Fruit traits such as cluster compactness,fruit maturity,and berry number per clusters are important to blueberry breeders and producers for making informed decisions about genotype selection related to yield traits an...Fruit traits such as cluster compactness,fruit maturity,and berry number per clusters are important to blueberry breeders and producers for making informed decisions about genotype selection related to yield traits and harvestability as well as for plant management.The goal of this study was to develop a data processing pipeline to count berries,to measure maturity,and to evaluate compactness(cluster tightness)automatically using a deep learning image segmentation method for four southern highbush blueberry cultivars(‘Emerald’,‘Farthing’,‘Meadowlark’,and‘Star’).An iterative annotation strategy was developed to label images that reduced the annotation time.A Mask R-CNN model was trained and tested to detect and segment individual blueberries with respect to maturity.The mean average precision for the validation and test dataset was 78.3%and 71.6%under 0.5 intersection over union(IOU)threshold,and the corresponding mask accuracy was 90.6%and 90.4%,respectively.Linear regression of the detected berry number and the ground truth showed an R2 value of 0.886 with a root mean square error(RMSE)of 1.484.Analysis of the traits collected from the four cultivars indicated that‘Star’had the fewest berries per clusters,‘Farthing’had the least mature fruit in mid-April,‘Farthing’had the most compact clusters,and‘Meadowlark’had the loosest clusters.The deep learning image segmentation technique developed in this study is efficient for detecting and segmenting blueberry fruit,for extracting traits of interests related to machine harvestability,and for monitoring blueberry fruit development.展开更多
传统的图像聚类方法存在对初始数据敏感且计算复杂度高的问题,且图像全局特征难以有效地表达图像内容。针对这些问题,提出一种基于Union-Find的图像聚类方法。首先,该方法采用视觉词袋模型Bo VWM(Bag of Visual Words Model)来描述图像...传统的图像聚类方法存在对初始数据敏感且计算复杂度高的问题,且图像全局特征难以有效地表达图像内容。针对这些问题,提出一种基于Union-Find的图像聚类方法。首先,该方法采用视觉词袋模型Bo VWM(Bag of Visual Words Model)来描述图像内容并且利用投票方法来计算每对图像的相似度得分;然后,对于相似度得分大于给定阈值的图像对进行union和find两个操作并将相连的分量形成聚类结果。实验结果表明,该方法较之于传统方法能较好地改善图像聚类效果,且不需要初始聚类数目作为先验参数。展开更多
Based on detailed analysis of advantages and disadvantages of the existing connected-component labeling (CCL) algorithm,a new algorithm for binary connected components labeling based on run-length encoding (RLE) a...Based on detailed analysis of advantages and disadvantages of the existing connected-component labeling (CCL) algorithm,a new algorithm for binary connected components labeling based on run-length encoding (RLE) and union-find sets has been put forward.The new algorithm uses RLE as the basic processing unit,converts the label merging of connected RLE into sets grouping in accordance with equivalence relation,and uses the union-find sets which is the realization method of sets grouping to solve the label merging of connected RLE.And the label merging procedure has been optimized:the union operation has been modified by adding the "weighted rule" to avoid getting a degenerated-tree,and the "path compression" has been adopted when implementing the find operation,then the time complexity of label merging is O(nα(n)).The experiments show that the new algorithm can label the connected components of any shapes very quickly and exactly,save more memory,and facilitate the subsequent image analysis.展开更多
A fast label-equivalence-based connected components labeling algorithm is proposed in this paper.It is a combination of two existing efficient methods,which are pivotal operations in two-pass connected components labe...A fast label-equivalence-based connected components labeling algorithm is proposed in this paper.It is a combination of two existing efficient methods,which are pivotal operations in two-pass connected components labeling algorithms.One is a fast pixel scan method,and the other is an array-based Union-Find data structure.The scan procedure assigns each foreground pixel a provisional label according to the location of the pixel.That is to say,it labels the foreground pixels following background pixels and foreground pixels in different ways,which greatly reduces the number of neighbor pixel checks.The array-based Union-Find data structure resolves the label equivalences between provisional labels by using only a single array with path compression,and it improves the efficiency of the resolving procedure which is very time-consuming in general label-equivalence-based algorithms.The experiments on various types of images with different sizes show that the proposed algorithm is superior to other labeling approaches for huge images containing many big connected components.展开更多
Study on the evaluation system for multi-source image fusion is an important and necessary part of image fusion. Qualitative evaluation indexes and quantitative evaluation indexes were studied. A series of new concept...Study on the evaluation system for multi-source image fusion is an important and necessary part of image fusion. Qualitative evaluation indexes and quantitative evaluation indexes were studied. A series of new concepts, such as independent single evaluation index, union single evaluation index, synthetic evaluation index were proposed. Based on these concepts, synthetic evaluation system for digital image fusion was formed. The experiments with the wavelet fusion method, which was applied to fuse the multi-spectral image and panchromatic remote sensing image, the IR image and visible image, the CT and MRI image, and the multi-focus images show that it is an objective, uniform and effective quantitative method for image fusion evaluation.展开更多
Crop-type identification is one of the most significant applications of agricultural remote sensing,and it is important for yield estimation prediction and field management.At present,crop identification using dataset...Crop-type identification is one of the most significant applications of agricultural remote sensing,and it is important for yield estimation prediction and field management.At present,crop identification using datasets from unmanned aerial vehicle(UAV)and satellite platforms have achieved state-of-the-art performances.However,accurate monitoring of small plants,such as the coffee flower,cannot be achieved using datasets from these platforms.With the development of time-lapse image acquisition technology based on ground-based remote sensing,a large number of small-scale plantation datasets with high spatial-temporal resolution are being generated,which can provide great opportunities for small target monitoring of a specific region.The main contribution of this paper is to combine the binarization algorithm based on OTSU and the convolutional neural network(CNN)model to improve coffee flower identification accuracy using the time-lapse images(i.e.,digital images).A certain number of positive and negative samples are selected from the original digital images for the network model training.Then,the pretrained network model is initialized using the VGGNet and trained using the constructed training datasets.Based on the well-trained CNN model,the coffee flower is initially extracted,and its boundary information can be further optimized by using the extracted coffee flower result of the binarization algorithm.Based on the digital images with different depression angles and illumination conditions,the performance of the proposed method is investigated by comparison of the performances of support vector machine(SVM)and CNN model.Hence,the experimental results show that the proposed method has the ability to improve coffee flower classification accuracy.The results of the image with a 52.5°angle of depression under soft lighting conditions are the highest,and the corresponding Dice(F1)and intersection over union(IoU)have reached 0.80 and 0.67,respectively.展开更多
Remote sensing images are taken at high altitude from above,with complex spatial scenes of images and a large number of target types.The detection of image targets on large scale remote sensing images suffers from the...Remote sensing images are taken at high altitude from above,with complex spatial scenes of images and a large number of target types.The detection of image targets on large scale remote sensing images suffers from the problem of small target size and target density.This paper proposes an improved model for remote sensing image detection based on you only look once version 7(YOLOv7).First,the small-scale detection layer is added to reacquire tracking frames to improve the network’s recognition ability of small-scale targets,and then Bottleneck Transformers are fused in the backbone to make full use of the convolutional neural network(CNN)+Transformer architecture to enhance the feature extraction ability of the network.After that,the convolutional block attention module(CBAM)mechanism is added in the head to improve the model’s ability of small-scale target.Finally,the non-maximum suppressed(NMS)of YOLOv7 algorithm is changed to distance intersection over union-non maximum suppression(DIOU-NMS)to improve the detection ability of overlapping targets in the network.The results show that the method in this paper can improve the detection rate of small-scale targets in remote sensing images and effectively solve the problem of high overlap and is tested on the NWPU-VHR10 and DOTA1.0 datasets,and the accuracy of the improved model is improved by 6.3%and 4.2%,respectively,compared with the standard YOLOv7 algorithm.展开更多
Microplot extraction(PE)is a necessary image processing step in unmanned aerial vehicle-(UAV-)based research on breeding fields.At present,it is manually using ArcGIS,QGIS,or other GIS-based software,but achieving the...Microplot extraction(PE)is a necessary image processing step in unmanned aerial vehicle-(UAV-)based research on breeding fields.At present,it is manually using ArcGIS,QGIS,or other GIS-based software,but achieving the desired accuracy is timeconsuming.We therefore developed an intuitive,easy-to-use semiautomatic program for MPE called Easy MPE to enable researchers and others to access reliable plot data UAV images of whole fields under variable field conditions.The program uses four major steps:(1)binary segmentation,(2)microplot extraction,(3)production of∗.shp files to enable further file manipulation,and(4)projection of individual microplots generated from the orthomosaic back onto the raw aerial UAV images to preserve the image quality.Crop rows were successfully identified in all trial fields.The performance of the proposed method was evaluated by calculating the intersection-over-union(IOU)ratio between microplots determined manually and by Easy MPE:the average IOU(±SD)of all trials was 91%(±3).展开更多
基金supported by the USDA National Institute of Food and Agriculture Specialty Crop Research Initiative(Award No:2014-51181-22383).
文摘Fruit traits such as cluster compactness,fruit maturity,and berry number per clusters are important to blueberry breeders and producers for making informed decisions about genotype selection related to yield traits and harvestability as well as for plant management.The goal of this study was to develop a data processing pipeline to count berries,to measure maturity,and to evaluate compactness(cluster tightness)automatically using a deep learning image segmentation method for four southern highbush blueberry cultivars(‘Emerald’,‘Farthing’,‘Meadowlark’,and‘Star’).An iterative annotation strategy was developed to label images that reduced the annotation time.A Mask R-CNN model was trained and tested to detect and segment individual blueberries with respect to maturity.The mean average precision for the validation and test dataset was 78.3%and 71.6%under 0.5 intersection over union(IOU)threshold,and the corresponding mask accuracy was 90.6%and 90.4%,respectively.Linear regression of the detected berry number and the ground truth showed an R2 value of 0.886 with a root mean square error(RMSE)of 1.484.Analysis of the traits collected from the four cultivars indicated that‘Star’had the fewest berries per clusters,‘Farthing’had the least mature fruit in mid-April,‘Farthing’had the most compact clusters,and‘Meadowlark’had the loosest clusters.The deep learning image segmentation technique developed in this study is efficient for detecting and segmenting blueberry fruit,for extracting traits of interests related to machine harvestability,and for monitoring blueberry fruit development.
文摘传统的图像聚类方法存在对初始数据敏感且计算复杂度高的问题,且图像全局特征难以有效地表达图像内容。针对这些问题,提出一种基于Union-Find的图像聚类方法。首先,该方法采用视觉词袋模型Bo VWM(Bag of Visual Words Model)来描述图像内容并且利用投票方法来计算每对图像的相似度得分;然后,对于相似度得分大于给定阈值的图像对进行union和find两个操作并将相连的分量形成聚类结果。实验结果表明,该方法较之于传统方法能较好地改善图像聚类效果,且不需要初始聚类数目作为先验参数。
文摘Based on detailed analysis of advantages and disadvantages of the existing connected-component labeling (CCL) algorithm,a new algorithm for binary connected components labeling based on run-length encoding (RLE) and union-find sets has been put forward.The new algorithm uses RLE as the basic processing unit,converts the label merging of connected RLE into sets grouping in accordance with equivalence relation,and uses the union-find sets which is the realization method of sets grouping to solve the label merging of connected RLE.And the label merging procedure has been optimized:the union operation has been modified by adding the "weighted rule" to avoid getting a degenerated-tree,and the "path compression" has been adopted when implementing the find operation,then the time complexity of label merging is O(nα(n)).The experiments show that the new algorithm can label the connected components of any shapes very quickly and exactly,save more memory,and facilitate the subsequent image analysis.
基金Sponsored by the National Natural Science Foundation of China (Grant No. 81071219)
文摘A fast label-equivalence-based connected components labeling algorithm is proposed in this paper.It is a combination of two existing efficient methods,which are pivotal operations in two-pass connected components labeling algorithms.One is a fast pixel scan method,and the other is an array-based Union-Find data structure.The scan procedure assigns each foreground pixel a provisional label according to the location of the pixel.That is to say,it labels the foreground pixels following background pixels and foreground pixels in different ways,which greatly reduces the number of neighbor pixel checks.The array-based Union-Find data structure resolves the label equivalences between provisional labels by using only a single array with path compression,and it improves the efficiency of the resolving procedure which is very time-consuming in general label-equivalence-based algorithms.The experiments on various types of images with different sizes show that the proposed algorithm is superior to other labeling approaches for huge images containing many big connected components.
基金National Natural Science Foundation ofChina (No. 60375008) Shanghai EXPOSpecial Project ( No.2004BA908B07 )Shanghai NRC International CooperationProject (No.05SN07118)
文摘Study on the evaluation system for multi-source image fusion is an important and necessary part of image fusion. Qualitative evaluation indexes and quantitative evaluation indexes were studied. A series of new concepts, such as independent single evaluation index, union single evaluation index, synthetic evaluation index were proposed. Based on these concepts, synthetic evaluation system for digital image fusion was formed. The experiments with the wavelet fusion method, which was applied to fuse the multi-spectral image and panchromatic remote sensing image, the IR image and visible image, the CT and MRI image, and the multi-focus images show that it is an objective, uniform and effective quantitative method for image fusion evaluation.
基金This work was supported by the National Science Foundation of China(41471277).
文摘Crop-type identification is one of the most significant applications of agricultural remote sensing,and it is important for yield estimation prediction and field management.At present,crop identification using datasets from unmanned aerial vehicle(UAV)and satellite platforms have achieved state-of-the-art performances.However,accurate monitoring of small plants,such as the coffee flower,cannot be achieved using datasets from these platforms.With the development of time-lapse image acquisition technology based on ground-based remote sensing,a large number of small-scale plantation datasets with high spatial-temporal resolution are being generated,which can provide great opportunities for small target monitoring of a specific region.The main contribution of this paper is to combine the binarization algorithm based on OTSU and the convolutional neural network(CNN)model to improve coffee flower identification accuracy using the time-lapse images(i.e.,digital images).A certain number of positive and negative samples are selected from the original digital images for the network model training.Then,the pretrained network model is initialized using the VGGNet and trained using the constructed training datasets.Based on the well-trained CNN model,the coffee flower is initially extracted,and its boundary information can be further optimized by using the extracted coffee flower result of the binarization algorithm.Based on the digital images with different depression angles and illumination conditions,the performance of the proposed method is investigated by comparison of the performances of support vector machine(SVM)and CNN model.Hence,the experimental results show that the proposed method has the ability to improve coffee flower classification accuracy.The results of the image with a 52.5°angle of depression under soft lighting conditions are the highest,and the corresponding Dice(F1)and intersection over union(IoU)have reached 0.80 and 0.67,respectively.
基金supported by the National Natural Science Foundation of China(Nos.62005196 and 61974104)。
文摘Remote sensing images are taken at high altitude from above,with complex spatial scenes of images and a large number of target types.The detection of image targets on large scale remote sensing images suffers from the problem of small target size and target density.This paper proposes an improved model for remote sensing image detection based on you only look once version 7(YOLOv7).First,the small-scale detection layer is added to reacquire tracking frames to improve the network’s recognition ability of small-scale targets,and then Bottleneck Transformers are fused in the backbone to make full use of the convolutional neural network(CNN)+Transformer architecture to enhance the feature extraction ability of the network.After that,the convolutional block attention module(CBAM)mechanism is added in the head to improve the model’s ability of small-scale target.Finally,the non-maximum suppressed(NMS)of YOLOv7 algorithm is changed to distance intersection over union-non maximum suppression(DIOU-NMS)to improve the detection ability of overlapping targets in the network.The results show that the method in this paper can improve the detection rate of small-scale targets in remote sensing images and effectively solve the problem of high overlap and is tested on the NWPU-VHR10 and DOTA1.0 datasets,and the accuracy of the improved model is improved by 6.3%and 4.2%,respectively,compared with the standard YOLOv7 algorithm.
基金This work was partly funded by the CREST Program“Knowledge Discovery by Constructing AgriBigData”(JPMJCR1512)the SICORP Program“Data Science-Based Farming Support System for Sustainable Crop Production under Climatic Change”of the Japan Science and Technology Agency and the“Smart-Breeding System for Innovative Agriculture (BAC3001)”of the Ministry of Agriculture,Forestry and Fisheries of Japan.
文摘Microplot extraction(PE)is a necessary image processing step in unmanned aerial vehicle-(UAV-)based research on breeding fields.At present,it is manually using ArcGIS,QGIS,or other GIS-based software,but achieving the desired accuracy is timeconsuming.We therefore developed an intuitive,easy-to-use semiautomatic program for MPE called Easy MPE to enable researchers and others to access reliable plot data UAV images of whole fields under variable field conditions.The program uses four major steps:(1)binary segmentation,(2)microplot extraction,(3)production of∗.shp files to enable further file manipulation,and(4)projection of individual microplots generated from the orthomosaic back onto the raw aerial UAV images to preserve the image quality.Crop rows were successfully identified in all trial fields.The performance of the proposed method was evaluated by calculating the intersection-over-union(IOU)ratio between microplots determined manually and by Easy MPE:the average IOU(±SD)of all trials was 91%(±3).