Hui He

Hui He

Auto-generated profile, based on publicly available information

Hui He

School of Software Engineering, Chengdu University of Information Technology,Chengdu,China

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
1 January 2021 in Wireless Communications and Mobile Computing
Verified
Journal Article
Open access
PDF file
JHJunhao Huang
Junhao Huang
ZZZhicheng Zhang
Zhicheng Zhang
GXGuoping Xie
Guoping Xie
HHHui He
Hui He
Noncontact human‐computer interaction has an important value in wireless sensor networks. This work is aimed at achieving accurate interaction on a computer based on auto eye control, using a cheap webcam as the video source. A real‐time accurate human‐computer interaction system based on eye state recognition, rough gaze estimation, and tracking is proposed. Firstly, binary classification of the eye states (opening or closed) is carried on using the SVM classification algorithm with HOG features of the input eye image. Second, rough appearance‐based gaze estimation is implemented based on a simple CNN model. And the head pose is estimated to judge whether the user is facing the screen or not. Based on these recognition results, noncontact mouse control and character input methods are designed and developed to replace the standard mouse and keyboard hardware. Accuracy and speed of the proposed interaction system are evaluated by four subjects. The experimental results show that users can use only a common monocular camera to achieve gaze estimation and tracking and to achieve most functions of real‐time precise human‐computer interaction on the basis of auto eye control.

30 August 2023
Verified
Conference Paper
Closed access
HHHui He
Hui He
YXYuanping Xu
Yuanping Xu
CZChaolong Zhang
Chaolong Zhang
BGBenjun Guo
Benjun Guo
Zhijie XuZhijie Xu
Zhijie Xu
JHJian Huang
Jian Huang
This study explores an improved Masked Autoencoder (MAE) model for anomaly detection in common industrial scene images. Industrial image anomaly detection, as an important research topic in computer vision, can detect abnormal data deviations from normal expected behavior and ensure the normal operation of various systems. In actual industrial scenarios, the scarcity of abnormal samples, the cost of labeled data, and the lack of prior knowledge about anomalies make unsupervised learning methods widely used in the field of image anomaly detection. However, most unsupervised learning methods currently require the application of large-scale datasets. In order to make unsupervised learning applicable to small-scale industrial image datasets, we replaced the backbone network with Swin Transformer based on the Masked Autoencoder method, while improving its mask strategy and optimizer. The effectiveness and advantage of the proposed method are demonstrated through an experimental comparison with existing model, the results show that this method is better than MAE model pretrained on ImageNet, and outperforms other unsupervised learning models in multiple categories.

9 December 2015
Verified
Conference Paper
Closed access
PDF file
HCHongshun Chen
Hongshun Chen
HHHui He
Hui He
HXHongyu Xiao
Hongyu Xiao
JHJing Huang
Jing Huang
We proposed a fast and fully automatic mosaic method for high-resolution satellite images. First, the overlapped rectangle is computed according to geographical locations of the reference and mosaic images and feature points on both the reference and mosaic images are extracted by a scale-invariant feature transform (SIFT) algorithm only from the overlapped region. Then, the RANSAC method is used to match feature points of both images. Finally, the two images are fused into a seamlessly panoramic image by the simple linear weighted fusion method or other method. The proposed method is implemented in C++ language based on OpenCV and GDAL, and tested by Worldview-2 multispectral images with a spatial resolution of 2 meters. Results show that the proposed method can detect feature points efficiently and mosaic images automatically.