Lijun Qi

Dr. Lijun Qi

College of Engineering, China Agricultural University, No.17 Qing Hua Dong Lu, Haidian District, Beijing 100083, China

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

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

Representative Publications

View All Publications
1 September 2020 in Biosystems Engineering
Verified
Journal Article
Closed access
HZHao Zhang
Hao Zhang
Lijun QiLijun Qi
Lijun Qi
YWYalei Wu
Yalei Wu
EMElizabeth M. Musiu
Elizabeth M. Musiu
ZCZhenzhen Cheng
Zhenzhen Cheng
Pei WangPei Wang
Pei Wang

1 February 2019 in Crop Protection
Verified
Journal Article
Closed access
EMElizabeth M. Musiu
Elizabeth M. Musiu
Lijun QiLijun Qi
Lijun Qi
YWYalei Wu
Yalei Wu

10 June 2019 in Sensors
Verified
Journal Article
Open access
PDF file
YWYalei Wu
Yalei Wu
Lijun QiLijun Qi
Lijun Qi
HZHao Zhang
Hao Zhang
EMElizabeth M. Musiu
Elizabeth M. Musiu
ZYZepeng Yang
Zepeng Yang
Pei WangPei Wang
Pei Wang
Accurate measurement of the downwash flow field of plant protection unmanned aerial vehicles (UAVs) is essential for analyzing the spatial distribution of droplets. To realize on-line rapid detection of the downwash flow field of a multi-rotor UAV, a flexible polypropylene detection device based on the principle of full bridge strain effect was proposed. Its performance principle was based on the physical deformation caused by wind pressure. The Fluid Flow and Static Structural modules of ANSYS 16.0 finite element software were used to simulate one-way fluid-solid coupling interaction. The surface of the resistive strain gauge embedded in the flexible detecting structure responded well to wind speed variation, hence it was suitable for downwash airflow wind field detection. By solving the strain force on the surface of the flexible detection structure, the length and layout of the grating wire of the strain gauge on the surface of the flexible detection structure were optimized. Meanwhile at 4 m·s−1 wind speed, the output voltage at varied bridge flexible acquisition systems in the acquisition card was measured. Results indicated coefficient of variation of 3.67%, 1.63% and 1.5%, respectively, which proved the good data acquisition consistency of the system. Through calibration test, the regression equation for the relationship between output voltage and wind speed for three unique sensor signal measuring circuits was established. The determination coefficients R2 for single bridge, half bridge and full bridge circuits were 0.9885, 0.9866 and 0.9959, respectively. In conclusion, by applying the multi-rotor plant protection UAV test platform, the results indicated the maximum relative error of the wind speed at each sampling point of the system at 1.0 m altitude was below 5.61%. Simulated and measured value had an RMSE maximum error of 0.1246 m·s−1. Moreover, downwash airflow detection not only has high accuracy but also has high sensitivity. Thus, there is convenience and practicability in the plant protection offered by this approach. The rapid measurement of UAV wind field and the established two-dimensional wind field model can provide a basis for precise application of agricultural aviation.

28 February 2020 in Remote Sensing
Verified
Journal Article
Open access
PDF file
ZCZhenzhen Cheng
Zhenzhen Cheng
Lijun QiLijun Qi
Lijun Qi
YCYifan Cheng
Yifan Cheng
YWYalei Wu
Yalei Wu
HZHao Zhang
Hao Zhang
To minimize pesticide dosage and its adverse environmental impact, Unmanned Aerial Vehicle (UAV) spraying requires precise individual canopy information. Branches from neighboring trees may overlap, preventing image-based artificial intelligence analysis from correctly identifying individual trees. To solve this problem, this paper proposes a segmentation and evaluation method for mingled fruit tree canopies with irregular shapes. To extract the individual trees from mingled canopies, the study fitted the projection curve distribution of the interlacing tree with Gaussian Mixture Model (GMM) and solved the matter of segmentation by estimating the GMM parameters. For the intermingling degree assessment, the Gaussian parameters were used to quantify the characteristics of the mingled fruit trees and then as the input for Extreme Gradient Boosting (XGBoost) model training. The proposed method was tested on the aerial images of cherry and apple trees. Results of the experiments show that the proposed method can not only accurately identify individual trees, but also estimate the intermingledness of the interlacing canopies. The root mean squares (R) of the over-segmentation rate (Ro) and under-segmentation rate (Ru) for individual trees counting were less than 10%. Moreover, the Intersection over Union (IoU), used to evaluate the integrity of a single canopy area, was greater than 88%. An 84.3% Accuracy (ACC) with a standard deviation of 1.2% was achieved by the assessment model. This method will supply more accurate data of individual canopy for spray volume assessments or other precision-based applications in orchards.

10 May 2021 in Agriculture
Verified
Journal Article
Open access
PDF file
ZCZhenzhen Cheng
Zhenzhen Cheng
Lijun QiLijun Qi
Lijun Qi
YCYifan Cheng
Yifan Cheng
Highly effective pesticide applications require a continual adjustment of the pesticide spray flow rate that attends to different canopy characterizations. Real-time image processing with rapid target detection and data-processing technologies is vital for precision pesticide application. However, the extant studies do not provide an efficient and reliable method of extracting individual trees with irregular tree-crown shapes and complicated backgrounds. This paper on our study proposes a Mahalanobis distance and conditional random field (CRF)-based segmentation model to extract cherry trees accurately in a natural orchard environment. This study computed Mahalanobis distance from the image’s color, brightness and location features to acquire an initial classification of the canopy and background. A CRF was then created by using the Mahalanobis distance calculations as unary potential energy and the Gaussian kernel function based on the image color and pixels distance as binary potential energy. Finally, the study completed image segmentation using mean-field approximation. The results show that the proposed method displays a higher accuracy rate than the traditional algorithms K-means and GrabCut algorithms and lower labeling and training costs than the deep learning algorithm DeepLabv3+, with 92.1%, 94.5% and 93.3% of the average P, R and F1-score, respectively. Moreover, experiments on datasets with different overlap conditions and image acquisition times, as well as in different years and seasons, show that this method performs well under complex background conditions, with an average F1-score higher than 87.7%.

16 July 2022 in Agriculture
Verified
Journal Article
Open access
PDF file
ZLZhongao Lu Lu
Zhongao Lu Lu
Lijun QiLijun Qi
Lijun Qi
HZHao Zhang
Hao Zhang
JWJunjie Wan
Junjie Wan
JZJiarui Zhou
Jiarui Zhou
Obtaining canopy area, crown width, position, and other information from UAV aerial images and adjusting spray parameters in real-time according to this information is an important way to achieve precise pesticide application in orchards. However, the natural illumination environment in the orchard makes extracting the fruit tree canopy difficult. Hereto, an effective unsupervised image segmentation method is developed in this paper for fast fruit tree canopy acquisition from UAV images under natural illumination conditions. Firstly, the image is preprocessed using the shadow region luminance compensation method (SRLCM) that is proposed in this paper to reduce the interference of shadow areas. Then, use Naive Bayes to obtain multiple high-quality color features from 10 color models was combined with ensemble clustering to complete image segmentation. The segmentation experiments were performed on the collected apple tree images. The results show that the proposed method’s average precision rate, recall rate, and F1-score are 95.30%, 84.45%, and 89.53%, respectively, and the segmentation quality is significantly better than ordinary K-means and GMM algorithms.