基于快速伪球滤波的智能拖拉机视觉导航中场景去雾方法

doi:10.13973/j.cnki.robot.2015.0603

摘要
图/表
参考文献
相关文章 (14)

全文: PDF (1460 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
张征明, 卢伟, 陆静霞. 基于快速伪球滤波的智能拖拉机视觉导航中场景去雾方法[J]. 机器人, 2015, 37(5): 603-613,640.DOI: 10.13973/j.cnki.robot.2015.0603. ZHANG Zhengming, LU Wei, LU Jingxia. Dehazing Method Based on Fast Pseudosphere Filtering for Visual Navigation of Intelligent Tractor in Haze Weather Scene. ROBOT, 2015, 37(5): 603-613,640. DOI: 10.13973/j.cnki.robot.2015.0603.

摘要

为适应智能拖拉机雾霾天气下道路的视觉导航，同时针对作业环境图像背景中天空居多的特征，提出一种基于快速伪球滤波的去雾方法.首先根据滤波器参数利用降秩逼近的方法对视觉图像产生滤波模板.而后利用伪球滤波保持边缘的平滑特性获得准确的暗通道图和大气透射图.最后，利用大气耗散模型的修正解快速恢复无雾图像.实验结果表明，快速伪球滤波方法与导向图滤波、Tarel 中值滤波、多尺度 Retinex、小波域 Retinex 方法相比，对图像去雾效果综合评价指标值分别提高 54.7%、37.6%、35.2%、44%，算法耗时约 0.18s.能够满足智能拖拉机视觉导航实时性的要求.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	张征明
	卢伟
	陆静霞

关键词 ：图像去雾, 伪球滤波, 降秩逼近, 智能拖拉机, 视觉导航

Abstract：

In order to make the visual navigation of intelligent tractors adapt to the foggy weather, an image dehazing method using the fast pseudosphere filter is proposed, to get a clear image from a foggy picture with the sky as main background.Firstly, the filter template for the visual images is obtained based on filter parameters by using the reduced rank approximation method.Then, the edge smoothness is guaranteed through pseudosphere filtering to get the exact dark channel and the atmosphere scattering veil.Finally, a clear view of the image is recovered quickly with the correction solution of the atmospheric dissipation model.The experimental results show that this method can improve the objective assessment indicator of the image dehazing by 54.7%, 37.6%, 35.2% and 44% compared with the guided image filtering method, Tarel median filtering method, multi-scale retinex method and the wavelet-based retinex method.Furthermore, the time consumption of this algorithm is about 0.18s, which can meet requirements of the intelligent tractors for real-time visual navigation.

Key words： image dehazing pseudosphere filter reduced rank approximation intelligent tractor visual navigation

收稿日期: 2015-05-18 录用日期: 2015-08-21

TP39

基金资助:

国家自然科学基金青年基金资助项目（51405239）；江苏省自然科学基金青年基金资助项目（BK20130696）；中央高校基本科研业务费专项资金资助项目（KYZ201427）；远程测控技术江苏省重点实验室开放基金资助项目（YCCK201501）

通讯作者: 卢伟，njaurobot@njau.edu.cn E-mail: njaurobot@njau.edu.cn

作者简介: 张征明（1994~-），男，本科生.研究领域:机器人传感与控制技术.
卢伟（1978~-），男，博士，副教授，硕士生导师.研究领域:机器人传感与控制，无损检测及微弱信号处理.

链接本文:

https://robot.sia.cn/CN/10.13973/j.cnki.robot.2015.0603 或 https://robot.sia.cn/CN/Y2015/V37/I5/603

[1] Li B, Wang M H.In-field recognition and navigation path extraction for pineapple harvesting robots[J].Intelligent Automation & Soft Computing, 2013, 19(1): 9-20.

[2] Wei X Q, Jia K, Lan J H, et al.Automatic method of fruit objectextraction under complex agricultural background for vision system of fruit picking robot[J].OPTIK, 2014, 125(19): 5684-5689.

[3] Tang J L, Jing X, He D J, et al.Visual navigation control for agricultural robot using serial BP neural network[J].Transactions of the Chinese Society of Agricultural Engineering, 2011, 27(2): 194-198.

[4] 赵德安,贾伟宽,张云,等.农业机器人自主导航改进自适应滤波控制器设计[J/OL].[2015-03-16].http://www.cnki.net/kcms/detail/11.1964.S.20150316.0939.003.html.Zhao D A, Jia W K, Zhang Y, et al.Design to agricultural robot autonomous navigation control based on improved self-adaptive filter[J/OL].[2015-03-16].http://www.cnki.net/kcms/detail/11.1964.S.20150316.0939.003.html.

[5] Zhou Z Y, Zhang Z G, Luo X W.A fuzzy path preview algorithmfor the rice transplanting robot navigation system[J].Journal of Software, 2014, 9(4): 881-888.

[6] 李景彬,陈兵旗,刘阳.棉花铺膜播种机导航路线图像检测方法[J].农业机械学报,2014,40(1):40-45. Li J B, Chen B Q, Liu Y.Image detection method of navigation route of cotton plastic film mulch planter[J].Transactions of the Chinese Society for Agricultural Machinery, 2014, 40(1): 40-45.

[7] Ji W, Zhao D A, Cheng F Y, et al.Automatic recognition vision system guided for apple harvesting robot[J].Computers and Electrical Engineering, 2012, 38(5): 1186-1195.

[8] 肖胜笔,李燕.具有颜色保真性的快速多尺度 Retinex 去雾算法[J].计算机工程与应用,2015,51(6):176-180. Xiao S B, Li Y.Fast multiscale retinex algorithm of image haze removal with color fidelity[J].Computer Engineering and Applications, 2015, 51(6): 176-180.

[9] 赵晓霞,王汝琳,李雪艳.基于多尺度 Retinex 的雾天降质图象增强算法[J].工矿自动化,2009(10):62-66. Zhao X X, Wang R L, Li X Y.Enhancement algorithm of fog-degraded image based on multiscale retinex[J].Industry and Mine Automation, 2009(10): 62-66.

[10] 杨骥,杨亚东,梅雪,等.基于改进的限制对比度自适应直方图的视频快速去雾算法[J].计算机工程与设计,2015,36(1):221-226. Yang J, Yang Y D, Mei X, et al.Fast video dehazing based on improved contrast limited adaptive histogram equalization[J].Computer Engineering and Design, 2015, 36(1): 221-226.

[11] 王一帆,尹传历,黄义明,等.基于双边滤波的图像去雾[J].中国图象图形学报,2014,19(3):386-392. Wang Y F, Yin C L, Huang Y M, et al.Image haze removal using a bilateral filter[J].Journal of Image and Graphics, 2014, 19(3): 386-392.

[12] 曹永妹,张尤赛.图像去雾的小波域Retinex算法[J].江苏科技大学报,2014,28(1):50-55. Cao Y M, Zhang Y S.Wavelet-based retinex algorithm for image defogging[J].Journal of Jiangsu University of Science and Technology, 2014, 28(1): 50-55.

[13] Zhu R, Wang L J.Improved wavelet transform algorithm for single image dehazing[J].OPTIK, 2014, 125(13): 3064-3066.

[14] He K M, Sun J, Tang X O.Single image haze removal using dark channel prior[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341-2353.

[15] Tarel J P.Fast visibility restoration from a single color or gray level image[C]//12th IEEE International Conference on Computer Vision and Pattern Recognition.Piscataway, USA: IEEE, 2009: 2201-2208.

[16] Narasimhan S G, Nayar S K.Contrast restoration of weather degraded images[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(6): 713-724.

[17] 孙红光,房超,张慧杰,等.一种自适应基于暗通道先验的去雾方法[J].吉林大学学报,2012,50(5):987-992.Sun H G, Fang C, Zhang H J, et al.An adaptive haze removal based on dark channel prior[J].Journal of Jilin University, 2012, 50(5): 987-992.

[18] Jiang J G, Hou T F, Qi M B.Improved algorithm on image haze removal using dark channel prior[J].Journal of Circuits and Systems, 2011, 16(2): 7-12.

[19] 张冰冰.去雾通用框架及算法研究[D].厦门:华侨大学,2013.Zhang B B.Research on general fog removal framework and algorithm[D].Xiamen: Huaqiao University, 2013.

[20] 王志衡,吴福朝.伪球滤波和边缘检测[J].软件学报,2008,19(4):803-816.Wang Z H, Wu F C.Pseduosphere filter and edge detection[J].Journal of Software, 2008, 19(4): 803-816.

[21] He K M, Sun J, Tang X O.Guided image filtering[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(6): 1397-1409.

[22] Guo F, Tan J, Cai Z X.Objective measurement for image defogging algorithms[J].Journal of Central South University, 2014, 21(1): 272-286.

[23] Tarel J P, Aurelien C, Houssam H.Foggy road image database [DB/OL].[2010-03-05].http://www.Lcpc.fr/english/products/image-databases/-article/frida-foggy-road-image-database.