Immature green citrus fruit detection and counting based on fast normalized cross correlation (FNCC) using natural outdoor colour images

A fast normalized cross correlation (FNCC) based machine vision algorithm was proposed in this study to develop a method for detecting and counting immature green citrus fruit using outdoor colour images toward the development of an early yield mapping system. As a template matching method, FNCC was used to detect potential fruit areas in the image, which was the very basis for subsequent false positive removal. Multiple features, including colour, shape and texture features, were combined in this algorithm to remove false positives. Circular Hough transform (CHT) was used to detect circles from images after background removal based on colour components. After building disks centred in centroids resulted from both FNCC and CHT, the detection results were merged based on the size and Euclidian distance of the intersection areas of the disks from these two methods. Finally, the number of fruit was determined after false positive removal using texture features. For a validation dataset of 59 images, 84.4 % of the fruits were successfully detected, which indicated the potential of the proposed method toward the development of an early yield mapping system.     

Feature extraction of hyperspectral images for detecting immature green citrus fruit

At an early immature growth stage of citrus, a hyperspectral camera of 369–1042 nm was employed to acquire 30 hyperspectral images in order to detect immature green fruit within citrus trees under natural illumination conditions. First, successive projections algorithm (SPA) were implemented to select 677, 804, 563, 962, and 405 nm wavebands and to construct multispectral images from the original hyperspectral images for further processing. Then, histogram threshold segmentation using NDVI of 804 and 677 nm was implemented to remove image backgrounds. Three slope parameters, calculated from the pairs 405 and 563 nm, 563 and 677 nm, and 804 and 962 nm were used to construct a classifier to identify the potential citrus fruit. Then, a marker-controlled watershed segmentation based on wavelet transform was applied to obtain potential fruit areas. Finally, a green fruit detection model was constructed according to Grey Level Co-occurrence Matrix (GLCM) texture features of the independent areas. Three supervised classifiers, logistic regression, random forest and support vector machine (SVM) were developed using texture features. The detection accuracies were 79%, 75%, and 86% for the logistic regression, random forest, and SVM models, respectively. The developed algorithm showed a great potential for identifying immature green citrus for an early yield estimation.     

Passion fruit detection and counting based on multiple scale faster R-CNN using RGB-D images

The accurate and reliable fruit detection in orchards is one of the most crucial tasks for supporting higher level agriculture tasks such as yield mapping and robotic harvesting. However, detecting and counting small fruit is a very challenging task under variable lighting conditions, low-resolutions and heavy occlusion by neighboring fruits or foliage. To robustly detect small fruits, an improved method is proposed based on multiple scale faster region-based convolutional neural networks (MS-FRCNN) approach using the color and depth images acquired with an RGB-D camera. The architecture of MS-FRCNN is improved to detect lower-level features by incorporating feature maps from shallower convolution feature maps for regions of interest (ROI) pooling. The detection framework consists of three phases. Firstly, multiple scale feature extractors are used to extract low and high features from RGB and depth images respectively. Then, RGB-detector and depth-detector are trained separately using MS-FRCNN. Finally, late fusion methods are explored for combining the RGB and depth detector. The detection framework was demonstrated and evaluated on two datasets that include passion fruit images under variable illumination conditions and occlusion. Compared with the faster R-CNN detector of RGB-D images, the recall, the precision and F1-score of MS-FRCNN method increased from 0.922 to 0.962, 0.850 to 0.931 and 0.885 to 0.946, respectively. Furthermore, the MS-FRCNN method effectively improves small passion fruit detection by achieving 0.909 of the F1 score. It is concluded that the detector based on MS-FRCNN can be applied practically in the actual orchard environment.

     

Detection of Huanglongbing (citrus greening) based on hyperspectral image analysis and PCR

Huanglongbing (HLB, citrus greening) is one of the most serious quarantine diseases of citrus worldwide. To monitor in real-time, recognize diseased trees, and efficiently prevent and control HLB disease in citrus, it is necessary to develop a rapid diagnostic method to detect HLB infected plants without symptoms. This study used Newhall navel orange plants as the research subject, and collected normal color leaf samples and chlorotic leaf samples from a healthy orchard and an HLB-infected orchard, respectively. First, hyperspectral data of the upper and lower leaf surfaces were obtained, and then the polymerase chain reaction (PCR) was used to detect the HLB bacterium in each leaf. The PCR test results showed that all samples from the healthy orchard were negative, and a portion of the samples from the infected orchard were positive. According to these results, the leaf samples from the orchards were divided into disease-free leaves and HLB-positive leaves, and the least squares support vector machine recognition model was established based on the leaf hyperspectral reflectance. The effect on the model of the spectra obtained from the upper and lower leaf surfaces was investigated and different pretreatment methods were compared and analyzed. It was observed that the HLB recognition rate values of the calibration and validation sets based on upper leaf surface spectra under 9-point smoothing pretreatment were 100% and 92.5%, respectively. The recognition rate values based on lower leaf surface spectra under the second-order derivative pretreatment were also 100% and 92.5%, respectively. Both upper and lower leaf surface spectra were available for recognition of HLB-infected leaves, and the HLB PCR-positive leaves could be distinguished from the healthy by the hyperspectral modeling analysis. The results of this study show that early and nondestructive detection of HLB-infected leaves without symptoms is possible, which provides a basis for the hyperspectral diagnosis of citrus with HLB.     

Effects of INA on postharvest blue and green molds and anthracnose decay in citrus fruit

As a synthetic functional analog of salicylic acid, 2,6-dichloroisonicotinic acid(INA) is effective in inducing the host disease resistance of a plant against a pathogen. The effects of INA on controlling postharvest blue and green molds and anthracnose decay and defense-related enzymes on citrus fruits were investigated, and the ascorbic acid of naturally infected citrus flavedo was also measured. Results showed that 1.0 mmol L~(–1) INA treatments significantly reduced blue and green molds and anthracnose decay development on both wound-inoculated fruit and naturally-infected fruit compared with the control fruit. The treatment effectively enhanced the β-1,3-glucanase(GLU), chitinase(CHI), phenylalanine ammonia-lyase(PAL) and peroxidase(POD) activities and the polyphenol oxidase(PPO) in flavedo. The results presented here suggest that INA might be used as a chemical fungicide substitution to control postharvest diseases in citrus fruits.     

基于LBP纹理和改进Camshift算子的车辆检测与跟踪

提出了利用背景图像LBP（局部二值模式）纹理和当前帧图像LBP纹理的相似度分析提取前景的方法,克服了车辆检测中常用的帧差法、背景差分法对光照比较敏感的缺点.同时基于H,S,V分量及改进的LBP纹理的联合直方图与金字塔L-K光流法中心跟踪相结合的Camshift跟踪算法,有效地解决了背景目标颜色相近可能会导致跟踪的目标区域加入背景后变大、处理较大帧间位移的视频跟踪上搜索窗口的位置准确度较低的问题.实验证明,该方法具有良好的检测和追踪效果.     

基于物联网的果园水分智慧化管理对柑橘叶片光合特性以及果实品质的影响

为提高柑橘水分利用率和果实品质,实现柑橘果园的水分自动化灌溉和标准化生产。以沃柑为研究对象,研究两种水分管理模式对柑橘光合特性和品质的影响。结果表明：物联网水分智慧化管理提高了柑橘叶片四个时期降低了叶片的蒸腾速率,提高了叶片的瞬时水分利用率。同时,物联网水分智慧化管理显著提高了柑橘总糖、糖酸比和维生素C含量,降低了总酸含量。该水分管理模式有利于促进柑橘产业可持续发展。     

基于无人机高光谱遥感的柑橘患病植株分类与特征波段提取

目的 结合传统与现代农业病虫害监测的优缺点,探索通过无人机高光谱遥感技术检测出患病的柑橘植株、通过人工田间调查方式判断其患病种类及患病程度的病虫害监测方法。方法 使用无人机获取原始高光谱图像,经过光谱预处理和特征工程后,采用连续投影算法提取对柑橘患病植株分类贡献值最大的特征波长组合,基于全波段使用BP神经网络和XgBoost算法、基于特征波段使用逻辑回归和支持向量机算法,建立分类模型。结果 基于全波段的BP神经网络和XgBoost算法的ROC曲线下面积(Area under curve,AUC)分别为0.883 0和0.912 0,分类准确率均超过95%;提取出698和762 nm的特征波长组合,基于特征波长使用逻辑回归和支持向量机算法建立的分类模型召回率分别达到了93.00%和96.00%。结论 基于特征波长建模在患病样本分类中表现出很高的准确率,证明了特征波长组合的有效性。本研究结果可为柑橘种植园的病虫害监测提供一定的数据和理论支撑。     

基于Mixup算法和卷积神经网络的柑橘黄龙病果实识别研究

目的 解决传统柑橘黄龙病果实图像识别方法依赖人工设计特征、费时费力、网络模型参数量大、识别准确率低等问题。方法 首先,采集柑橘黄龙病的果实图像,并对其进行翻转、旋转、仿射、高斯扰动等数据扩增;采用Mixup算法建立样本之间的线性关系,增强模型识别数据样本的鲁棒性;然后,迁移Xception网络在ImageNet数据集上的先验知识,提出一种基于Mixup算法和卷积神经网络的柑橘黄龙病果实识别模型-X-ResNeXt模型;最后,采用动量梯度下降优化方法,有效地减缓震荡影响,并且有效地加速模型向局部最优点收敛。结果 采用数据扩增数据集训练的X-ResNeXt模型准确率可以达到91.38%;在进行迁移学习优化后,训练时间减少了432 s,准确率提升为91.97%;结合Mixup混类数据增强进一步训练,模型准确率提升为93.74%;最后,利用动量梯度下降方法进行模型收敛优化,最终模型的准确率达到94.29%,比Inception-V3和Xception网络分别提高了3.98%和1.51%。结论 在数据量较少情况下,降低模型复杂度并迁移已有先验知识,有助于模型性能提升;Mixup混类数据增强方法有利于提高模型识别柑橘黄龙病果实图像样本的适应性,提升柑橘黄龙病果实识别模型性能;X-ResNeXt模型在准确率与召回率指标上优于经典识别模型,可为柑橘黄龙病的高精度、快速无损识别提供参考。     

冷激处理对蜜柚贮藏生理的影响及减轻粒化的研究

用0℃冰水混合物为冷却介质,结合涂膜处理蜜柚,以聚乙烯薄膜袋包装为对照,研究了不同处理对蜜柚生理代谢及相关酶活性的影响.结果表明：冷激或冷激结合涂膜处理可显著抑制柚果的呼吸强度,有效地降低果实乙醇含量,降低果肉POD（过氧化物酶）酶活性,减轻粒化发生的程度.     

CPPU对无核椪柑着果和果实品质的效应研究

比较了不同CPPU浓度和处理时期对无核椪柑着果和果实品质的影响.结果表明,CPPU处理对提高无核椪柑着果率、单果重和果实品质有显著影响.在CPPU5～10 mg/L范围内,随浓度增加,着果率增加,但浓度大于10 mg/L时,着果率呈下降趋势,单果重则与CPPU浓度呈正比.CPPU与GA3混合处理对提高着果率和单果重有加合效应.随CPPU浓度增加,果皮厚度呈增加趋势,而果形指数和可溶性固形物含量呈下降趋势.CPPU10 mg/L不同时期处理的着果率均显著高于对照,且以谢花后处理的效果最好,其着果率显著高于第一次生理落果后处理的着果率.对果实品质的影响不同时期处理间差异不显著,但与对照之间的差异明显.CPPU处理2次的效果略强于处理1次的,但成本也相应增加.     

柑橘园柑橘小实蝇入侵扩散规律与危害动态模型研究

为了探索柑橘小实蝇入侵扩散与危害规律,提高其监测与防控水平,2008-2010年应用柑橘小实蝇专用性诱剂和诱捕器,在全市19个镇（街道）35个柑橘园建立监测点进行全市性入侵扩散分布普查;在古城伏龙柑橘园和市区水果市场建立2个系统监测点开展全年种群数量消长监测,结果表明柑橘小实蝇种群入侵扩散与时空分布呈塔型趋势,即以城区为中心,并呈向周边区域扩散蔓延趋势;全年种群时序数量变化主要呈单峰型曲线变化,一般于6月中下旬至7月上中旬初见性诱成虫,8月上旬形成增长拐点,9-10月形成数量高峰, 影响种群数量消长的主要因子有种群基数、气候和生境条件等,从而创建柑橘小实蝇基数（m6）与全年种群诱量（M）关系模型M=23.8339 m6+59.8003（n=6, r=0.9735**）、当旬虫口密度(mn)与其前3个月的旬平均气温(tn-9)关系模型mn=1.9248tn-9-14.88063（n=72, r=0.5123**）,以及柑橘挂果期成虫诱量（M）、有虫株率（R%）、有虫果率（P%）、每虫果幼虫量（N）等关系模型：R=0.3667M-1.2746（n=11, r=0.8901**）;P=0.0581R+0.3112（n=11, r=0.9649**）;N=0.6438P+0.9610（n=11, r=0.7000*）。应用柑橘小实蝇种群入侵扩散危害规律及其参数模型,可反映柑橘园柑橘小实蝇发生变化动态,可随旬作出预报和决策防治,这对提高其监测预警和持续控制具有重要指导意义。     

基于无人机遥感影像的沙糖橘果树提取方法研究

目的 通过无人机获取沙糖橘果园的遥感图像,快速提取果树分布位置,为果树的长势监测和产量预估提供参考。方法 以无人机拍摄的可见光遥感图像为研究对象,计算超红指数、超绿指数、超蓝指数、可见光波段差异植被指数、红绿比指数和蓝绿比指数6种可见光植被指数,使用双峰阈值法选取阈值进行果树的提取。在使用光谱指数进行识别的基础上,结合数字表面模型作为识别模型的输入变量,进行对比试验。结果 相比使用单一光谱指数,结合数字表面模型提高了果树和非果树像元的提取精度,6次波段融合后的总体精度均大于97%。超红指数与数字表面模型结合后的总体精度最高,为98.77%,Kappa系数为0.956 7,植被信息提取精度优于其他5种可见光植被指数与数字表面模型结合后的提取精度。结论 数字表面模型结合可见光植被指数的提取方法能够更深层次地挖掘遥感数据蕴含的信息量,为影像中色调相似地物的提取提供参考。     

载果量对初果期晚熟杂柑风味及质地品质的影响

【目的】探讨不同树体载果量水平对初果期红桔、美国糖桔、春见、红美人和胡柚等5个晚熟杂柑品种风味品质及果实质地的影响,以期为各品种初果期最适宜树体载果量区间设定和鲜食品质提升提供理论依据。【方法】2019年,以生长势基本一致、4年生的各品种挂果树为材料,在设施栽培条件下设定单一载果量处理,以果实可溶性固形物（TSS）含量与可滴定酸（TA）含量比值变化趋势为主要指标,判断各品种果实成熟进程并选定相对适宜的采收期;2020年在此基础上设定高、低载果量2个处理,分别测定各品种成熟期果实TSS和TA含量,果肉和果皮中可溶性糖、有机酸组分及含量,以及果实质地相关参数,并对载果量与各果实品质指标进行相关分析。【结果】适宜的低载果量下,初果期红桔果肉中蔗糖、果糖、葡萄糖和柠檬酸含量不同程度提升;春见果肉中蔗糖、果糖和葡萄糖含量提升的同时柠檬酸含量下降、苹果酸含量提升;而红美人在低载果量下果肉中蔗糖含量下降、葡萄糖含量提升的同时苹果酸含量下降,各品种果肉中糖酸比例不同程度发生改变;至采收时,高载果量处理下红桔TSS/TA比值较低载果量降低12.7%;春见和美国糖桔2个品种TSS/TA比值较低载果量分别增加7.3%和7.1%。在红桔上,树体载果量水平与果皮硬度呈极显著相关（P<0.01,下同）,与果皮韧性和果肉有机酸含量呈显著相关（P<0.05,下同）;在胡柚上,载果量与果皮韧性呈极显著相关,与果皮可溶性糖含量呈显著相关;在红美人上,载果量与果皮硬度呈显著相关,与果皮可溶性糖含量呈极显著相关;在春见上,载果量与果皮有机酸含量呈显著相关,与果肉可溶性糖含量呈极显著相关;在美国糖桔上,载果量与果肉硬度呈极显著相关,与果肉韧性呈显著相关;但所有供试品种果肉化渣性指标,即果肉紧实度和囊衣硬度与树体载果量水平均未表现出明显相关性。【结论】初果期红桔、红美人和胡柚3个供试品种在较低载果量下,TSS/TA比值略高、最终采收时综合风味更好,春见和美国糖桔2个品种则在较高载果量下TSS/TA比值略高,综合风味更佳。该结果可为不同品种柑橘控产提质技术的进一步完善提供数据支持和参考。     

基于特征选择与骨架提取的种子萌发的芽长、根长检测

芽长是种子活力的一个重要判定标准.传统的芽长检测方法采用人工测量方式,存在费时费力、且受人为主观因素影响较大等问题.利用数字图像处理技术的芽长自动检测算法可以提高芽长测量的效率,并且能够统一测量标准从而避免主观误差.本研究基于特征选择与骨架提取算法原理设计了种子芽长、根长检测复合算法及软件,首先利用颜色特征提取叶片信息...     

几种药剂对苹果绣线菊蚜的防效试验

选择35%赛丹乳油、5%速杀星乳油、45%扫蚜特1号乳油、2.5%绿色功夫乳油及10%吡虫啉可湿性粉剂等药剂,在室内大田对苹果绣线菊蚜的防效进行研究,结果表明,在室内绿色功夫、速杀星防效较好;在大田吡虫啉、扫蚜特1号及赛丹防效较好.     

Detection of a deep 3-microm absorption feature in the spectrum of Amalthea (JV)

Near-infrared spectra of Jupiter's small inner satellites Amalthea and Thebe are similar to those of D-type asteroids in the 0.8- to 2.5-micrometer wavelength range. A deep absorption feature is detected at 3 micrometers in the spectra of the trailing side of Amalthea, which is similar to that of the non-ice components of Callisto and can be attributed to hydrous minerals. These surface materials cannot be explained if the satellite formed at its present orbit by accreting from a circumjovian nebula. Amalthea and Thebe may be the remnants of Jupiter's inflowing building blocks that formed in the outer part or outside of the circumjovian nebula.     

柑桔品种对柑桔潜叶蛾实验种群的影响

研究了 4个柑桔品种对柑桔潜叶蛾 (Phyllocnistis citrella Staiton)实验种群的影响 .结果表明 ,在各柑桔品种上柑桔潜叶蛾从卵到蛹的发育历期、存活率 ,雌成虫产卵量、产卵动态、寿命和种群生命表参数都存在明显差异 ;供试品种对潜叶蛾抗性的强弱顺序为 :福桔 >蕉柑 >雪柑 >芦柑 .福桔上潜叶蛾存活率为 2 2 .97%、产卵量 2 0 .91粒·雌 -1,均比其它 3个品种上的低 ;发育历期为 19.5 8d,比其它品种上的长 ;种群生命表参数中 ,内禀增长率为 0 .0 72 1、周限增长率为 1.0 75 d-1,均比其它品种上的低 ,世代平均历期为 2 1.5 d,比其它品种上的长 ,表明福桔对柑桔潜叶蛾抗性相对较强     

基于无人机三维点云的玉米植株自动计数研究

植株计数是农民、育种专家等在整个作物生长季评估作物生长状况和管理实践的最常用方法之一,可用来进行合理的田间规划以及管理。针对高密度种植试验区高通量获取玉米自动株数方法匮乏的问题,本研究利用无人机遥感平台,获取田间314个不同基因型的玉米高密度育种小区的数码影像和激光雷达(light detection and ranging, LiDAR)点云数据,发展了一种结合玉米三维空间信息的固定窗口局部最大值算法,实现了高密度玉米育种小区成株数的自动检测,并对比了基于此两种不同数据源的检测精度。该方法以冠层高度模型(canopy height model, CHM)中包含的株高信息为基础,以玉米种植株距为固定窗口进行单株玉米种子点检测,并将检测到的种子点与目视解译的玉米位置进行空间匹配来进行精度的评估。结果表明,基于无人机数码影像构建3种空间分辨率CHM的综合检测精度分别为81.30%、83.11%和78.93%;基于无人机LiDAR的综合精度分别为82.33%、88.66%和81.46%;基于两种数据源构建的CHM,均在空间分辨率为0.05 m时,获得最佳的检测精度。此外,当空间分辨率相同时,...