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.     

人工神经网络在遥感图像森林植被分类中的应用

应用人工神经网络模型对陆地卫星TM多光谱图像进行了森林植被分类的研究 ,共选取了 8种主要植被类型 ,重点是研究在不同背景条件下存在同谱异物现象的云杉、油松和落叶松等针叶林树种的分类方法 .所采用的网络模型为 3层误差后向传播神经网络模型 ,鉴于贺兰山自然植被垂直带谱明显 ,利用误差后向传播网络模型的并行分布式结构 ,研究中引入高程数据作为一个独立波段与 3个多光谱波段一起直接进行分类 ,取得了很好效果 .该方法与常规的最大似然法相比 ,存在同谱异物现象的云杉、油松和落叶松的分类精度平均提高了 2 7 5个百分点 .对存在同物异谱现象的阔叶林的分类精度也有一定程度的提高 .     

Vegetation detection and discrimination within vegetable plasticulture row-middles using a convolutional neural network

Precision Agriculture - Weed control between plastic covered, raised beds in Florida vegetable crops relies predominantly on herbicides. Broadcast applications of post-emergence herbicides are...     

基于声学响应和BP神经网络检测鸡蛋裂纹

为了提高鸡蛋裂纹检测的准确性,建立了声学敲击检测鸡蛋裂纹的装置,采集和分析鸡蛋被敲击后的声音信号。提取了4个特征频率、偏斜度平均值和峰度平均值共6个特征参数,并作为神经网络的输入量,创建了基于MATLAB的结构为6-15-2的3层BP神经网络模型判别鸡蛋裂纹。检测结果显示:对蛋壳受各种程度破坏后的鸡蛋判别精度可达92%以上,对蛋壳完整的鸡蛋判别精度达到96%,对鸡蛋总体的判别精度可达94%。     

Green citrus detection using ‘eigenfruit’, color and circular Gabor texture features under natural outdoor conditions

A machine vision algorithm was developed to detect and count immature green citrus fruits in natural canopies using color images. A total of 96 images were acquired in October 2010 from an experimental citrus grove in the University of Florida, Gainesville, Florida. Thirty-two of the total 96 images were selected randomly and used for training the algorithm, and 64 images were used for validation. Color, circular Gabor texture analysis and a novel ‘eigenfruit’ approach (inspired by the ‘eigenface’ face detection and recognition method) were used for green citrus detection. A shifting sub-window at three different scales was used to scan the entire image for finding the green fruits. Each sub-window was classified three times by eigenfruit approach using intensity component, eigenfruit approach using saturation component, and circular Gabor texture. Majority voting was performed to determine the results of the sub-window classifiers. Blob analysis was performed to merge multiple detections for the same fruit. For the validation set, 75.3% of the actual fruits were successfully detected using the proposed algorithm.     

Citrus fruits maturity detection in natural environments based on convolutional neural networks and visual saliency map

Citrus fruits do not ripen at the same time in natural environments and exhibit different maturity stages on trees, hence it is necessary to realize selective harvesting of citrus picking robots. The visual attention mechanism reveals a physiological phenomenon that human eyes usually focus on a region that is salient from its surround. The degree to which a region contrasts with its surround is called visual saliency. This study proposes a novel citrus fruit maturity method combining visual saliency and convolutional neural networks to identify three maturity levels of citrus fruits. The proposed method is divided into two stages: the detection of citrus fruits on trees and the detection of fruit maturity. In stage one, the object detection network YOLOv5 was used to identify the citrus fruits in the image. In stage two, a visual saliency detection algorithm was improved and generated saliency maps of the fruits; The information of RGB images and the saliency maps were combined to determine the fruit maturity class using 4-channel ResNet34 network. The comparison experiments were conducted around the proposed method and the common RGB-based machine learning and deep learning methods. The experimental results show that the proposed method yields an accuracy of 95.07%, which is higher than the best RGB-based CNN model, VGG16, and the best machine learning model, KNN, about 3.14% and 18.24%, respectively. The results prove the validity of the proposed fruit maturity detection method and that this work can provide technical support for intelligent visual detection of selective harvesting robots.

     

Fruit detection in natural environment using partial shape matching and probabilistic Hough transform

Precision Agriculture - This paper proposes a novel technique for fruit detection in natural environments which is applicable in automatic harvesting robots, yield estimation systems and quality...     

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.

     

Hyperspectral discrimination of foliar biotic damages in rice using principal component analysis and probabilistic neural network

Assessment of crop health status in real time could provide reliable and useful information for making effective and efficient management decisions regarding the appropriate time and method to control crop diseases and insect damage. In this study, hyperspectral reflectance of symptomatic and asymptomatic rice leaves infected by Pyricularia grisea Sacc, Bipolaris oryzae Shoem, Aphelenchoides besseyi Christie and Cnaphalocrocis medinalis Guen was measured in a laboratory within the 350–2?500 nm spectral region. Principal component analysis was performed to obtain the principal component spectra (PCs) of different transformations of the original spectra, including original (R), common logarithm of reciprocal (lg (1/R)), and the first derivative of original and common logarithm of reciprocal spectra (R′ and (lg (1/R))′). A probabilistic neural network classifier was applied to discriminate the symptomatic rice leaves from asymptomatic ones with the front PCs. For identifying symptomatic and asymptomatic rice leaves, the mean overall discrimination accuracies for R, lg (1/R), R′ and (lg (1/R))′ were 91.3, 93.1, 92.3 and 92%, and the mean Kappa coefficients were 0.771, 0.835, 0.829 and 0.82, respectively. To discriminate between disease and insect damage, the overall accuracies for R, lg (1/R), R′ and (lg (1/R))′ were 97.7, 98.1, 100 and 100%, and the Kappa coefficients were 0.962, 0.97, 1 and 1, respectively. These results demonstrated that hyperspectral remote sensing can discriminate between multiple diseases and the insect damage of rice leaves under laboratory conditions.     

Virus population dynamics and acquired virus resistance in natural microbial communities

Viruses shape microbial community structure and function by altering the fitness of their hosts and by promoting genetic exchange. The complexity of most natural ecosystems has precluded detailed studies of virus-host interactions. We reconstructed virus and host bacterial and archaeal genome sequences from community genomic data from two natural acidophilic biofilms. Viruses were matched to their hosts by analyzing spacer sequences that occur among clustered regularly interspaced short palindromic repeats (CRISPRs) that are a hallmark of virus resistance. Virus population genomic analyses provided evidence that extensive recombination shuffles sequence motifs sufficiently to evade CRISPR spacers. Only the most recently acquired spacers match coexisting viruses, which suggests that community stability is achieved by rapid but compensatory shifts in host resistance levels and virus population structure.     

Classification of sugar beet and volunteer potato reflection spectra with a neural network and statistical discriminant analysis to select discriminative wavelengths

The objectives of this study were to determine the reflectance properties of volunteer potato and sugar beet and to assess the potential of separating sugar beet and volunteer potato at different fields and in different years, using spectral reflectance characteristics. With the ImspectorMobile, vegetation reflection spectra were successfully repeatedly gathered in two fields, on seven days in 2 years that resulted in 11 datasets. Both in the visible and in the near-infrared reflection region, combinations of wavelengths were responsible for discrimination between sugar beet and volunteer potato plants. Two feature selection methods, discriminant analysis (DA) and neural network (NN), succeeded in selecting sets of discriminative wavebands, both for the range of 450-900 and 900-1650 nm. First, 10 optimal wavebands were selected for each of the 11 available datasets individually. Second, by calculating the discriminative power of each selected waveband, 10 fixed wavebands were selected for all 11 datasets analyses. Third, 3 fixed wavebands were determined for all 11 datasets. These three wavebands were chosen because these had been selected by both DA and NN and were for sensor 1: 450, 765, and 855 nm and for sensor 2: 900, 1440, and 1530 nm. With the resulting three sets of wavebands, classifications were performed with a DA, a neural network with 1 hidden neuron (NN1) and a neural network with two hidden neurons (NN2). The maximum classification performance was obtained with the near-infrared sensor coupled to the NN2 method with an optimal adapted set of 10 wavebands, where the percentages were 100 ± 0.1 and 1 ± 1.3% for true negative (TN) classified volunteer potato plants and false negative (FN) classified sugar beet plants respectively. In general the NN2 method gave the best classification results, followed by DA and finally the NN1 method. When the optimal adapted waveband sets were generalized to a set of 10 fixed wavebands, the classification results were still at a reasonable level of a performance at 87% TN and 1% FN for the NN2 classification method. However, when a further reduction and generalization was made to 3 fixed wavebands, the classification results were poor with a minimum performance of 69% TN and 3% FN for the NN2 classification method. So, these results indicate that for the best classification results it is required that the sensor and classification system adapt to the specific field situation, to optimally discriminate between volunteer potato and sugar beet pixel spectra.     

高效液相色谱-二极管阵列检测器法测定水蜜桃中水溶性有机酸和维生素的含量

采用高效液相色谱-二极管阵列检测器法(HPLC-DAD) 同时检测水蜜桃中水溶性有机酸和维生素含量.样品经纯水超声波提取、离心和膜过滤,ZORBAX SB-C18(4.6 mm×250 mm,5μm) 液相色谱柱分离,以0.5 mmol·L-1磷酸-乙腈梯度洗脱,流速0.8 mL·min-1;二极管阵列检测器(DAD) 同时以210 nm波长检测苹果酸、柠檬酸、琥珀酸,254 nm波长检测烟酸、维生素C、维生素B1,270 nm波长检测维生索B2.结果显示:待测成分在8 min内达到良好的基线分离,线性范围广,苹果酸、柠檬酸、琥珀酸的检出限为0.5μg·mL-1,烟酸、维生素C、维生素B.的检出限为0.1μg·mL-1,维牛素B2的检出限为0.05 μg·mL-1.方法的加标同收率为97.0%～102.3%,线性相关系数为0.999 3～0.999 9,精确度平均偏差0.33%～1.97%.该方法适用于水蜜桃样品中多种水溶性有机酸和维生素的同时测定.     

Detection of biotic and abiotic stresses in crops by using hierarchical self organizing classifiers

Hyperspectral signatures can provide abundant information regarding health status of crops; however it is difficult to discriminate between biotic and abiotic stress. In this study, the case of simultaneous occurrence of yellow rust disease symptoms and nitrogen stress was investigated by using hyperspectral features from a ground based hyperspectral imaging system. Hyperspectral images of healthy and diseased plant canopies were taken at Rothamsted Research, UK by a Specim V10 spectrograph. Five wavebands of 20 nm width were utilized for accurate identification of each of the stress and healthy plant conditions. The technique that was developed used a hybrid classification scheme consisting of hierarchical self organizing classifiers. Three different architectures were considered: counter-propagation artificial neural networks, supervised Kohonen networks (SKNs) and XY-fusion. A total of 12 120 spectra were collected. From these 3 062 (25.3%) were used for testing. The results of biotic and abiotic stress identification appear to be promising, reaching more than 95% for all three architectures. The proposed approach aimed at sensor based detection of diseased and stressed plants so that can be treated site specifically contributing to a more effective and precise application of fertilizers and fungicides according to specific plant’s needs.     

Combination of the natural and anthropogenically-controlled conditions for obtaining various rice yield using drip irrigation systems

The possibility to use drip irrigation systems to cultivate rice with periodic irrigation based on the results of the researches carried out in 2013–2015 is shown. The test was conducted on the crops of aerobic rice of the Volgogradskii variety according to the two-factorial scheme, including three variants of the soil water mode with the constant and differentiated preirrigation threshold and soil moistening layer and three variants of macrofertilizer rates calculated for collecting 5, 6, and 7 t of grain from 1 ha. On average for the years of experiments, the rice yield depending on the studied factor changed from 5.13 to 6.87 t/ha at the irrigation rate 4440–6060 m³/ha. To obtain 5 t/ha, 6 t/ha, and 7 t/ha, the irrigation water consumption totaled 1013—959 m³/t, 860–805 m³/t, and 771–716 m³/t. The profitability of rice production according to such technology achieved 57.3–116.5% depending on the yield.     

银川地区日光温室桃树促早栽培适宜扣棚及升温时期探讨

为了研究银川地区桃树设施栽培适宜的扣棚及升温时间,对银川市历年(1971～2000年)以及近两年(2008～2009年)10、11、12月份室外温度数据进行分析,得出宁夏地区日光温室果树促早栽培的适宜扣棚时间为10月26日左右;通过对宁夏设施4个桃树主栽品种室内萌芽状况以及温度观测,借助犹它模型(Utah model)...     

Artificial neural network implementation in single low-cost chip for the detection of insecticides by modeling of screen-printed enzymatic sensors response

This work presents a hardware implementation of artificial neural networks (ANNs) using a dsPIC^® microcontroller to resolve mixtures of pesticides measured by amperometric acetylcholinesterase (AChE) biosensors. The response of three biosensors with different concentrations of Chlorpyrifos Oxon (CPO) and Chlorfenvinfos (CFV) was modeled by two ANNs, which were implemented on the dsPIC^®. The performance of the ANNs was good, the prediction ability was better than 0.986 when the obtained values were compared with those expected for a set of eight external test samples, which were not used for training. This implementation is proposed to develop low-cost analytical chemical specialized tools.     

Optimization of an artificial neural network topology using coupled response surface methodology and genetic algorithm for fluidized bed drying

In this study, an integrated response surface methodology (RSM) and genetic algorithm (GA) are recommended for developing artificial neural networks (ANNs) with great chances to be an optimal one. A multi-layer feed forward (MLFF) ANN was applied to correlate the outputs (energy and exergy) to the four exogenous inputs (drying time, drying air temperature, carrot cubes size, and bed depth). The RSM was used to build the relationship between the input parameters and output responses, and used as the fitness function to measure the fitness value of the GA approach. In the relationship building, five variables were used (number of neurons, momentum coefficient and step size in the hidden layer, number of epochs and number of training times). A polynomial model was developed from training results to mean square error (MSE) of 50 developed ANNs to generate 3D response surfaces and contour plots. Finally, GA was applied to find the optimal topology of ANN. The ANN topology had minimum MSE when the number of neurons in the hidden layer, momentum coefficient, step size, number of training epochs and training times were 28, 0.66, 0.35, 2877 and 3, respectively. The energy and exergy of carrot cubes during fluidized bed drying were predicted with R² values of greater than 0.97 using optimal ANN topology.     

粗糙集和神经网络理论在数据挖掘中的应用分析

本文对数据挖掘的两种重要新方法粗糙集理论和神经网络以及它们的应用进行了分析、比较,总结出每种算法的性能特征,以便于使用者了解掌握各种分类算法、更好地选择合适的算法。     

A shadow detection and removal method for fruit recognition in natural environments

Precision Agriculture - Effective shadow detection and shadow removal can improve the performance of fruit recognition in natural environments and provide technical support for agricultural...     

贵州县域自然条件比较分析

为因地制宜发展农业生产、协调区域发展和进行宏观决策提供自然条件依据，对贵州省87个县级区域的8个自然因素进行比较排序，所得结果证实，自然条件较优的多数县域较集中分布于贵阳、遵义和安顺3个市的中心区附近，位于贵州高原主体部分，与全省综合农业区划所指出的“黔中区”相一致。而自然条件较差的县域一般分散分布于周边的鸟蒙山、北盘江下游与红水河流域、雷公山与月亮山、武陵山、大娄山等山区。说明贫困山区分布较广，贫困面较大。