计算机科学 ›› 2014, Vol. 41 ›› Issue (6): 278-281.doi: 10.11896/j.issn.1002-137X.2014.06.055

• 图形图像与模式识别 • 上一篇    下一篇

全景鸟瞰拼接图像的质量评价方法

常嘉义,秦瑞,李庆,陈大鹏   

  1. 中国科学院微电子研究所 北京100871;中国科学院无锡物联网研究发展中心 无锡214135;中国科学院微电子研究所 北京100871;中国科学院微电子研究所昆山分所 昆山215347;中国科学院微电子研究所 北京100871;中国科学院微电子研究所昆山分所 昆山215347;中国科学院微电子研究所 北京100871
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受汽车移动物联网总体技术研究(2012ZX03005018),智能交通创新服务系统(XDA06040300),国家自然科学基金:面向“智慧工厂”的视觉目标检测和智能决策研究(61303174)资助

Image Quality Assessment of Panoramic Image

CHANG Jia-yi,QIN Rui,LI Qing and CHEN Da-peng   

  • Online:2018-11-14 Published:2018-11-14

摘要: 针对全景拼接图像尚无有效的全参考质量评价方法,无法有效地选择最佳拼接方案以及优化系统参数的问题,创新性地提出一种基于图像信息采样的质量评价方法 ,即通过统计俯视图像素在原始图像中的对应分布,对原始图像素的重采样率和均值方差等统计信息进行分析评估。首先介绍一种车载环视摄像头下4个不同角度的视频图像拼接的方法,然后提出像素采样率性能指标,最后通过仿真实验与实际测试,对比图像方差、熵值和平均梯度等指标,证明了提出的评价方法能够有效地评价拼接图像质量和优化摄像头安装参数。

关键词: 车载环视系统,图像拼接,图像质量评价,像素映射 中图法分类号TP751.1文献标识码A

Abstract: Due to no effective quality evaluation methods for bird-eye panoramic image stitching,a novel metric was proposed,which is based on the sampling distribution of the final image to the original image.According to this metric,a novel framework for image quality assessment integrated with sampling distribution was elaborated in the following section.Firstly,we briefly described a general algorithm of bird-eye panoramic image.Then,the metric based on sampling distribution was proposed.At last,other metrics,such as image variance,entropy and average gradient were compared.The comprehensive experiments demonstrate our method is effective and robust.

Key words: Panorama parking system,Image-stitching,Image quality evaluation,Pixel mapping

[1] Kato K,Suzuki M,Fujita Y,et al.Image synthesis display method and apparatus for vehicle camera:US 7139412[P].2006-11-21
[2] 丁鑫.全景视觉泊车辅助系统研究[D].杭州:浙江大学,2010
[3] 鲁斌,秦瑞,李庆,等.车载环视拼接方法的研究[J].计算机科学,2013,40(9):293-295
[4] Luo L B,Koh I S,Min K Y,et al.Low-cost implementation of bird’s-eye view system for camera-on-vehicle [C]∥ 2010Digest of Technical Papers International Conference on Consumer Electronics (ICCE).IEEE,2010:311-312
[5] Cancare F,Bhandari S,Bartolini D B,et al.A bird's eye view of FPGA-based Evolvable Hardware [C]∥2011NASA/ESA Conference on Adaptive Hardware and Systems (AHS).IEEE,2011
[6] Liu Y C,Lin K Y,Chen Y S.Bird’s-eye view vision system for vehicle surrounding monitoring [M]∥Robot Vision.Springer Berlin Heidelberg,2008:207-218
[7] Scaramuzza D,Martinelli A,Siegwart R.A flexible technique for accurate omnidirectional camera calibration and structure from motion[C]∥ IEEE International Conference on Computer Vision Systems,2006(ICVS’06).IEEE,2006:45-45
[8] Wang Z,Bovik A C,Sheikh H R,et al.Image quality assessment:From error visibility to structural similarity[J].Image Processing,IEEE Transactions on 2004,13(4):600-612
[9] 陈秀新,邢素霞.图像/视频检索与图像融合[M].北京:机械工业出版社,2012:130-224
[10] 丁绪星,朱日宏,李建欣.一种基于人眼视觉特性的图像质量评价[J].中国图象图形学报,2004,9(2):65-69

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!