智能人机交互创新团队成员—张明亮

发布者:hhxx发布时间:2023-12-29浏览次数:70

张明亮,讲师,于20162020年分别获大连理工大学运筹学和计算数学的硕士、博士学位。近几年主要从事深度图像估计、三维场景重建以及底层图像处理等方面的研究工作,共发表论文10篇,授权发明专利5项。

 

研究方向:计算机视觉;图像处理;深度学习。

 

承担科研项目情况

1.     科教产融合试点工程基础研究类培新项目,2023PX095,基于异源传感器的高质量三维场景重建,2023/01-2024/12,10万元、负责人

2.     校(院)人才科研项目,2023RCKY249,面向自动驾驶场景的精确深度估计及三维重建技术研究,2023/08-2024/7,12万元、负责人

部分代表性论文

[1]     Mingliang Zhang and Xinchen Ye and Xin Fan and Wei Zhong. Unsupervised depth estimation from monocular videos with hybrid geometric-refined loss and contextual attention[J]. Neurocomputing, 2020, 379 : 250 – 261.

[2]     Mingliang Zhang and Xinchen Ye and Xin Fan. Unsupervised detail-preserving network for high quality monocular depth estimation[J]. Neurocomputing, 2020, 404 : 1 –13.

[3]     Xinchen Ye and Xin Fan and Mingliang Zhang and Rui Xu and Wei Zhong. Unsupervised monocular depth estimation via recursive stereo distillation[J]. IEEE Transactions on Image Processing, 2021, 30 : 4492 – 4504.

[4]     Xinchen Ye and Mingliang Zhang and Jingyu Yang and Xin Fan and Fangfang Guo. A sparsity-promoting image decomposition model for depth recovery[J]. Pattern Recognition, 2020, 107 : 107506.

[5]     Xianjie Gao and Mingliang Zhang and Jinming Luo. Low-Light image enhancement via retinex-style decomposition of denoised deep image prior[J]. Sensors, 2022, 22 :5593.

[6]     Mengqi Gao and Jiangjiao Li and Dazheng Zhou and Yumin Zhi and Mingliang Zhang and Bin Li. Fall detection based on OpenPose and MobileNetV2 network[J]. IET Image Processing, 2023, 17 : 722-732.

[7]     Dazheng Zhou and Mingliang Zhang and Bin Li. A Two-Branch Framework for Monocular Depth Estimation[C]. International Conference on Image, Vision and Computing (ICIVC), 2023.

[8]     Xinchen Ye and Mingliang Zhang and Xin Fan and Rui Xu and Juncheng Pu and Ruoke Yan. Cascaded detail-aware network for unsupervised monocular depth estimation[C]. IEEE International Conference on Multimedia and Expo (ICME), 2020 : 1 –6.

[9]     Xinchen Ye and Mingliang Zhang and Rui Xu and Wei Zhong and Xin Fan and Zhu Liu and Jiaao Zhang. Unsupervised monocular depth estimation based on dual attention mechanism and depth-aware loss[C]. IEEE International Conference on Multimedia and Expo (ICME), 2019 : 169 – 174.

[10]  Xinchen Ye and Mingliang Zhang and Qianyu Yan and Xin Fan and Zhongxuan Luo. Image denoising based on non-parametric ADMM algorithm[C]. Pacific Rim Conference on Multimedia, 2018 : 318 – 328.

 

代表性授权发明专利

1.       叶昕辰;张明亮;蔡玉;樊鑫,一种基于非参数化交替方向乘子法的图像去噪算法,中国专利,专利号:ZL201810207235.6.

2.       张明亮;周大正;智昱旻;李彬;刘丽霞;张友梅;张瑜,基于完整上下文信息的单目深度估计方法及系统,中国专利,专利号:ZL202310490937.0.

3.       叶昕辰;徐睿;樊鑫;张明亮,一种基于上下文注意力机制的单目无监督深度估计方法,中国专利,专利号:ZL202010541514.3.

4.       李彬;刘伟龙;侯兰东;杨姝慧;徐一明;张友梅;张瑜;张明亮,一种四足机器人运动控制方法、系统、存储介质及设备,中国专利,专利号:ZL202210512279.6.

5.       张友梅;李江娇;李彬;高梦奇;智昱旻;周大正;张明亮;张瑜,基于时空信息的跌倒检测方法、系统、存储介质及设备,中国专利,专利号:ZL202210536743.5.