Hongqi Zhang

Hongqi Zhang

Auto-generated profile, based on publicly available information

Hongqi Zhang

Key Laboratory of Computational Optical Imaging Technology

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
1 January 2026 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
HZHongqi Zhang
Hongqi Zhang
HSHe Sun
He Sun
XSXu Sun
Xu Sun
HGHongmin Gao
Hongmin Gao
Haoyang YuHaoyang Yu
Haoyang Yu
Bing ZhangBing Zhang
Bing Zhang

25 November 2021 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
HZHongqi Zhang
Hongqi Zhang
Xudong SunXudong Sun
Xudong Sun
YZYuan Zhu
Yuan Zhu
FXFengqiang Xu
Fengqiang Xu
XFXianping Fu
Xianping Fu
Band selection (BS) methods based on deep learning have achieved significant development. However, most existing band selection methods commonly utilize a fully connected neural network (FCN) or convolutional neural network (CNN) to explore the correlation among bands and rarely combine the two styles of the network to select bands. Moreover, almost all the methods employ the form of the combination of $L_{1}$ norm and Sigmoid to constitute attention model, which may lead to losing some informative band feature. To tackle these troubles, this letter proposes a novel band selection network using FCN and CNN, termed as global-local spectral weight network based on attention (GLSWA), in which the band features of each pixel is mined using the network of two types, and designing an attention-based scoring module (ASM) and a convolutional reconstruction module (CRM), respectively, so that each attention of band is adjusted by simultaneous considering the entire band features and successive one. Experimental results on three real hyperspectral image (HSI) datasets show that the proposed method achieves satisfactory accuracy than some state-of-the-art algorithms.

25 July 2023
Verified
Conference Paper
Closed access
YYYin Yu
Yin Yu
HTHaoran Teng
Haoran Teng
HZHongqi Zhang
Hongqi Zhang
FTFujun Tian
Fujun Tian
The research of automatic recognition of machining features constitutes a crucial supporting pillar for intelligent design and manufacturing. Despite the availability of existing algorithms, there are prevalent problems including low recognition efficiency, low recognition accuracy, and limited applicability to hybrid intersection features. The recognition capability of neural networks has achieved significant success in various fields. The application potential of neural networks for machining feature recognition is currently being explored. In this paper, we propose a feedforward neural network and a novel 3D convolutional neural network framework based on semantic and voxelization methods to identify machining features from 3D CAD models. Sufficient experiments on the datasets of 24 machining characteristics reveal an excellent accuracy result. The proposed framework provides a reliable algorithmic basis for implementing real-time computer aided process planning (CAPP) systems.