SZShunshun Zhong

Shunshun Zhong

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Shunshun Zhong has a total of 9 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Local adaptive smoothing method for small-scale noise in 3D PMP reconstruction systems

    by Chaolong Zhang, Wenfang Su, Dinghui Luo, Shunshun Zhong, Haibo Zhou, Ji'AN Duan

    In the 3D point cloud produced by the Phase Measurement Profilometry system, isolated noise can be removed using techniques such as statistical filtering. However, efficiently processing small-scale noise in the point cloud without compromising the details of the measured object remains a significant challenge. A fine smoothing method for small-scale noise, based on both 2D images and 3D point clouds, is proposed. First, the point cloud, originally in the (Xc, Yc, Z) format, is transformed into pixel-height coordinates using the system's parameters. Next, gradient information from the neighborhood surrounding each sampling point is fed into a type-1 fuzzy module. This module, which leverages expert natural language, is commonly used to handle data or system uncertainty. The output of this module is then employed to assess the richness of the detail information in the current region, enabling an adaptive adjustment of the smoothing algorithm's threshold. Experimental results demonstrate that the proposed method effectively smooth small-scale noise while preserving the detailed features of the measured object.

  • Open Access

    Multi-Level Scale Attention Fusion Network for Adhesive Spots Segmentation in Microlens Packaging

    by Yixiong Yan, Sijia Chen, Lian Duan, Dinghui Luo, Fan Zhang, Shunshun Zhong

    The demand for high-quality beams from high-power lasers has led to the need for high-precision inspection of adhesion points for collimating lens packages. In this paper, we propose a Multi-Level Scale Attention Fusion Network (MLSAFNet) by fusing a Multi-Level Attention Module (MLAM) and a Multi-Scale Channel-Guided Module (MSCGM) to achieve highly accurate and robust adhesive spots detection. Additionally, we built a Laser Lens Adhesive Spots (LLAS) dataset using automated lens packaging equipment and performed pixel-by-pixel standardization for the first time. Extensive experimental results show that the mean intersection over union (mIoU) of MLSAFNet reaches 91.15%, and its maximum values of localization error and area measurement error are 21.83 μm and 0.003 mm2, respectively, which are better than other target detection methods.