GCGongchao Chen

Gongchao Chen

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Gongchao Chen has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • DACNet: depth-aware convolutional network for corn hyperspectral image classification

    by Gongchao Chen, Guohou Li, Songlin Jin, Linfeng Bai

    With the rapid advancement of agricultural monitoring technologies, hyperspectral imaging has shown considerable potential in seed classification tasks. However, accurate classification of hyperspectral corn seed images remains a challenge due to the high dimensionality of the data, insufficient feature utilization, and limited classification performance. To address these issues, we introduce a depth-aware convolutional network (DACNet) designed for corn hyperspectral image classification. The network integrates multi-layer 3D and 2D convolutions to extract spectral, spatial, and textural features, with fully connected layers used for the final classification. Specifically, principal component analysis is applied to reduce spectral dimensionality while preserving essential information. Then, 3D convolutions are used to extract joint spectral–spatial features, which are further enhanced by multi-head attention mechanisms. These features are reshaped and processed through 2D convolutions to better capture spatial and textural details while keeping computational complexity manageable. Finally, fully connected layers are used to classify corn seed categories accurately. Experiments conducted on a hyperspectral corn seed image dataset and two publicly available remote sensing datasets validate the effectiveness and robustness of DACNet.


  • Machine learning-enhanced vision systems for cutting tool notch detection in new energy battery manufacturing

    by Ying Zheng, Muzi Wang, Gongchao Chen, Heyang Feng, Songlin Jin, Wenyi Zhao, Weidong Zhang

    This paper presents a study on the problem of burrs on the electrodes of new energy batteries, which are a major factor contributing to battery short-circuits and explosions. During the process of electrode cutting, the use of cutting tools with a notch is likely to cause burrs on the electrode. Therefore, it is essential to accurately detect the notch of the cutting tool. This paper explores the issue of cutting tool notch detection using machine learning-enhanced vision systems. Firstly, a set of cutting tool image acquisition devices is used to capture high-quality images of the cutting tool edge. Next, an algorithm for removing attachments based on concave point matching is proposed, effectively eliminating edge attachments by analyzing the concave point information of the edge. Additionally, we propose an enhanced Zernike moment sub-pixel edge extraction method, which achieves sub-pixel edge extraction while preserving the edge characteristics of the cutting tool. Furthermore, a notch detection algorithm based on quartic Hermite interpolation is introduced to detect the notch of the cutting tool by initially identifying the tool’s edge. The proposed algorithms are compared with other state-of-the-art methods, demonstrating faster and more accurate extraction of sub-pixel cutting tool edges and detection of cutting tool notches.