的智能化,降低人力成本,提高检测合格率,现已将机器视觉技术应用于缺陷检测中。在机器视觉系统中,图像处理和分析算法尤为重要。如何提高算法的准确性和鲁棒性一直是研究的重点。文中基于对大量文献和实验结果的分析,介绍机器视觉的应用现状,并对单板表面缺陷检测过程中的图像去噪、图像分割、特征提取等方法进行总结,概括相关方法的原理、特点、局限性以及适用范围,并对未来技术发展趋势进行展望。     

基于DSP的木材缺陷图像处理系统

探讨了木材缺陷计算机视觉识别技术研究的现状,提出了基于DSP的木材缺陷图像处理系统的硬件结构以及图像处理的算法;介绍了图像采集芯片SAA7113和实现图像采集的方法,并给出上述系统的处理结果。     

基于分形理论和数学形态学的木材表面缺陷识别的图像处理

在木材表面缺陷识别过程中,能否精确提取缺陷轮廓是提高分选准确率的重要因素。采用分形理论和数学形态学进行板材缺陷图像分割和边缘提取,能有效的克服传统方法中缺陷图像提取受背景纹理影响大的不足,为后续的木材表面缺陷的识别打下坚实的基础,提高木材的使用率,对木材表面缺陷识别具有实际意义。     

Browsing Damage on Pine (Pinus sylvestris and P. contorta) by a migrating moose (Alces alces) Population in Winter: Relation to Habitat Composition and Road Barriers

In Scandinavia, moose (Alces alces L.) sometimes cause severe browsing damage to economically-important pine. Moose-vehicle accidents have spurred construction of fences along roads, and these may interfere with moose migration between summer and winter ranges, or the road alone may be a barrier. If this happens and moose build up along roads, landowners may suffer economically. Therefore, this study investigated whether roads, fences or other factors influence the use of young pine stands by moose. Eighty stands along roads in northern Sweden were evaluated in which individually-browsed branches were counted on 9972 pines. Moose browsing was not significantly related to birch (Betula pendula Roth, B. pubescens Ehrh.) density, nor did it differ between pines (Pinus contorta Douglas or P. sylvestris L.). However, increased pine density, site productivity and proximity to a highway were associated with increased browsing. Further large-scale studies are needed to understand moose habitat selection and the effects of roads.     

Effects of Root Freezing on the Physiology and Growth of Picea glauca,Picea mariana and Pinus banksiana Seedlings Under Different Soil Moisture Regimes

The root systems of 2-yr-old Picea glauca, Picea mariana and Pinus banksiana seedlings were submitted to various frost temperatures during an artificial frost to induce different levels of root damage. Frost-damaged and control seedlings were placed in a greenhouse under high and low soil moisture regimes. Seedling growth and physiology were evaluated periodically. Seedling survival was reduced when root damage reached levels of 60-80%. Root systems of all three species showed partial to total recovery by the end of the experiment. In general, root freezing damage caused reductions in seedling growth, with these reductions becoming less significant over time. Root damage had little to no effect on black spruce and jack pine seedling physiology, while white spruce CO 2 uptake decreased with increasing root damage. Shoot nitrogen content of all three species decreased slightly with increasing root damage.     

Decomposition and nutrient loss from prunings of different contour hedgerow species in tea plantations in the sloping highlands of Sri Lanka

Contour hedgerows of multipurpose tree species in the sloping tea lands of Sri Lanka are expected to reduce soil erosion and also add significant amounts of plant nutrients to the soil via periodic prunings. The objective of this experiment was to characterize the biomass decomposition pattern and quantify the amount of nutrients added through prunings of six tree species (Calliandra calothyrsus, Senna spectabilis, Euphatorium innulifolium, Flemingia congesta, Gliricidia sepium and Tithonia diversifolia) currently being used in hedgerows associated with tea. Withered leaf and stem prunings (50 g) were enclosed in 2-mm litter bags, placed at 5-cm depth and retrieved after one, three, six, nine and 12 weeks. Loss of initial dry weight, N, P and K was measured. Single exponential decay function adequately described both dry weight and nutrient loss. Tree species differed significantly in their rate of breakdown with decomposition constants (k) varying from 0.0299 to 0.2006 week⁻¹ for leaves and from 0.0225 to 0.0633 week⁻¹ for stems. Gliricidia showed the highest k for leaves with the rest in the following descending order: Senna > Tithonia ≥ Euphatorium > Calliandra > Flemingia. A similar pattern was observed for loss of all nutrients with Calliandra and Flemingia always having lower k values than the rest. Although N immobilization was not observed, immobilization of P and K was observed during the first week of incubation in some species, particularly in stem prunings. Annual biomass of prunings differed significantly between tree species in the following descending order: Calliandra > Senna > Flemingia > Tithonia > Gliricidia > Euphatorium. Calliandra added the greatest amount of nutrients annually to the soil with Euphatorium adding the least. Calliandra prunings provided the annual total K requirement and 49% of the N requirement of mature tea. However, none of the species provided more than 5% of the P requirement. It is concluded that among the tree species tested, Calliandra and Flemingia are the most suitable for contour hedgerows in tea plantations of this agroclimatic region because of their higher soil nutrient enrichment capacity and slower decomposition rates which would minimize leaching losses. This revised version was published online in June 2006 with corrections to the Cover Date.     

Effects of Seed Weight and Seed Type on Early Seedling Growth of Pinus sylvestris under Harsh and Optimal Conditions

The effects of seed weight and seed type on seedling growth of Pinus sylvestris (L.) were studied by seeding individually weighed orchard and stand seed in different mixtures under harsh (direct seeding in field) and optimal (seeding in nursery) conditions. In the nursery experiment an increase in the seed weight from 3 to 7 mg increased the seedling height by 10-27% and total weight by 27-113%, and decreased the height/diameter ratio by 5-6% after 2 yrs. With elimination of seed weight effects, orchard seedlings were 2% taller than stand seedlings in year 2. Without elimination of seed weight effects, orchard seedlings were 7-13% taller. In the field experiment an increase in the seed weight from 3 to 7 mg increased seedling height by 18-65%, stem volume by 81-274% and the number of top-buds by 23-34% in year 5. After elimination of seed weight effects, orchard seedlings were 7-13% taller than stand seedlings and without elimination of seed weight effects 20-21% taller after 5 yrs. Even after elimination of both seed weight and genetic effects orchard seedlings were 3-9% larger than stand seedlings in the field experiment. In conclusion, the influence of seed weight and seed type on growth traits and slenderness is highly significant and the influence seems to be greater in harsh conditions.     

Potential to harness superior nutritional qualities of exotic baobabs if local adaptation can be conferred through grafting

Baobab leaves form an important part of the local diet in Sahel countries and elsewhere in Africa. Existing leaf nutritional data and agroforestry performance information are based solely on Adansonia digitata L., the baobab of continental Africa. The introduction potential of Adansonia species from the center of diversity in Madagascar and from Australia remains untapped. To assess this potential, the mineral contents and B₁ and B₂ vitamin levels of dried baobab leaves were determined for five-year old trees of A. digitata, A. gibbosa (A. Cunn.) Guymer ex D. Baum, A. rubrostipa Jum. & H. Perrier (syn. A. fony Baill.), A. perrieri Capuron and A. za Baill. grown in an introduction trial in Mali. Nutritional data were evaluated against survival and vigor to identify promising germplasm. Leaf vitamin and crude protein contents were highest in the Madagascar species, especially A. rubrostipa (B₁ 88 mg 100 g⁻¹, B₂ 187 mg 100 g⁻¹, protein 20.7% dry weight). However, the local species far outperformed the introductions in survival, tree height, basal diameter and resistance to termites. We suggest grafting as a way of harnessing the vigor of well-adapted local baobab varieties to the superior nutritional profiles of A. rubrostipa and others. Cross-species grafting tests in Adansonia were successful, thus creating new agroforestry possibilities with different scion/rootstock combinations.     

Modelling of adequate pretwist for obtaining straight timber

Abstract

Wood in general and wooden studs in particular are often distorted owing to uneven shrinkage during the drying process in the sawmill. Twist is often the most detrimental of all types of distortion, and it is caused by spiral grain in combination with variations in moisture content. For sawmills, the objective is to produce dried, straight boards, and one method of dealing with boards with excessive spiral grain is to sort them out and then dry them in a pretwisted position to obtain straight boards after drying. A model using the finite element (FE) method for the simulation of drying twist distortions was first calibrated against laboratory experiments in which boards were dried with and without restraints and pretwists. After the calibration, the FE results were compared with industrial test results for boards that were dried without restraints or with restraints with zero pretwist, i.e. straight restraints. The FE model used an elastic–ideally plastic material model to obtain permanent deformations. The calibration was to set the yield stresses so that there was a good match between FE results and results from the laboratory experiments. The comparison between the industrial test results and the FE results showed that the FE model is capable of realistic simulations of drying boards with and without restraints and presumably also pretwists.     

Stand Structure in Pine,Spruce and Deciduous Forests: A Comparison Between Finnish and Russian Karelia

This study investigated the stand structure in pine, spruce and deciduous forests in the border district of Finland and Russia. A total of 46 mature forest stands was selected as pairs, the members of each pair being as similar as possible with respect to their forest site type, age, moisture and topography. The stands were then compared between the two countries by means of basal areas and number of stems. The proportions of dominating tree species were 2-12% lower, and correspondingly the proportions of secondary tree species higher, in Russian forests. The density of the forest stock was also higher in each forest type in Russia. The forests in the two countries differed most radically in terms of the abundance of dead trees. The amount was two to four times higher in Russian deciduous and spruce forests, and in pine forests the difference was 10-fold. The stand structures indicated that Russian coniferous stands, in particular, were more heterogeneous than intensively managed pine and spruce stands in Finland.     

Growth and Terminal Bud Formation in Picea abies Seedlings Grown with Alternating Diurnal Temperature and Different Light Qualities

The root collar diameter and the height:diameter ratio are of particular importance in container-grown seedlings where a high density in the containers may produce spindly seedlings. Temperature regimes and light quality are known to affect plant growth. The aim of this study was to identify responses in Picea abies (L.) Karst. seedlings grown with light providing different red:far-red ratios and under temperature regimes with alternating day (DT) and night temperature (NT) from negative (DT < NT) to positive (DT > NT) difference (DIF) between DT and NT. Experiments were conducted in controlled environment chambers and in a daylight phytotron. Only limited thermoperiodic responses appeared in P . abies seedlings with respect to seedling height and dry weight accumulation. The formation of terminal buds, however, was clearly delayed in seedlings grown at negative DIF. The results indicate a requirement for day extension light that is high in far-red, to prevent terminal bud formation under natural short-day conditions. An extended study should be conducted to clarify the minimum level of light intensity and the optimal light quality needed to prevent terminal bud formation under natural short-day conditions.     

CAD与建筑设计的关系

本文分析了CAD在设计中引起的正面和负面影响,并进行了系统的阐述,从而使设计者在应用中能够保持客观的态度。     

Growth of Phlebiopsis gigantea in wood of seven conifer species

Heterobasidion parviporum and Heterobasidion annosum are widely distributed root‐rot fungi that infect conifers throughout Europe. Infection of conifer stumps by spores of these pathogens can be controlled by treating fresh stumps with a competing non‐pathogenic fungus, Phlebiopsis gigantea. In this study, growth of three Latvian strains of P. gigantea and the biological control agent ‘Rotstop’ strain was evaluated in stem pieces of Norway spruce, Scots pine, lodgepole pine, Douglas‐fir, Weymouth pine, Siberian larch and Sitka spruce. The growth rates of one H. parviporum and one H. annosum isolate were also measured in the same stem pieces. The growth rate of P. gigantea varied greatly in wood of different conifer species. It was higher in the three pine species, lower in Norway spruce and lowest in Sitka spruce and Siberian larch, and in Douglas‐fir, this fungus did not grow. The largest area of wood occupied by P. gigantea was in lodgepole pine. Growth of Latvian isolates of P. gigantea in the wood of Pinus and Picea species was comparable to that of the Rotstop isolate. Consequently, stump treatment with local P. gigantea isolates should be recommended. However, our results suggest that Douglas‐fir stump treatment against Heterobasidion by P. gigantea may be ineffective and other stump treatment methods should be considered.