基于改进暗通道先验算法的农田视频实时去雾清晰化系统
|
摘要
为解决雨雾天气条件下基本农田视频监控图像的退化问题,在暗通道先验(dark channel prior,DCP)去雾算法的基础上,利用拉普拉斯金字塔的区域细节重建方法,实现了大面积亮域场景下自适应去雾的改进暗通道先验算法(modified dark channel prior,MDCP),进而基于该算法提出了一种DSP嵌入式系统的前端化视频图像去雾清晰化处理方案。试验表明:MDCP算法相较于DCP算法和Retinex算法在细节强度、色调还原以及结构信息方面均表现得更为突出,综合评测指标可达0.93;处理后的视频图像对比度良好,彩色图像颜色的饱和度和真实性有效保持,轮廓对比度以及远端天空细节明显增强;MDCP算法的处理速度优势随图像尺寸增大而逐渐增大,在图像尺寸为1 280×720时,MDCP算法比DCP算法的平均处理速度提高5.9%。研究结果为雨雾天气下退化视频图像进行前端化去雾处理方案设计提供理论依据和实践指导。
Using real-time video to capture farmland digitization regulation is an important step in the protection of essential farmland, but problems exist such as a large area of bright sky background and extreme weather i.e. image degradation caused by rain or fog. Generally, we run the defogging process which is used for image processing to clarify the hazy image in the service. However, the cost is high and the process is in unreal time so that it is not suitable for the storage of video data and real-time alarm. With the innovation of computer hardware, it is possible now to defog in real-time under the haze weather. The Langley research center of the national aeronautics and space administration transplanted the algorithm which is based on Retinex algorithm to DSP(Digital signal process) enhancement system that meets the real-time requirements to deal with 256 ×256 gray-scale image. Claire Vue's team from Tsinghua University developed a real-time system on the i Phone 4 to defog 192 ×144 video image. Cai Zixing's team from Central South University put forwarded an algorithm based on the mist theory to achieve theoretical efficiency of real-time processing. In this paper, we aim at defogging the basic farmland video surveillance images in real-time. We achieved the MDCP(modified dark channel prior)algorithm which was improved on the basis of dark channel prior defogging algorithm with the combination of the dividing and merging of human visual perception to hazing. We built up a system which can clarify the basic farmland video surveillance image by using the subsample of transmittance, adjacent pixels completion, application processing block and the front-end hardware layered method to defog. In order to objectively demonstrate the effectiveness of MDCP algorithm,we used no reference evaluation model to evaluate MDCP algorithm, dark channel prior algorithm and multi-scale Rentinex algorithm and we gained the objective assessment of clarifying the hazy image. The data showed that MDCP algorithm was more prominent in intensity, tone reproduction and information of structural aspects than the other two algorithms in clarification. MDCP algorithm had the highest comprehensive evaluation indicators following by DCP(dark channel prior),and Retinex was the lowest among the three. The defogging system which was used for basic farmland video surveillance included video input device(camera), real-time image processing device(DSP hardware system) and monitor. We adopted SONY SSC-G103 CCD(Charge-couple Device) camera as video input device. DSP hardware system which is made up by the TMS320DM642 platform helped to complete the acquisition of video codec, to format conversion, and to clarify processing. Our test which was based on video image processing and algorithm complexity showed that the system improved the strength of hazy image, tone reproduction and structural information indicator and it kept the good real-time and fluency. In summary, the basic farmland video monitoring front-end of defogging system had some advantages of low cost,low power consumption and processing in real-time while comparing to traditional system which enhanced image in services. It achieved the goal that defogging the video surveillance image in front-end and real-time.
Using real-time video to capture farmland digitization regulation is an important step in the protection of essential farmland, but problems exist such as a large area of bright sky background and extreme weather i.e. image degradation caused by rain or fog. Generally, we run the defogging process which is used for image processing to clarify the hazy image in the service. However, the cost is high and the process is in unreal time so that it is not suitable for the storage of video data and real-time alarm. With the innovation of computer hardware, it is possible now to defog in real-time under the haze weather. The Langley research center of the national aeronautics and space administration transplanted the algorithm which is based on Retinex algorithm to DSP(Digital signal process) enhancement system that meets the real-time requirements to deal with 256 ×256 gray-scale image. Claire Vue's team from Tsinghua University developed a real-time system on the i Phone 4 to defog 192 ×144 video image. Cai Zixing's team from Central South University put forwarded an algorithm based on the mist theory to achieve theoretical efficiency of real-time processing. In this paper, we aim at defogging the basic farmland video surveillance images in real-time. We achieved the MDCP(modified dark channel prior)algorithm which was improved on the basis of dark channel prior defogging algorithm with the combination of the dividing and merging of human visual perception to hazing. We built up a system which can clarify the basic farmland video surveillance image by using the subsample of transmittance, adjacent pixels completion, application processing block and the front-end hardware layered method to defog. In order to objectively demonstrate the effectiveness of MDCP algorithm,we used no reference evaluation model to evaluate MDCP algorithm, dark channel prior algorithm and multi-scale Rentinex algorithm and we gained the objective assessment of clarifying the hazy image. The data showed that MDCP algorithm was more prominent in intensity, tone reproduction and information of structural aspects than the other two algorithms in clarification. MDCP algorithm had the highest comprehensive evaluation indicators following by DCP(dark channel prior),and Retinex was the lowest among the three. The defogging system which was used for basic farmland video surveillance included video input device(camera), real-time image processing device(DSP hardware system) and monitor. We adopted SONY SSC-G103 CCD(Charge-couple Device) camera as video input device. DSP hardware system which is made up by the TMS320DM642 platform helped to complete the acquisition of video codec, to format conversion, and to clarify processing. Our test which was based on video image processing and algorithm complexity showed that the system improved the strength of hazy image, tone reproduction and structural information indicator and it kept the good real-time and fluency. In summary, the basic farmland video monitoring front-end of defogging system had some advantages of low cost,low power consumption and processing in real-time while comparing to traditional system which enhanced image in services. It achieved the goal that defogging the video surveillance image in front-end and real-time.
引文
[1]李灿,张凤荣,朱泰峰,等.基本农田保护区规划调控下的土地利用空间重构分析[J].农业工程学报,2012,28(16):217-224.Li Can,Zhang Fengrong,Zhu Taifeng,et al.Spatial restructurin analysis of land use under planning and control of prim farmland protection area[J].Transactions of the Chinese Societ of Agricultural Engineering(Transactions of the CSAE),201228(16):217-224.(in Chinese with English abstract)
[2]李学明.基于Retinex理论的图像增强算法[J].计算机应用研究,2005(2):235-237.Li Xueming.Image enhancement algorithm based on Retine theory[J].Application Research of Computers,2005(2):235-237(in Chinese with English abstract)
[3]王非同.从“鞋盒子”里拍出的全国“挑战杯”特等奖[N/OL]清华大学新闻网[2011-12-09].http://www.tsinghua.edu.cn p u b l i s h/n e w s/4 2 0 5/2 0 1 1/2 0 1 1 1 2 0 9 1 4 1 5 2 5 2 5 9 6 3 3 3 6 320111209141525259633363_.html.
[4]郭璠,蔡自兴,谢斌.基于雾气理论的视频去雾算法[J].电子学报,2011(9):2019-2025.Guo Fan,Cai Zixing,Xie Bin.Video defogging algorithm based on fog theory[J].Acta Electronica Sinica,2011(9):2019-2025(in Chinese with English abstract)
[5]He Kaiming,Sun Jian,Tang Xiaoou.Single image haze remova using dark channel prior[J].Pattern Analysis and Machin Intelligence,IEEE Transactions on,2011,33(12):2341-2353.
[6]王欣威.基于物理模型的天气退化图像复原技术研究[D].沈阳:沈阳理工大学,2005.Wang Xinwei.Research on the Technology of Restoring weathe degraded image Based on Physical Model[D].Shenyang:Shenyang Ligong University,2005.(in Chinese with English abstract)
[7]陈瑶,孙兴波,黄祥,等.一种改进的暗原色单幅图像去雾方法[J].四川理工学院学报,2012,25(5):62-64.Chen Yao,Sun Xingbo,Huang Xiang,et al.Method of single image removal based on improved dark channel priority[J].Sichuan University of Science&Engineering,2012,25(5):62-64.(in Chinese with English abstract)
[8]Ancuti Codruta O,Ancuti Cosmin,Hermans Chris,et al.A fast semi-inverse approach to detect and remove the haze from a single image[M]//Kimmel Ron,Klette Reinhard,Sugimoto Akihiro.Computer Vision:ACCV 2010.Berlin:Springer,2011:501-514.
[9]王红,何小海,杨晓敏.基于模糊理论和CLAHE的雾天图像自适应清晰化算法[J].微电子学与计算机,2012(1):32-34.Wang Hong,He Xiaohai,Yang Xiaomin.An adaptive foggy image enhancement algorithm based on fuzzy theory and CLAHE[J].Microellectronics and Computer,2012(1):32-34.(in Chinese with English abstract)
[10]禹晶,徐东彬,廖庆敏.图像去雾技术研究进展[J].中国图象图形学报,2011,16(9):1561-1576.Yu Jing,Xu Dongbin,Liao Qingmin.Image defogging:Asurvey[J].Journal of Image and Graphics,2011,16(9):1561-1576.(in Chinese with English abstract)
[11]周胜灵,丁珠玉.基于DM642的农产品图像边缘检测系统设计[J].农机化研究,2012(3):102-105.Zhou Shengling,Ding Zhuyu.Design of agricultural products edge detection system based on DM642[J].Journal of Agricultural Mechanization Research,2012(3):102-105.(in Chinese with English abstract)
[12]葛卫龙,张晓晖,韩宏伟,等.基于DM642的激光水下图像处理系统设计与实现[J].红外与激光工程,2012,41(6):1641-1645.Ge Weilong,Zhang Xiaohui,Han Hongwei,et al.Design and implementation of image processing system for range-gated underwater laser imaging system based on DM642[J].Infrared and Laser Engineering,2012,41(6):1641-1645.(in Chinese with English abstract)
[13]张铁民,庄晓霖.基于DM642的高地隙小车的田间路径识别导航系统[J].农业工程学报,2015,31(4):160-167.Zhang Tiemin,Zhuang Xiaolin.Identification and navigation system of farmland path for high-clearance vehicle based on DM642[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2015,31(4):160-167.(in Chinese with English abstract)
[14]陈天华,卢思翰.基于DSP的小型农用无人机导航控制系统设计[J].农业工程学报,2012,28(21):164-169.Chen Tianhua,Lu Sihan.Autonomous navigation control system of agricultural mini-unmaned aerial vehicles based on DSP[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2012,28(21):164-169.(in Chinese with English abstract)
[15]Shiau Y H,Chen P Y,Yang H Y,et al.Weighted haze removal method with halo prevention[J].Journal of Visual Communication and Image Representation,2014,25(2):445-453.
[16]李大鹏,禹晶,肖创柏.图像去雾的无参考客观质量评测方法[J].中国图象图形学报,2011,16(9):1753-1757.Li Dapeng,Yu Jing,Xiao Chuangbai.No-reference quality assessment method for defogged images[J].Journal of Image and Graphics,2011,16(9):1753-1757.(in Chinese with English abstract)
[17]郭璠,蔡自兴.图像去雾算法清晰化效果客观评价方法[J].自动化学报,2012(9):1410-1419.Guo Fan,Cai Zixing.Objective assessment method for the clearness effect of image defogging algorithm[J].Acta Automatica Sinica,2012(9):1410-1419.(in Chinese with English abstract)
[18]Hines Glenn D,Rahman Zia-ur,Jobson Daniel J,et al.Multiimage registration for an enhanced vision system[Z].2003:5108.
[19]赵晓霞.基于RETINEX理论的视频图像增强系统研究[D].北京:中国矿业大学(北京),2011.Zhao Xiaoxia.Research of Video Images Enhancement System Based on Retinex Theory[D].Beijing:China University of Mining and Technology(Beijing),2011.(in Chinese with English abstract)
[20]方帅,杨静荣,曹洋,等.图像引导滤波的局部多尺度Retinex算法[J].中国图象图形学报,2012(7):748-755.Fang Shuai,Yang Jingrong,Cao Yang,et al.Local multi-scale Retinex algorithm based on guided image filtering[J].Journal of Image and Graphics,2012(7):748-755.(in Chinese with English abstract)
[21]Sun Wei.A new single-image fog removal algorithm based on physical model[J].Optik-International Journal for Light and Electron Optics,2013,124(21):4770-4775.
[22]Gao Yuanyuan,Hu Haimiao,Wang Shuhang,et al.A fast image dehazing algorithm based on negative correction[J].Signal Processing,2014,103(10):380-398.
[23]Woodell Glenn,Jobson Daniel J,Rahman Zia-ur,et al.Enhancement of imagery in poor visibility conditions[Z].2005:5778.
[24]张旭明,徐滨士,董世运.用于图像处理的自适应中值滤波[J].计算机辅助设计与图形学学报,2005,17(2):295-299.Zhang Xuming,Xu Binshi,Dong Shiyun,et al.Adaptive median filtering for image processing[J].Journal of Computer-aided Design&Computer Graphics,2005,17(2):295-299.(in Chinese with English abstract)
[25]郝峻晟,戚飞虎.一种直方图局部均衡化的新方法[J].中国图象图形学报,2003,8(A):13-17.Hao Junsheng,Qi Feihu.A new approach for histogram local equalization[J].Journal of Image and Graphics,2003,8(A):13-17.(in Chinese with English abstract)
[2]李学明.基于Retinex理论的图像增强算法[J].计算机应用研究,2005(2):235-237.Li Xueming.Image enhancement algorithm based on Retine theory[J].Application Research of Computers,2005(2):235-237(in Chinese with English abstract)
[3]王非同.从“鞋盒子”里拍出的全国“挑战杯”特等奖[N/OL]清华大学新闻网[2011-12-09].http://www.tsinghua.edu.cn p u b l i s h/n e w s/4 2 0 5/2 0 1 1/2 0 1 1 1 2 0 9 1 4 1 5 2 5 2 5 9 6 3 3 3 6 320111209141525259633363_.html.
[4]郭璠,蔡自兴,谢斌.基于雾气理论的视频去雾算法[J].电子学报,2011(9):2019-2025.Guo Fan,Cai Zixing,Xie Bin.Video defogging algorithm based on fog theory[J].Acta Electronica Sinica,2011(9):2019-2025(in Chinese with English abstract)
[5]He Kaiming,Sun Jian,Tang Xiaoou.Single image haze remova using dark channel prior[J].Pattern Analysis and Machin Intelligence,IEEE Transactions on,2011,33(12):2341-2353.
[6]王欣威.基于物理模型的天气退化图像复原技术研究[D].沈阳:沈阳理工大学,2005.Wang Xinwei.Research on the Technology of Restoring weathe degraded image Based on Physical Model[D].Shenyang:Shenyang Ligong University,2005.(in Chinese with English abstract)
[7]陈瑶,孙兴波,黄祥,等.一种改进的暗原色单幅图像去雾方法[J].四川理工学院学报,2012,25(5):62-64.Chen Yao,Sun Xingbo,Huang Xiang,et al.Method of single image removal based on improved dark channel priority[J].Sichuan University of Science&Engineering,2012,25(5):62-64.(in Chinese with English abstract)
[8]Ancuti Codruta O,Ancuti Cosmin,Hermans Chris,et al.A fast semi-inverse approach to detect and remove the haze from a single image[M]//Kimmel Ron,Klette Reinhard,Sugimoto Akihiro.Computer Vision:ACCV 2010.Berlin:Springer,2011:501-514.
[9]王红,何小海,杨晓敏.基于模糊理论和CLAHE的雾天图像自适应清晰化算法[J].微电子学与计算机,2012(1):32-34.Wang Hong,He Xiaohai,Yang Xiaomin.An adaptive foggy image enhancement algorithm based on fuzzy theory and CLAHE[J].Microellectronics and Computer,2012(1):32-34.(in Chinese with English abstract)
[10]禹晶,徐东彬,廖庆敏.图像去雾技术研究进展[J].中国图象图形学报,2011,16(9):1561-1576.Yu Jing,Xu Dongbin,Liao Qingmin.Image defogging:Asurvey[J].Journal of Image and Graphics,2011,16(9):1561-1576.(in Chinese with English abstract)
[11]周胜灵,丁珠玉.基于DM642的农产品图像边缘检测系统设计[J].农机化研究,2012(3):102-105.Zhou Shengling,Ding Zhuyu.Design of agricultural products edge detection system based on DM642[J].Journal of Agricultural Mechanization Research,2012(3):102-105.(in Chinese with English abstract)
[12]葛卫龙,张晓晖,韩宏伟,等.基于DM642的激光水下图像处理系统设计与实现[J].红外与激光工程,2012,41(6):1641-1645.Ge Weilong,Zhang Xiaohui,Han Hongwei,et al.Design and implementation of image processing system for range-gated underwater laser imaging system based on DM642[J].Infrared and Laser Engineering,2012,41(6):1641-1645.(in Chinese with English abstract)
[13]张铁民,庄晓霖.基于DM642的高地隙小车的田间路径识别导航系统[J].农业工程学报,2015,31(4):160-167.Zhang Tiemin,Zhuang Xiaolin.Identification and navigation system of farmland path for high-clearance vehicle based on DM642[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2015,31(4):160-167.(in Chinese with English abstract)
[14]陈天华,卢思翰.基于DSP的小型农用无人机导航控制系统设计[J].农业工程学报,2012,28(21):164-169.Chen Tianhua,Lu Sihan.Autonomous navigation control system of agricultural mini-unmaned aerial vehicles based on DSP[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2012,28(21):164-169.(in Chinese with English abstract)
[15]Shiau Y H,Chen P Y,Yang H Y,et al.Weighted haze removal method with halo prevention[J].Journal of Visual Communication and Image Representation,2014,25(2):445-453.
[16]李大鹏,禹晶,肖创柏.图像去雾的无参考客观质量评测方法[J].中国图象图形学报,2011,16(9):1753-1757.Li Dapeng,Yu Jing,Xiao Chuangbai.No-reference quality assessment method for defogged images[J].Journal of Image and Graphics,2011,16(9):1753-1757.(in Chinese with English abstract)
[17]郭璠,蔡自兴.图像去雾算法清晰化效果客观评价方法[J].自动化学报,2012(9):1410-1419.Guo Fan,Cai Zixing.Objective assessment method for the clearness effect of image defogging algorithm[J].Acta Automatica Sinica,2012(9):1410-1419.(in Chinese with English abstract)
[18]Hines Glenn D,Rahman Zia-ur,Jobson Daniel J,et al.Multiimage registration for an enhanced vision system[Z].2003:5108.
[19]赵晓霞.基于RETINEX理论的视频图像增强系统研究[D].北京:中国矿业大学(北京),2011.Zhao Xiaoxia.Research of Video Images Enhancement System Based on Retinex Theory[D].Beijing:China University of Mining and Technology(Beijing),2011.(in Chinese with English abstract)
[20]方帅,杨静荣,曹洋,等.图像引导滤波的局部多尺度Retinex算法[J].中国图象图形学报,2012(7):748-755.Fang Shuai,Yang Jingrong,Cao Yang,et al.Local multi-scale Retinex algorithm based on guided image filtering[J].Journal of Image and Graphics,2012(7):748-755.(in Chinese with English abstract)
[21]Sun Wei.A new single-image fog removal algorithm based on physical model[J].Optik-International Journal for Light and Electron Optics,2013,124(21):4770-4775.
[22]Gao Yuanyuan,Hu Haimiao,Wang Shuhang,et al.A fast image dehazing algorithm based on negative correction[J].Signal Processing,2014,103(10):380-398.
[23]Woodell Glenn,Jobson Daniel J,Rahman Zia-ur,et al.Enhancement of imagery in poor visibility conditions[Z].2005:5778.
[24]张旭明,徐滨士,董世运.用于图像处理的自适应中值滤波[J].计算机辅助设计与图形学学报,2005,17(2):295-299.Zhang Xuming,Xu Binshi,Dong Shiyun,et al.Adaptive median filtering for image processing[J].Journal of Computer-aided Design&Computer Graphics,2005,17(2):295-299.(in Chinese with English abstract)
[25]郝峻晟,戚飞虎.一种直方图局部均衡化的新方法[J].中国图象图形学报,2003,8(A):13-17.Hao Junsheng,Qi Feihu.A new approach for histogram local equalization[J].Journal of Image and Graphics,2003,8(A):13-17.(in Chinese with English abstract)