Design of Rapid Image Mosaic Based on CUDA by 100-Megapixel Optical System

To avoid the difficulty of image processing in the gigapixel optical system, this paper proposes a CUDA-based acceleration strategy for the rapid mosaic of a large-scale image and realizes the rapid mosaic of a large-scale image using the collaborative processing of CPU and GPU. Finally, the author designed an electronic hardware and software system and a fast splicing algorithm suitable for the rapid processing of large-scale image-based on a 100-megapixel monocentric multiscale optical system. And the real-time processing of data from nine 12 million pixel sub-cameras at 7.5 frames per second is completed to realize the real-time splicing of the video in the whole field of view.

[1]  P. Sadayappan,et al.  Characterizing and enhancing global memory data coalescing on GPUs , 2015, 2015 IEEE/ACM International Symposium on Code Generation and Optimization (CGO).

[2]  Zhe Zhu,et al.  A Comparative Study of Blending Algorithms for Realtime Panoramic Video Stitching , 2016, ArXiv.

[3]  Jeffrey S. Vetter,et al.  A Survey of CPU-GPU Heterogeneous Computing Techniques , 2015, ACM Comput. Surv..

[4]  Paul Richmond,et al.  Simulating heterogeneous behaviours in complex systems on GPUs , 2018, Simul. Model. Pract. Theory.

[5]  Nikolai Baudis,et al.  Performance Evaluation of Priority Queues for Fine-Grained Parallel Tasks on GPUs , 2017, 2017 IEEE 25th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS).

[6]  Markus H. Gross,et al.  Panoramic Video from Unstructured Camera Arrays , 2015, Comput. Graph. Forum.

[7]  M E Gehm,et al.  Characterization of the AWARE 10 two-gigapixel wide-field-of-view visible imager. , 2014, Applied optics.

[8]  Wentong Cai,et al.  Evaluation of Conflict Resolution Methods for Agent-Based Simulations on the GPU , 2018, SIGSIM-PADS.

[9]  Vivek Sarkar,et al.  Automatic data layout generation and kernel mapping for CPU+GPU architectures , 2016, CC.

[10]  Babak Falsafi,et al.  FPGAs versus GPUs in Data centers , 2017, IEEE Micro.