XHXiaomei Hu

Xiaomei Hu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xiaomei Hu has a total of 38 co-authors. Here are the top co-authors by number of shared publications:

  • Dong Wang

    The Key Laboratory of Intelligent Manufacturing and Robotics, School of Mechatronic Engineering and Automation, Shanghai University, Mailbox 232, No. 149 Yanchang Road, Shanghai 200072, China

    2 shared publications
  • Ning Zeng

    Shanghai University

    2 shared publications
  • Yu Tao

    The Key Laboratory of Intelligent Manufacturing and Robotics, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China

    2 shared publications
  • Bo Cheng

    The Sixth Institute, 601 Branch of China Aeronautical Science and Technology Corporation, Hohhot, China

    1 shared publication
  • Chuan Wang

    The Key Laboratory of Intelligent Manufacturing and Robotics, School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China

    1 shared publication
  • Dong Wang

    Faculty of Business and Economics Department of Statistics Department of Biostatistics The University of Hong Kong Rutgers University University of North Carolina at Chapel Hill

    1 shared publication

Latest Publications

  • Open Access

    Research on Pear Detection Algorithm Based on Improved YOLOv7

    by Xiaomei Hu, Longjie Zhao, Shanggao Tong, Yi Chen

  • Open Access

    Variability-Weighted Interpolation Algorithm Based on Fixed-Frame Sampling of Data

    by Bo Cheng, Mingnan Zhang, Xiaomei Hu

    A spatial data interpolation algorithm is a method to transform scattered and sparse measurement data into regular and continuous applicable data. This algorithm can make the display results smooth and continuous without changing the data characteristics, which is closer to the real acquisition object. In response to the low interpolation accuracy of the inverse distance weighting (IDW) algorithm and the poor interpolation efficiency of the ordinary kriging (OK) algorithm, this study proposes a variational-weighted (VW) interpolation algorithm based on data fixed-frame sampling. By introducing the variational function of OK into IDW and taking different weight coefficients from OK, a new computational model is constructed to improve the interpolation accuracy and adapt to different types of data characteristics. In the whole interpolation process, the data are sampled in a fixed frame and a new sampling point search method is proposed to improve the computational efficiency. The study not only compares the accuracy and efficiency of the algorithm using two types of data but also tests the stability of the new algorithm for different data volumes. It is shown that VW based on a fixed-grid sampling of the data is more accurate than the inverse distance interpolation algorithm for both data types. The VW interpolation algorithm based on data lattice sampling improves the computational efficiency for featureless data and exhibits better performance in terms of accuracy and computational efficiency for data with features, compared to the common kriging interpolation algorithm. In addition, the VW interpolation algorithm based on a fixed-grid sampling of data has a more stable performance for different amounts of data.

  • Open Access

    Multi-Person Pose Estimation via Learning Feature Integration

    by Xiaomei Hu, Jiahao Tian, Huixiang Qiao, Minjie Wang

    Human pose estimation is a fundamental but challenging task in computer vision. Although batch normalization is widely used for deep learning, feature extraction in deep convolutional neural networks (DCNN) is still not well explored. In this work, we propose a pose encoding module (PEM) to enhance the learning ability and generalization ability of feature extraction. Given input images, PEM integration instance normalization and batch normalization, combining them in an appropriate way to learn to capture and eliminate appearance changes while maintaining the distinction between learning features can be seen as an integration and adjustment of global information. In addition, we use a simple and efficient up-sampling strategy to recover high-resolution representations for predicting more accurate human keypoint heatmaps, which has achieved better performance than the average network in recent missions. We studied our approach on a standard benchmark for human pose estimation.


  • Open Access

    Study on the control system of Agaricus bisporus picking robot

    by Hu Xiaomei, Pan Zhaoren, Yang Shuzhen, Yu Tao

    At present, the Agaricus bisporus industrialized cultivation has formed in the world, and fertilization, feeding, humidity control has been automated. However, no automation has been achieved in the human-like picking process. Therefore, an A. bisporus picking robot is designed and the control system is put forward. The control system of A. bisporus picking robot takes the motion control card as the core and Windows10 as the operating system. The upper computer receives a row of A. bisporus photographs taken by the camera and obtains A. bisporus coordinate points through image processing, and the stepper motor and DC motor are driven by the terminal board of the motion control card to pick the A. bisporus. Moreover, the parallel control system is designed to implement image processing and A. bisporus picking in order to improve the efficiency of A. bisporus picking robot. In addition, semi-closed loop system of stepping motor is adopted to compensate for the error caused by multi-step walking, and the control method of two-step walking of A. bisporus picking robot is proposed to solve some A. bisporus that can not be picked up. The experiment results show that the control system of A. bisporus picking robot runs smoothly and efficiently, and it has very strong application value.


  • Open Access

    Design and application of visual system in the Agaricus bisporus picking robot

    by Hu Xiaomei, Wang Chuan, Yu Tao

    The Agaricus bisporus picking robot has not been commercially applied in the world. Based on the self-developed A. bisporus picking robot, the visual system design is carried out, and aiming at the specificity of the picking object, a measuring method of diameter and center point position based on monocular vision is proposed. Since the unequal heights of the A. bisporus affect the accuracy of visual recognition, the three-dimensional coordinates of the centre point of the A. bisporus are measured by the horizontal movement of the camera and the ellipse-fitting algorithm is proposed to improve the accuracy of position. Moreover, the depth information is used to compensate the error of the diameter measurement of A. bisporus. Through the picking experiment at the A. bisporus planting base, the results prove that the recognition success rate of the visual system is up to 90%.


  • Open Access

    Visual Simulation Platform for Complex Products

    by Xiaomei Hu, Jiashu Miao, Chuan Wang, Xiao Ma, Wei Chenjun

    In order to meet the needs of modern product development, aiming at the problem of product's long development cycle, difficulty and lack of functionality, we propose a visual simulation platform for complex products. The platform satisfies almost all product requirements, and integrates the function of product design, display, simulation and post-maintenance management. High visibility, high degree of integration, product versatility and friendly human-computer interaction improve the development efficiency. And based on WebGL technology, the platform system is successfully built, which achieves the visualized development of the product.

  • Production line 3D visualization monitoring system design based on OpenGL

    by Jian-Fei Chai, Xiao-Mei Hu, He-Wei Qu, Ming-Hang Li, Hui-Jing Xu, Yu Liu, Tao Yu


  • Novel Cylinder Movement Modeling Method Based on Aerodynamics

    by Jian-Qing Zhang, Xiao-Mei Hu, Jin-Sheng Kang, Feng Xiong, Ning Zeng

  • Open Access

    Prediction Research of Red Tide Based on Improved FCM

    by Xiaomei Hu, Dong Wang, Hewei Qu, Xinran Shi

    Red tides are caused by the combination effects of many marine elements. The complexity of the marine ecosystem makes it hard to find the relationship between marine elements and red tides. The algorithm of fuzzyc-means (FCM) can get clear classification of things and expresses the fuzzy state among different things. Therefore, a prediction algorithm of red tide based on improved FCM is proposed. In order to overcome the defect of FCM which is overdependent on the initial cluster centers and the objective function, this paper gains the initial cluster centers through the principle of regional minimum data density and the minimum mean distance. The feature weighted cluster center is added to the objective function. Finally, the improved FCM algorithm is applied in the prediction research of red tide, and the results show that the improved FCM algorithm has good denoising ability and high accuracy in the prediction of red tides.


  • Open Access

    Research on the Concentration Prediction of Nitrogen in Red Tide Based on an Optimal Grey Verhulst Model

    by Xiaomei Hu, Yubin Wang, Yue Yu, Dong Wang, Yuan Tian

    In order to reduce the harm of red tide to marine ecological balance, marine fisheries, aquatic resources, and human health, an optimal Grey Verhulst model is proposed to predict the concentration of nitrogen in seawater, which is the key factor in red tide. The Grey Verhulst model is established according to the existing concentration data series of nitrogen in seawater, which is then optimized based on background value and time response formula to predict the future changes in the nitrogen concentration in seawater. Finally, the accuracy of the model is tested by the posterior test. The results show that the prediction value based on the optimal Grey Verhulst model is in good agreement with the measured nitrogen concentration in seawater, which proves the effectiveness of the optimal Grey Verhulst model in the forecast of red tide.