Huan Lei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Huan Lei has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Zhenyu Zhong
Guangdong Key Laboratory of Modern Control Technology, Institute of Intelligent Manufacturing, Guangdong Academy of Sciences, Guangzhou 510070, China
4 shared publications - Zeyu Jiao
Guangdong Key Laboratory of Modern Control Technology, Institute of Intelligent Manufacturing, Guangdong Academy of Sciences, Guangzhou, China
3 shared publications - Chentong Li
Guangdong Key Laboratory of Modern Control Technology, Institute of Intelligent Manufacturing, Guangdong Academy of Science, Guangzhou, Guangdong 510070, P. R. China
2 shared publications - Chaojun Hou
Academy of Contemporary Agriculture Engineering Innovations, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, China
1 shared publication - Hengshan Zong
China Aerospace Academy of Systems Science and Engineering, Beijing, China
1 shared publication - Jiajun Zhuang
Academy of Contemporary Agriculture Engineering Innovations, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, China
1 shared publication
Latest Publications
- Open Access
- 1 January 2023
- Published by International Journal of Agricultural and Biological Engineering (IJABE) in International Journal of Agricultural and Biological Engineering
- Vol. 16 (6) , 246-254
Accurate and rapid image segmentation method for bayberry automatic picking via machine learning
Accurate and rapid image segmentation method for bayberry automatic picking via machine learning
- 1 January 2023
- Published by International Journal of Agricultural and Biological Engineering (IJABE) in International Journal of Agricultural and Biological Engineering
- Vol. 16 (6) , 246-254
Open AccessAccurate and rapid image segmentation method for bayberry automatic picking via machine learning
Accurate and rapid image segmentation method for bayberry automatic picking via machine learning
- 10 February 2022
- Published by Springer Nature in Machine Vision and Applications
- Vol. 33 (2) , 1-12
Potential escalator-related injury identification and prevention based on multi-module integrated system for public health
- 10 February 2022
- Published by Springer Nature in Machine Vision and Applications
- Vol. 33 (2) , 1-12
Potential escalator-related injury identification and prevention based on multi-module integrated system for public health
- Open Access
- 19 November 2021
- Published by Association for Computing Machinery (ACM)
- p. 15-20
The Segmentation of Perianal Abscess Lesion Area via Gradient Operator of CT Images
Perianal abscess is a high incidence of anorectal diseases, and simply surgical treatment could result in the removal of unnecessary tissue, and precise segmentation could solve this problem. In this work, we find a method based on the gradient of the medical image to conquer this problem. Firstly, the edge operator is used to get the gradient of the original image, and by setting the preianal area and taking the gradient again, we could get the edges in the perianal area. Then, by the symmetry of the preianal area, we could get the closed polygon of the lesion area. And by smoothing the polygon, we could finally obtain the closed curve of the lesion area. As far as we know, our method is the first to apply image gradient and mathematical methods to the field of image segmentation of the perianal abscess and provide an auxiliary calibration method for medical image data.
- 19 November 2021
- Published by Association for Computing Machinery (ACM)
- p. 15-20
Open AccessThe Segmentation of Perianal Abscess Lesion Area via Gradient Operator of CT Images
Perianal abscess is a high incidence of anorectal diseases, and simply surgical treatment could result in the removal of unnecessary tissue, and precise segmentation could solve this problem. In this work, we find a method based on the gradient of the medical image to conquer this problem. Firstly, the edge operator is used to get the gradient of the original image, and by setting the preianal area and taking the gradient again, we could get the edges in the perianal area. Then, by the symmetry of the preianal area, we could get the closed polygon of the lesion area. And by smoothing the polygon, we could finally obtain the closed curve of the lesion area. As far as we know, our method is the first to apply image gradient and mathematical methods to the field of image segmentation of the perianal abscess and provide an auxiliary calibration method for medical image data.
- Open Access
- 20 October 2021
- Published by MDPI AG in Sustainability
- Vol. 13 (21) , 11572
Recycling Waste Classification Using Vision Transformer on Portable Device
Recycling resources from waste can effectively alleviate the threat of global resource strain. Due to the wide variety of waste, relying on manual classification of waste and recycling recyclable resources would be costly and inefficient. In recent years, automatic recyclable waste classification based on convolutional neural network (CNN) has become the mainstream method of waste recycling. However, due to the receptive field limitation of the CNN, the accuracy of classification has reached a bottleneck, which restricts the implementation of relevant methods and systems. In order to solve the above challenges, in this study, a deep neural network architecture only based on self-attention mechanism, named Vision Transformer, is proposed to improve the accuracy of automatic classification. Experimental results on TrashNet dataset show that the proposed method can achieve the highest accuracy of 96.98%, which is better than the existing CNN-based method. By deploying the well-trained model on the server and using a portable device to take pictures of waste in order to upload to the server, automatic waste classification can be expediently realized on the portable device, which broadens the scope of application of automatic waste classification and is of great significance with respect to resource conservation and recycling.
- 20 October 2021
- Published by MDPI AG in Sustainability
- Vol. 13 (21) , 11572
Open AccessRecycling Waste Classification Using Vision Transformer on Portable Device
Recycling resources from waste can effectively alleviate the threat of global resource strain. Due to the wide variety of waste, relying on manual classification of waste and recycling recyclable resources would be costly and inefficient. In recent years, automatic recyclable waste classification based on convolutional neural network (CNN) has become the mainstream method of waste recycling. However, due to the receptive field limitation of the CNN, the accuracy of classification has reached a bottleneck, which restricts the implementation of relevant methods and systems. In order to solve the above challenges, in this study, a deep neural network architecture only based on self-attention mechanism, named Vision Transformer, is proposed to improve the accuracy of automatic classification. Experimental results on TrashNet dataset show that the proposed method can achieve the highest accuracy of 96.98%, which is better than the existing CNN-based method. By deploying the well-trained model on the server and using a portable device to take pictures of waste in order to upload to the server, automatic waste classification can be expediently realized on the portable device, which broadens the scope of application of automatic waste classification and is of great significance with respect to resource conservation and recycling.
- Open Access
Citrus Tree Segmentation from UAV Images Based on Monocular Machine Vision in a Natural Orchard Environment
The segmentation of citrus trees in a natural orchard environment is a key technology for achieving the fully autonomous operation of agricultural unmanned aerial vehicles (UAVs). Therefore, a tree segmentation method based on monocular machine vision technology and a support vector machine (SVM) algorithm are proposed in this paper to segment citrus trees precisely under different brightness and weed coverage conditions. To reduce the sensitivity to environmental brightness, a selective illumination histogram equalization method was developed to compensate for the illumination, thereby improving the brightness contrast for the foreground without changing its hue and saturation. To accurately differentiate fruit trees from different weed coverage backgrounds, a chromatic aberration segmentation algorithm and the Otsu threshold method were combined to extract potential fruit tree regions. Then, 14 color features, five statistical texture features, and local binary pattern features of those regions were calculated to establish an SVM segmentation model. The proposed method was verified on a dataset with different brightness and weed coverage conditions, and the results show that the citrus tree segmentation accuracy reached 85.27% ± 9.43%; thus, the proposed method achieved better performance than two similar methods.
Open AccessCitrus Tree Segmentation from UAV Images Based on Monocular Machine Vision in a Natural Orchard Environment
The segmentation of citrus trees in a natural orchard environment is a key technology for achieving the fully autonomous operation of agricultural unmanned aerial vehicles (UAVs). Therefore, a tree segmentation method based on monocular machine vision technology and a support vector machine (SVM) algorithm are proposed in this paper to segment citrus trees precisely under different brightness and weed coverage conditions. To reduce the sensitivity to environmental brightness, a selective illumination histogram equalization method was developed to compensate for the illumination, thereby improving the brightness contrast for the foreground without changing its hue and saturation. To accurately differentiate fruit trees from different weed coverage backgrounds, a chromatic aberration segmentation algorithm and the Otsu threshold method were combined to extract potential fruit tree regions. Then, 14 color features, five statistical texture features, and local binary pattern features of those regions were calculated to establish an SVM segmentation model. The proposed method was verified on a dataset with different brightness and weed coverage conditions, and the results show that the citrus tree segmentation accuracy reached 85.27% ± 9.43%; thus, the proposed method achieved better performance than two similar methods.