Fumiki Hosoi

Prof. Dr. Fumiki Hosoi


Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 February 2011 in Sensors
Verified
Journal Article
Open access
PDF file
FHFumiki Hosoi
Fumiki Hosoi
KNKazushige Nakabayashi
Kazushige Nakabayashi
Kenji OmasaKenji Omasa
Kenji Omasa
In the present study, an attempt was made to produce a precise 3D image of a tomato canopy using a portable high-resolution scanning lidar. The tomato canopy was scanned by the lidar from three positions surrounding it. Through the scanning, the point cloud data of the canopy were obtained and they were co-registered. Then, points corresponding to leaves were extracted and converted into polygon images. From the polygon images, leaf areas were accurately estimated with a mean absolute percent error of 4.6%. Vertical profile of leaf area density (LAD) and leaf area index (LAI) could be also estimated by summing up each leaf area derived from the polygon images. Leaf inclination angle could be also estimated from the 3-D polygon image. It was shown that leaf inclination angles had different values at each part of a leaf.

22 October 2018 in Sensors
Verified
Journal Article
Open access
PDF file
KIKenta Itakura
Kenta Itakura
FHFumiki Hosoi
Fumiki Hosoi
Automatic and efficient plant monitoring offers accurate plant management. Construction of three-dimensional (3D) models of plants and acquisition of their spatial information is an effective method for obtaining plant structural parameters. Here, 3D images of leaves constructed with multiple scenes taken from different positions were segmented automatically for the automatic retrieval of leaf areas and inclination angles. First, for the initial segmentation, leave images were viewed from the top, then leaves in the top-view images were segmented using distance transform and the watershed algorithm. Next, the images of leaves after the initial segmentation were reduced by 90%, and the seed regions for each leaf were produced. The seed region was re-projected onto the 3D images, and each leaf was segmented by expanding the seed region with the 3D information. After leaf segmentation, the leaf area of each leaf and its inclination angle were estimated accurately via a voxel-based calculation. As a result, leaf area and leaf inclination angle were estimated accurately after automatic leaf segmentation. This method for automatic plant structure analysis allows accurate and efficient plant breeding and growth management.

9 February 2019 in Remote Sensing
Verified
Journal Article
Open access
PDF file
KIKenta Itakura
Kenta Itakura
FHFumiki Hosoi
Fumiki Hosoi
The leaf inclination angle is a fundamental variable for determining the plant profile. In this study, the leaf inclination angle was estimated automatically from voxel-based three-dimensional (3D) images obtained from lidar (light detection and ranging). The distribution of the leaf inclination angle within a tree was then calculated. The 3D images were first converted into voxel coordinates. Then, a plane was fitted to some voxels surrounding the point (voxel) of interest. The inclination angle and azimuth angle were obtained from the normal. The measured leaf inclination angle and its actual value were correlated and indicated a high correlation (R2 = 0.95). The absolute error of the leaf inclination angle estimation was 2.5°. Furthermore, the leaf inclination angle can be estimated even when the distance between the lidar and leaves is about 20 m. This suggests that the inclination angle estimation of leaves in a top part is reliable. Then, the leaf inclination angle distribution within a tree was calculated. The difference in the leaf inclination angle distribution between different parts within a tree was observed, and a detailed tree structural analysis was conducted. We found that this method enables accurate and efficient leaf inclination angle distribution.

19 March 2020 in Remote Sensing
Verified
Journal Article
Open access
PDF file
KIKenta Itakura
Kenta Itakura
FHFumiki Hosoi
Fumiki Hosoi
It is important to grasp the number and location of trees, and measure tree structure attributes, such as tree trunk diameter and height. The accurate measurement of these parameters will lead to efficient forest resource utilization, maintenance of trees in urban cities, and feasible afforestation planning in the future. Recently, light detection and ranging (LiDAR) has been receiving considerable attention, compared with conventional manual measurement techniques. However, it is difficult to use LiDAR for widespread applications, mainly because of the costs. We propose a method for tree measurement using 360° spherical cameras, which takes omnidirectional images. For the structural measurement, the three-dimensional (3D) images were reconstructed using a photogrammetric approach called structure from motion. Moreover, an automatic tree detection method from the 3D images was presented. First, the trees included in the 360° spherical images were detected using YOLO v2. Then, these trees were detected with the tree information obtained from the 3D images reconstructed using structure from motion algorithm. As a result, the trunk diameter and height could be accurately estimated from the 3D images. The tree detection model had an F-measure value of 0.94. This method could automatically estimate some of the structural parameters of trees and contribute to more efficient tree measurement.

26 December 2018 in Horticulturae
Verified
Journal Article
Open access
PDF file
KIKenta Itakura
Kenta Itakura
YSYoshito Saito
Yoshito Saito
TSTetsuhito Suzuki
Tetsuhito Suzuki
NKNaoshi Kondo
Naoshi Kondo
FHFumiki Hosoi
Fumiki Hosoi
To produce high-quality citrus, the harvest time of citrus should be determined by considering its maturity. To evaluate citrus maturity, the Brix/acid ratio, which is the ratio of sugar content or soluble solids content to acid content, is one of the most commonly used indicators of fruit maturity. To estimate the Brix/acid ratio, fluorescence spectroscopy, which is a rapid, sensitive, and cheap technique, was adopted. Each citrus peel was extracted, and its fluorescence value was measured. Then, the fluorescent spectrum was analyzed using a convolutional neural network (CNN). In fluorescence spectroscopy, a matrix called excitation and emission matrix (EEM) can be obtained, in which each fluorescence intensity was recorded at each excitation and emission wavelength. Then, by regarding the EEM as an image, the Brix/acid ratio of juice from the flesh was estimated via performing a regression with a CNN (CNN regression). As a result, the Brix/acid ratio absolute error was estimated to be 2.48, which is considerably better than the values obtained by the other methods in previous studies. Hyperparameters, such as depth of layers, learning rate, and the number of filters used for this estimation, could be observed using Bayesian optimization, and the optimization contributed to the high accuracy.

14 June 2016 in Sensors
Verified
Journal Article
Open access
PDF file
YZYu Zhang
Yu Zhang
PTPoching Teng
Poching Teng
YSYo Shimizu
Yo Shimizu
FHFumiki Hosoi
Fumiki Hosoi
Kenji OmasaKenji Omasa
Kenji Omasa
For plant breeding and growth monitoring, accurate measurements of plant structure parameters are very crucial. We have, therefore, developed a high efficiency Multi-Camera Photography (MCP) system combining Multi-View Stereovision (MVS) with the Structure from Motion (SfM) algorithm. In this paper, we measured six variables of nursery paprika plants and investigated the accuracy of 3D models reconstructed from photos taken by four lens types at four different positions. The results demonstrated that error between the estimated and measured values was small, and the root-mean-square errors (RMSE) for leaf width/length and stem height/diameter were 1.65 mm (R2 = 0.98) and 0.57 mm (R2 = 0.99), respectively. The accuracies of the 3D model reconstruction of leaf and stem by a 28-mm lens at the first and third camera positions were the highest, and the number of reconstructed fine-scale 3D model shape surfaces of leaf and stem is the most. The results confirmed the practicability of our new method for the reconstruction of fine-scale plant model and accurate estimation of the plant parameters. They also displayed that our system is a good system for capturing high-resolution 3D images of nursery plants with high efficiency.