Estimating litchi flower number using a multicolumn convolutional neural network based on a density map

Lin, Jiaquan; Li, Jun; Yang, Zhou; Lu, Huazhong; Ding, Yue; Cui, Huajun

doi:10.1007/s11119-022-09882-7

Cited by 12 publications

(8 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[ 38 ], the 5-column neural network (FCNN) proposed by Lin et al. [ 29 ], and the CSRNet proposed by Li et al. [ 39 ].…”

Section: Resultsmentioning

confidence: 99%

“…Additionally, researchers have implemented density map regression to count litchi flowers. This method directly obtains the flower count through the model without requiring predictions of target size or location [ 29 ]. Nevertheless, density map regression, being a pixel-level task, is highly sensitive to input image information and may introduce noise in nontarget areas, thereby reducing the count accuracy.…”

Section: Discussionmentioning

confidence: 99%

“…2 B. Eventually, during the image annotation stage, the Litchi male flowers were point-annotated using LabelMe software [ 30 ], following Lin’s annotation method [ 29 ]. The flowers in the images exhibited diverse forms resulting from their natural growth patterns.…”

Section: Methodsmentioning

confidence: 99%

“…To address the problem of difficult counting since litchi trees have small flowers that bloom in large numbers, Lin et al. [ 29 ] proposed a litchi flower counting method that utilizes density map regression. They investigated techniques for constructing flower count density map datasets and trained multiple column CNNs to directly obtain litchi flower count density maps from RGB images.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Framework for Single-Panicle Litchi Flower Counting by Regression with Multitask Learning

Lin,

Li,

et al. 2024

Plant Phenomics

Self Cite

View full text Add to dashboard Cite

The number of flowers is essential for evaluating the growth status of litchi trees and enables researchers to estimate flowering rates and conduct various phenotypic studies, particularly focusing on the information of individual panicles. However, manual counting remains the primary method for quantifying flowers, and there has been insufficient emphasis on the advancement of reliable deep learning methods for estimation and their integration into research. Furthermore, the current density map-based methods are susceptible to background interference. To tackle the challenges of accurately quantifying small and dense male litchi flowers, a framework counting the flowers in panicles is proposed. Firstly, an existing effective algorithm YOLACT++ is utilized to segment individual panicles from images. Secondly, a novel algorithm FlowerNet based on density map regression is proposed to accurately count flowers in each panicle. By employing a multitask learning approach, FlowerNet effectively captures both foreground and background information, thereby overcoming interference from non-target areas during pixel-level regression tasks. It achieves a mean absolute error of 47.71 and a root mean squared error of 61.78 on the flower dataset constructed. Additionally, a regression equation is established using a dataset of inflorescences to examine the application of the algorithm for flower counting. It captures the relationship between the predicted number of flowers by FlowerNet and the manually counted number, resulting in a determination coefficient ( R 2 ) of 0.81. The proposed algorithm shows promise for automated estimation of litchi flowering quantity and can serve as a valuable reference for litchi orchard management during flowering period.

show abstract

“…[ 38 ], the 5-column neural network (FCNN) proposed by Lin et al. [ 29 ], and the CSRNet proposed by Li et al. [ 39 ].…”

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Framework for Single-Panicle Litchi Flower Counting by Regression with Multitask Learning

Lin,

Li,

et al. 2024

Plant Phenomics

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the growth and production of litchi trees, fruit yield is affected by various factors, such as the climate, fertilizer and irrigation ( Yang et al, 2015 ; Zhu, 2020 ). Many studies have shown that together with the external factors above, the number of litchi flowers, an internal factor, directly impacts litchi fruit yields as well as fruit colour and weight; too many or too few flowers is not conducive to the growth of litchi trees ( Lin J. et al, 2022 ). Therefore, regulating the number of litchi flowers plays a key role in the management of litchi florescence.…”

Section: Introductionmentioning

confidence: 99%

A novel approach for estimating the flowering rate of litchi based on deep learning and UAV images

Lin

Jia

et al. 2022

Front. Plant Sci.

Self Cite

View full text Add to dashboard Cite

Litchi flowering management is an important link in litchi orchard management. Statistical litchi flowering rate data can provide an important reference for regulating the number of litchi flowers and directly determining the quality and yield of litchi fruit. At present, the statistical work regarding litchi flowering rates requires considerable labour costs. Therefore, this study aims at the statistical litchi flowering rate task, and a combination of unmanned aerial vehicle (UAV) images and computer vision technology is proposed to count the numbers of litchi flower clusters and flushes in a complex natural environment to improve the efficiency of litchi flowering rate estimation. First, RGB images of litchi canopies at the flowering stage are collected by a UAV. After performing image preprocessing, a dataset is established, and two types of objects in the images, namely, flower clusters and flushes, are manually labelled. Second, by comparing the pretraining and testing results obtained when setting different training parameters for the YOLOv4 model, the optimal parameter combination is determined. The YOLOv4 model trained with the optimal combination of parameters tests best on the test set, at which time the mean average precision (mAP) is 87.87%. The detection time required for a single image is 0.043 s. Finally, aiming at the two kinds of targets (flower clusters and flushes) on 8 litchi trees in a real orchard, a model for estimating the numbers of flower clusters and flushes on a single litchi tree is constructed by matching the identified number of targets with the actual number of targets via equation fitting. Then, the data obtained from the manual counting process and the estimation model for the other five litchi trees in the real orchard are statistically analysed. The average error rate for the number of flower clusters is 4.20%, the average error rate for the number of flushes is 2.85%, and the average error for the flowering rate is 1.135%. The experimental results show that the proposed method is effective for estimating the litchi flowering rate and can provide guidance regarding the management of the flowering periods of litchi orchards.

show abstract

A vision transformer‐based robotic perception for early tea chrysanthemum flower counting in field environments

Qi,

Chen,

Gao

2024

Journal of Field Robotics

View full text Add to dashboard Cite

The current mainstream approaches for plant organ counting are based on convolutional neural networks (CNNs), which have a solid local feature extraction capability. However, CNNs inherently have difficulties for robust global feature extraction due to limited receptive fields. Visual transformer (ViT) provides a new opportunity to complement CNNs' capability, and it can easily model global context. In this context, we propose a deep learning network based on a convolution‐free ViT backbone (tea chrysanthemum‐visual transformer [TC‐ViT]) to achieve the accurate and real‐time counting of TCs at their early flowering stage under unstructured environments. First, all cropped fixed‐size original image patches are linearly projected into a one‐dimensional vector sequence and fed into a progressive multiscale ViT backbone to capture multiple scaled feature sequences. Subsequently, the obtained feature sequences are reshaped into two‐dimensional image features and using a multiscale perceptual field module as a regression head to detect the overall scale and density variance. The resulting model was tested on 400 field images in the collected TC test data set, showing that the proposed TC‐ViT achieved the mean absolute error and mean square error of 12.32 and 15.06, with the inference speed of 27.36 FPS (512 × 512 image size) under the NVIDIA Tesla V100 GPU environment. It is also shown that light variation had the greatest effect on TC counting, whereas blurring had the least effect. This proposed method enables accurate counting for high‐density and occlusion objects in field environments and this perception system could be deployed in a robotic platform for selective harvesting and flower phenotyping.

show abstract

Estimating litchi flower number using a multicolumn convolutional neural network based on a density map

Cited by 12 publications

References 34 publications

A Framework for Single-Panicle Litchi Flower Counting by Regression with Multitask Learning

A Framework for Single-Panicle Litchi Flower Counting by Regression with Multitask Learning

A novel approach for estimating the flowering rate of litchi based on deep learning and UAV images

A vision transformer‐based robotic perception for early tea chrysanthemum flower counting in field environments

Contact Info

Product

Resources

About