连续性健美操动作图像视觉误差校正方法分析
|
摘要
为了解决传统方法校正后图像容易出现模糊或锯齿效应,视觉误差校正效果不好的问题,研究了一种新的连续性健美操动作图像视觉误差校正方法。通过JAI相机(丹麦)逐行扫描电荷耦合器件(CCD)相机转换成视频信号,得到的信号通过图像采集卡采集,转化成PC机可处理的数字信号,通过全息投影获取连续性健美操动作图像。按照视觉误差完成对图像像素集视差函数的配准,通过向量量化技术实现对图像的亚像素级模板匹配,对经处理的连续性健美操动作图像进行分形编码处理,为视觉误差校正提供依据。对连续性健美操动作图像进行编码和解码处理,求出和原始图像间的误差,获取误差图像,对其进行插值处理,获取误差补偿结果,实现连续性健美操动作图像视觉误差校正。结果表明:经所提方法处理后的图像无显著的视觉误差,峰值信噪比和结构相似性很高。可见所提方法主观和客观评价结果好。
In order to solve the problem of blurring or sawtooth effect,and the poor visual error correction effect in the image corrected by traditional methods,a new visual error correction method for continuous aerobics action image was researched. Through JAI camera( Denmark) progressive scanning CCD camera converted into video signal,the obtained signal was collected by image acquisition card and converted into digital signal processed by charge coupled device( PC),the continuous aerobics action image was obtained by holographic projection. The parallax function of image pixel set is registered according to visual error,the sub-pixel template matching of image is realized by vector quantization technology,the processed continuous aerobics action image is processed by fractal coding,which provides a basis for visual error correction. The motion image of continuous aerobics is coded and decoded,the error between the original image and the original image is obtained,and the error image is interpolated to obtain the error compensation results,so as to realize the visual error correction of the motion image of continuous aerobics. The results show that the image processed by the proposed method has no significant visual error,and the peak signal-to-noise ratio( PSNR) and structural similarity are very high. It can be seen that the subjective and objective evaluation results of the proposed method are good.
In order to solve the problem of blurring or sawtooth effect,and the poor visual error correction effect in the image corrected by traditional methods,a new visual error correction method for continuous aerobics action image was researched. Through JAI camera( Denmark) progressive scanning CCD camera converted into video signal,the obtained signal was collected by image acquisition card and converted into digital signal processed by charge coupled device( PC),the continuous aerobics action image was obtained by holographic projection. The parallax function of image pixel set is registered according to visual error,the sub-pixel template matching of image is realized by vector quantization technology,the processed continuous aerobics action image is processed by fractal coding,which provides a basis for visual error correction. The motion image of continuous aerobics is coded and decoded,the error between the original image and the original image is obtained,and the error image is interpolated to obtain the error compensation results,so as to realize the visual error correction of the motion image of continuous aerobics. The results show that the image processed by the proposed method has no significant visual error,and the peak signal-to-noise ratio( PSNR) and structural similarity are very high. It can be seen that the subjective and objective evaluation results of the proposed method are good.
引文
1李振亚.运动视觉误差分析的模型设计与实现[J].现代电子技术,2017,40(18):92-94Li Zhenya. Design and implementation of motion vision error analysis model[J]. Modern Electronics Technique,2017,40(18):92-94
2 赵振庆,叶东,吴斌,等.消隐点共线约束逐点畸变校正算法[J].光学精密工程,2015,23(4):1196-1204Zhao Zhenqing,Ye Dong,Wu Bin,et al. Point wise distortion correction algorithm with vanishing point collinear constraint[J]. Optics and Precision Engineering,2015,23(4):1196-1204
3 李东斌.肥胖人群运动特征不合理性的视觉图像分割[J].科技通报,2015,31(8):259-261Li Dongbin. Visual image segmentation of motion characteristic of obese people[J]. Bulletin of Science and Technology,2015,31(8):259-261
4 Guo W,He D,Cai N. On capacity of network error correction coding with random errors[J]. IEEE Communications Letters,2018,22(4):696-699
5 郑帅超,房立金,徐志刚.单目视觉-激光测距定位系统的标定与姿态校正[J].机械科学与技术,2017,36(12):1926-1934Zheng Shuaichao,Fang Lijin,Xu Zhigang. Calibrating and correcting pose of monocular vision and laser ranging location system[J].Mechanical Science and Technology for Aerospace Engineering,2017,36(12):1926-1934
6 周前飞,刘晶红,居波,等.面阵CCD航空相机斜视图像的几何校正[J].液晶与显示,2015,30(3):505-513Zhou Qianfei,Liu Jinghong,Ju Bo,et al. Geometric correction of oblique images for array CCD aerial cameras[J]. Chinese Journal of Liquid Crystals and Displays,2015,30(3):505-513
7 Kuznetsov S O,Revenko A. Interactive error correction in implicative theories[J]. International Journal of Approximate Reasoning,2015,63(1):89-100
8 张飞,李景富.基于智能视觉的高空图像搜集系统的设计与实现[J].计算机测量与控制,2015,23(3):939-941Zhang Fei,Li Jingfu. Aerial image collecting system design and implementation based on intelligent vision[J]. Computer Measurement&Control,2015,23(3):939-941
9 刘和臣.运动员动作三维视觉图像准确识别仿真研究[J].计算机仿真,2016,33(8):369-372Liu Hechen. Simulation study on accurate recognition of 3D Visual Image of athlete's Action[J]. Computer Simulation,2016,33(8):369-372
10 柯鑫,江威,朱江兵.基于视觉注意机制的眼底图像视盘快速定位与分割[J].科学技术与工程,2015,15(35):47-53Ke Xin,Jiang Wei,Zhu Jiangbing. Fast location and segemention of optic disk in the fundus image based on visual attention[J]. Science Technology and Engineering,2015,15(35):47-53
11 Almheiri A,Dong X,Harlow D. Bulk locality and quantum error correction in AdS/CFT[J]. Journal of High Energy Physics,2015,2015(4):1-34
12 窦健泰,高志山,马骏,等.基于图像信息熵的ptychography轴向距离误差校正[J].物理学报,2017,66(16):107-115Dou Jiantai,Gao Zhishan,Ma Jun,et al. Correction of axial distance error in ptychography based on image information entropy[J].Acta Physica Sinica,2017,66(16):107-115
13 乔良.三维图像视觉下运动关键特征的提取方法改进[J].计算机仿真,2017,34(1):216-219Qiao Liang. Under the 3 d image visual movement key feature extraction method of improvement[J]. Computer Simulation,2017,34(1):216-219
14 李宇嘉,付利平,王永松.楔条形阳极紫外探测器图像畸变校正[J].电子设计工程,2017,25(21):133-136Li Yujia,Fu Liping,Wang Yongsong. Image rectification algorithms of wedge and strip anode detector[J]. Electronic Design Engineering,2017,25(21):133-136
15 荆旭,邱世广,尹旭悦,等.光轴外扩式布置的双目相机图像立体校正[J].上海交通大学学报,2015,49(2):141-149Jing Xu,Qiu Shiguang,Yin Xuyue,et al. Stereo correction of binocular images with optical axes divergent arrangement[J]. Journal of Shanghai Jiaotong University,2015,49(2):141-149
16 马玲,周斌.三维视觉图像跟踪运动员对受伤目标监测仿真[J].计算机仿真,2017,34(2):422-425Ma Ling,Zhou Bin. Simulation of 3D visual image tracking athletes'monitoring of injured target[J]. Computer Simulation,2017,34(2):422-425
17 朱爱斌,何大勇,邹超,等.刀具磨损图像视差图的非标定方法[J].西安交通大学学报,2016,50(3):8-15Zhu Aibin,He Dayong,Zou Chao,et al. Uncalibrated method for disparity map of tool wear images[J]. Journal of Xi'an Jiaotong University,2016,50(3):8-15
2 赵振庆,叶东,吴斌,等.消隐点共线约束逐点畸变校正算法[J].光学精密工程,2015,23(4):1196-1204Zhao Zhenqing,Ye Dong,Wu Bin,et al. Point wise distortion correction algorithm with vanishing point collinear constraint[J]. Optics and Precision Engineering,2015,23(4):1196-1204
3 李东斌.肥胖人群运动特征不合理性的视觉图像分割[J].科技通报,2015,31(8):259-261Li Dongbin. Visual image segmentation of motion characteristic of obese people[J]. Bulletin of Science and Technology,2015,31(8):259-261
4 Guo W,He D,Cai N. On capacity of network error correction coding with random errors[J]. IEEE Communications Letters,2018,22(4):696-699
5 郑帅超,房立金,徐志刚.单目视觉-激光测距定位系统的标定与姿态校正[J].机械科学与技术,2017,36(12):1926-1934Zheng Shuaichao,Fang Lijin,Xu Zhigang. Calibrating and correcting pose of monocular vision and laser ranging location system[J].Mechanical Science and Technology for Aerospace Engineering,2017,36(12):1926-1934
6 周前飞,刘晶红,居波,等.面阵CCD航空相机斜视图像的几何校正[J].液晶与显示,2015,30(3):505-513Zhou Qianfei,Liu Jinghong,Ju Bo,et al. Geometric correction of oblique images for array CCD aerial cameras[J]. Chinese Journal of Liquid Crystals and Displays,2015,30(3):505-513
7 Kuznetsov S O,Revenko A. Interactive error correction in implicative theories[J]. International Journal of Approximate Reasoning,2015,63(1):89-100
8 张飞,李景富.基于智能视觉的高空图像搜集系统的设计与实现[J].计算机测量与控制,2015,23(3):939-941Zhang Fei,Li Jingfu. Aerial image collecting system design and implementation based on intelligent vision[J]. Computer Measurement&Control,2015,23(3):939-941
9 刘和臣.运动员动作三维视觉图像准确识别仿真研究[J].计算机仿真,2016,33(8):369-372Liu Hechen. Simulation study on accurate recognition of 3D Visual Image of athlete's Action[J]. Computer Simulation,2016,33(8):369-372
10 柯鑫,江威,朱江兵.基于视觉注意机制的眼底图像视盘快速定位与分割[J].科学技术与工程,2015,15(35):47-53Ke Xin,Jiang Wei,Zhu Jiangbing. Fast location and segemention of optic disk in the fundus image based on visual attention[J]. Science Technology and Engineering,2015,15(35):47-53
11 Almheiri A,Dong X,Harlow D. Bulk locality and quantum error correction in AdS/CFT[J]. Journal of High Energy Physics,2015,2015(4):1-34
12 窦健泰,高志山,马骏,等.基于图像信息熵的ptychography轴向距离误差校正[J].物理学报,2017,66(16):107-115Dou Jiantai,Gao Zhishan,Ma Jun,et al. Correction of axial distance error in ptychography based on image information entropy[J].Acta Physica Sinica,2017,66(16):107-115
13 乔良.三维图像视觉下运动关键特征的提取方法改进[J].计算机仿真,2017,34(1):216-219Qiao Liang. Under the 3 d image visual movement key feature extraction method of improvement[J]. Computer Simulation,2017,34(1):216-219
14 李宇嘉,付利平,王永松.楔条形阳极紫外探测器图像畸变校正[J].电子设计工程,2017,25(21):133-136Li Yujia,Fu Liping,Wang Yongsong. Image rectification algorithms of wedge and strip anode detector[J]. Electronic Design Engineering,2017,25(21):133-136
15 荆旭,邱世广,尹旭悦,等.光轴外扩式布置的双目相机图像立体校正[J].上海交通大学学报,2015,49(2):141-149Jing Xu,Qiu Shiguang,Yin Xuyue,et al. Stereo correction of binocular images with optical axes divergent arrangement[J]. Journal of Shanghai Jiaotong University,2015,49(2):141-149
16 马玲,周斌.三维视觉图像跟踪运动员对受伤目标监测仿真[J].计算机仿真,2017,34(2):422-425Ma Ling,Zhou Bin. Simulation of 3D visual image tracking athletes'monitoring of injured target[J]. Computer Simulation,2017,34(2):422-425
17 朱爱斌,何大勇,邹超,等.刀具磨损图像视差图的非标定方法[J].西安交通大学学报,2016,50(3):8-15Zhu Aibin,He Dayong,Zou Chao,et al. Uncalibrated method for disparity map of tool wear images[J]. Journal of Xi'an Jiaotong University,2016,50(3):8-15