Content-Aware Cubemap Projection for Panoramic Image via Deep Q-Learning

Chen, Zihao1,3; Wang, Xu1; Zhou, Yu1; Zou, Longhao2,3; Jiang, Jianmin1

10.1007/978-3-030-37734-2_25

2020

16113349

26th International Conference on MultiMedia Modeling, MMM 2020

11962 LNCS

304-315

Daejeon, Korea, Republic of

Springer

Cubemap projection (CMP) becomes a potential panoramic data format for its efficiency. However, default CMP coordinate system with fixed viewpoint may cause distortion, especially around the boundaries of each projection plane. To promote quality of panoramic images in CMP, we propose a content-awared CMP optimization method via deep Q-learning. The key of this method is to predict an angle for rotating the image in Equirectangular projection (ERP), which attempts to keep foreground objects away from the edge of each projection plane after the image is re-projected with CMP. Firstly, the panoramic image in ERP is preprocessed for obtaining a foreground pixel map. Secondly, we feed the foreground map into the proposed deep convolutional network (ConvNet) to obtain the predicted rotation angle. The model parameters are training through the deep Q-learning scheme. Experimental results show our method keep more foreground pixels in center of each projection plane than the baseline.
© 2020, Springer Nature Switzerland AG.

其他

EI

[2016A030310058] ; [827000144] ; National Natural Science Foundation of China[61672443]

20201108278295

Learning systems ; Pixels ; Reinforcement learning

Artificial Intelligence:723.4

EV Compendex

1.College of Computer Science and Software Engineering, Shenzhen University, Shenzhen; 510680, China
2.Institute of Future Networks, Southern University of Science and Technology, Shenzhen, China
3.Peng Cheng Laboratory, PCL Research Center of Networks and Communications, Shenzhen, China

Chen, Zihao,Wang, Xu,Zhou, Yu,et al. Content-Aware Cubemap Projection for Panoramic Image via Deep Q-Learning[C]:Springer,2020:304-315.