将机器学习、神经网络等人工智能研究领域的常用方法与光电检测系统设计和数据处理相结合，突破传统手段在探测系统性能优化、信噪比提升方案和目标检测算法设计上的局限性，提高光电检测系统的性能指标和可靠性。

1、机器学习改进光电探测系统性能

       通过贝叶斯估计、高斯回归等统计学分析模型，配合机器学习训练方法，实现对水下激光雷达、距离选通成像系统的参数优化、降噪增强，极大地提升了系统探测能力。

2、 深度神经网络改善缺陷识别效果

        通过对抗生成神经网络和迁移学习方法改善缺陷样本不平衡特性，构建深度卷积神经网络实现缺陷可靠分析和准确分类，有效地改善了显示面板、工业产品表面缺陷的识别效果。

相关成果

论文：

1. Zeng, X. J., Guo, W. P., Yang, K. C., & Xia, M. (2018). Noise reduction and retrieval by modified lidar inversion method combines joint retrieval method and machine learning. Applied Physics B-Lasers and Optics, 124(12).

2. 程虎, 李微, 郭文平, & 杨克成. (2019). 基于高斯过程回归的距离选通成像系统工作参数的在线优化. 光学学报, 39(04), 198-205.

3. Yin, X. J., Cheng, H., Yang, K. C., & Xia, M. (2020). Bayesian reconstruction method for underwater 3D range-gated imaging enhancement. Applied Optics, 59(2), 370-379. 

4. Yang, K., Yu, L., Xia, M., Xu, T., & Li, W. (2021). Nonlinear RANSAC with crossline correction: An algorithm for vision-based curved cable detection system. Optics and Lasers in Engineering, 141, 106417. 

5. Xiaojun, Y., Kecheng, Y., Qi, Z., & Xiaohui, Z. (2018). Stencil Imaging and Defects Detection Using Artificial Neural Networks. Paper presented at the 2018 IEEE 16th Intl Conf on Dependable, Autonomic and Secure Computing, 16th Intl Conf on Pervasive Intelligence and Computing, 4th Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress(DASC/PiCom/DataCom/CyberSciTech), 12-15 Aug. 2018, Los Alamitos, CA, USA.

6. Song, S., Zheng, Z., Zhang, S., Ma, W., & Xia, M. (2020). A band-shaped Mura detection method based on unsupervised deep learning (Vol. 11717): SPIE.

7. Xie, C., Zheng, Z., Zhang, S., Chen, C., & Li, W. (2020). A band Mura detection method based on a new generative adversarial network (Vol. 11717): SPIE.

8. Song, S., Yang, K., Wang, A., Zhang, S., & Xia, M. (2021). A Mura Detection Model Based on Unsupervised Adversarial Learning. Ieee Access, 9, 49920-49928. doi:10.1109/ACCESS.2021.3069466