Wanjing Dong

Dr. Wanjing Dong

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
6 July 2021 in Sensors
Verified
Journal Article
Open access
PDF file
XTXiaowen Teng
Xiaowen Teng
Guangsheng ZhouGuangsheng Zhou
Guangsheng Zhou
YWYuxuan Wu
Yuxuan Wu
Chenglong HuangChenglong Huang
Chenglong Huang
WDWanjing Dong
Wanjing Dong
Shengyong XuShengyong Xu
Shengyong Xu
The three-dimensional reconstruction method using RGB-D camera has a good balance in hardware cost and point cloud quality. However, due to the limitation of inherent structure and imaging principle, the acquired point cloud has problems such as a lot of noise and difficult registration. This paper proposes a 3D reconstruction method using Azure Kinect to solve these inherent problems. Shoot color images, depth images and near-infrared images of the target from six perspectives by Azure Kinect sensor with black background. Multiply the binarization result of the 8-bit infrared image with the RGB-D image alignment result provided by Microsoft corporation, which can remove ghosting and most of the background noise. A neighborhood extreme filtering method is proposed to filter out the abrupt points in the depth image, by which the floating noise point and most of the outlier noise will be removed before generating the point cloud, and then using the pass-through filter eliminate rest of the outlier noise. An improved method based on the classic iterative closest point (ICP) algorithm is presented to merge multiple-views point clouds. By continuously reducing both the size of the down-sampling grid and the distance threshold between the corresponding points, the point clouds of each view are continuously registered three times, until get the integral color point cloud. Many experiments on rapeseed plants show that the success rate of cloud registration is 92.5% and the point cloud accuracy obtained by this method is 0.789 mm, the time consuming of a integral scanning is 302 s, and with a good color restoration. Compared with a laser scanner, the proposed method has considerable reconstruction accuracy and a significantly ahead of the reconstruction speed, but the hardware cost is much lower when building a automatic scanning system. This research shows a low-cost, high-precision 3D reconstruction technology, which has the potential to be widely used for non-destructive measurement of rapeseed and other crops phenotype.

14 January 2023 in Agriculture
Verified
Journal Article
Open access
PDF file
Shengyong XuShengyong Xu
Shengyong Xu
YZYi Zhang
Yi Zhang
WDWanjing Dong
Wanjing Dong
ZBZhilong Bie
Zhilong Bie
CPChengli Peng
Chengli Peng
Yuan HuangYuan Huang
Yuan Huang
It is important to propose the correct decision for culling and replenishing seedlings in factory seedling nurseries to improve the quality of seedlings and save resources. To solve the problems of inefficiency and subjectivity of the existing traditional manual culling and replenishment of seeds, this paper proposes an automatic method to discriminate the early growth condition of seedlings. Taking watermelon plug seedlings as an example, Azure Kinect was used to collect data of its top view three times a day, at 9:00, 14:00, and 19:00. The data were collected from the time of germination to the time of main leaf growth, and the seedlings were manually determined to be strong or weak on the last day of collection. Pre-processing, image segmentation, and point cloud processing methods were performed on the collected data to obtain the plant height and leaf area of each seedling. The plant height and leaf area on the sixth day were predicted using an LSTM recurrent neural network for the first three days. The R squared for plant height and leaf area prediction were 0.932 and 0.901, respectively. The dichotomous classification of normal and abnormal seedlings was performed using six machine learning classification methods, such as random forest, SVM, and XGBoost, for day six data. The experimental results proved that random forest had the highest classification accuracy of 84%. Finally, the appropriate culling and replenishment decisions are given based on the classification results. This method can provide some technical support and a theoretical basis for factory seedling nurseries and transplanting robots.

23 April 2022 in Plants
Verified
Journal Article
Open access
PDF file
MZMoran Zhang
Moran Zhang
Shengyong XuShengyong Xu
Shengyong Xu
Yuan HuangYuan Huang
Yuan Huang
ZBZhilong Bie
Zhilong Bie
MNMichitaka Notaguchi
Michitaka Notaguchi
WDWanjing Dong
Wanjing Dong
Rootstock grafting is an important method to improve the yield and quality of seedlings. Pumpkin is the rootstock of watermelon, melon, and cucumber, and the root phenotype of rootstock is an important reference for breeding. At present, the root phenotype is mainly measured by scanners, with which it is difficult to achieve non-destructive and in situ measurements. In this work, we propose a method for non-destructive measurement of the root phenotype on the surface layer of the root ball of pumpkin rootstock plug seedlings and an accurate estimation of the surface area, length, and volume of total root using an AZURE KINECT sensor. Firstly, the KINECT is used to capture four-view color and depth images of the root surface, and then multi-view images are spliced to obtain a complete image of the root surface. After preprocessing of the images, we extract the roots from the root ball. For root phenotype measurements, the surface areas of the surface roots and root ball are calculated, followed by calculating root encapsulation. Next, the non-overlapping roots in the surface root image are extracted, and the ratio of the surface area to the skeleton length is used as the average diameter of total root. Based on the high correlation between the surface area of surface root and the surface area of total root, a linear fitting model is established to estimate the surface area, length, and volume of total root. The experiment ultimately showed that the measurement error for the average diameter of total root is less than 30 μm, and consistency with the scanner is higher than 93.3%. The accuracy of the surface area of total root estimation was found to be more than 88.1%, and the accuracy of the root length of total root estimation was observed to be greater than 87.2%. The method proposed in this paper offers similar accuracy to a scanner, which meets the needs of non-destructive root phenotype research. This method is expected to replace root scanners for high-throughput phenotypic measurements and provides a new avenue for root phenotype measurements of pumpkin rootstocks. This technology will provide key basic data for evaluating the root growth of pumpkin rootstocks.

9 October 2021 in Materials
Verified
Journal Article
Open access
PDF file
MWMin Wei
Min Wei
Qiang WanQiang Wan
Qiang Wan
SLShanjun Li
Shanjun Li
LMLiang Meng
Liang Meng
DCDaocheng Cao
Daocheng Cao
KZKan Zheng
Kan Zheng
The abrasion failure is the key factor for prolonging the service life and energy saving of furrow openers. The hardness enhancement was reported to be an effective strategy to increase the wear resistance against the soil abrasion. D517 coatings were deposited on Q235 steel by electric spark to improve the wear-resistant property with an affordable cost for farmers. The wear behavior of the coatings was characterized in a pin on disk friction equipment and a homemade soil abrasion simulation system. The soil adhesion, which is highly related to energy consumption, was also evaluated. Results showed that D517 coatings revealed dendrite structure with some randomly distributed carbides. The electric current exerted a great influence on the microstructure, hardness, friction coefficient, and soil wear rate. The wear rate of samples deposited with 80 A and 90 A reduced to 79% and 84%, respectively, as compared with the normalized heat-treated 65 Mn steel after 6 h in soil. This work provides a promising solution to increase the wear resistance of furrow openers. It needs to be noted that the coating would increase the soil adhesion of the opener, which needs to be further explored to decrease the energy consumption.

21 December 2025 in Agriculture
Verified
Journal Article
Open access
PDF file
WDWanjing Dong
Wanjing Dong
RWRui Wang
Rui Wang
FZFanguo Zeng
Fanguo Zeng
YJYouming Jiang
Youming Jiang
YZYang Zhang
Yang Zhang
WXWei Xu
Wei Xu
Crop row line detection is essential for precision agriculture, supporting autonomous navigation, field management, and growth monitoring. To address the low detection accuracy of rapeseed seedling rows under complex field conditions, this study proposes a detection framework that integrates an improved BiSeNetV2 with a dynamic sliding-window fitting strategy. The improved BiSeNetV2 incorporates the Efficient Channel Attention (ECA) mechanism to strengthen crop-specific feature representation, an Atrous Spatial Pyramid Pooling (ASPP) decoder to improve multi-scale perception, and Depthwise Separable Convolutions (DS Conv) in the Detail Branch to reduce model complexity while preserving accuracy. After semantic segmentation, a Gaussian-filtered vertical projection method is applied to identify crop-row regions by locating density peaks. A dynamic sliding-window algorithm is then used to extract row trajectories, with the window size adaptively determined by the row width and the sliding process incorporating both a lateral inertial-drift strategy and a dynamically adjusted longitudinal step size. Finally, variable-order polynomial fitting is performed within each crop-row region to achieve precise extraction of the crop-row lines. Experimental results indicate that the improved BiSeNetV2 model achieved a Mean Pixel Accuracy (mPA) of 87.73% and a Mean Intersection over Union (MIoU) of 79.40% on the rapeseed seedling dataset, marking improvements of 9.98% and 8.56%, respectively, compared to the original BiSeNetV2. The crop row detection performance for rapeseed seedlings under different environmental conditions demonstrated that the Curve Fitting Coefficient (CFC), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) were 0.85, 1.57, and 1.27 pixels on sunny days; 0.86, 2.05 and 1.63 pixels on cloudy days; 0.74, 2.89, and 2.22 pixels on foggy days; and 0.76, 1.38, and 1.11 pixels during the evening, respectively. The results reveal that the improved BiSeNetV2 can effectively identify rapeseed seedlings, and the detection algorithm can identify crop row lines in various complex environments. This research provides methodological support for crop row line detection in precision agriculture.

20 May 2021 in Preprints.org
Verified
Preprint
Open access
PDF file
TXTeng Xiaowen
Teng Xiaowen
Guangsheng ZhouGuangsheng Zhou
Guangsheng Zhou
YWYuxuan Wu
Yuxuan Wu
Chenglong HuangChenglong Huang
Chenglong Huang
WDWanjing Dong
Wanjing Dong
Shengyong XuShengyong Xu
Shengyong Xu
The 3D reconstruction method using RGB-D camera has a good balance in hardware cost, point cloud quality and automation. However, due to the limitation of inherent structure and imaging principle, the acquired point cloud has problems such as a lot of noise and difficult registration. This paper proposes a three-dimensional reconstruction method using Azure Kinect to solve these inherent problems. Shoot color map, depth map and near-infrared image of the target from six perspectives by Azure Kinect sensor. Multiply the 8-bit infrared image binarization with the general RGB-D image alignment result provided by Microsoft to remove ghost images and most of the background noise. In order to filter the floating point and outlier noise of the point cloud, a neighborhood maximum filtering method is proposed to filter out the abrupt points in the depth map. The floating points in the point cloud are removed before generating the point cloud, and then using the through filter filters out outlier noise. Aiming at the shortcomings of the classic ICP algorithm, an improved method is proposed. By continuously reducing the size of the down-sampling grid and the distance threshold between the corresponding points, the point clouds of each view are continuously registered three times, until get the complete color point cloud. A large number of experimental results on rape plants show that the point cloud accuracy obtained by this method is 0.739mm, a complete scan time is 338.4 seconds, and the color reduction is high. Compared with a laser scanner, the proposed method has considerable reconstruction accuracy and a significantly ahead of the reconstruction speed, but the hardware cost is much lower and it is easy to automate the scanning system. This research shows a low-cost, high-precision 3D reconstruction technology, which has the potential to be widely used for non-destructive measurement of crop phenotype.