保留边界特征的深度图像增强算法研究

针对现有深度图像增强算法存在边界保留特性差的问题, 提出梯度掩模导向联合滤波(gradient mask guided joint filter,GMGJF)算法。利用深度图像进行Sobel梯度变换获取边界方向信息, 利用深度图像空洞区域生成空洞掩模, 再以边界方向和空洞掩模为导向联合彩色图像对深度图像进行迭代高斯滤波和空洞填充。实验结果表明, GMGJF算法的PSNR(peak signal to noise ratio)、SSIM(structural similarity index measure)比IMF(iterative median filter)、GF(guided filter)、JBF(joint bilateral filter)算法的PSNR、SSIM至少提高了3.50%和1.07%, 不仅去噪能力、空洞填充能力最强, 而且边界特征保持最好, 有利于深度图像的特征提取与目标识别。

Abstract

The drawback of current depth image enhancement algorithms is poor performance of edge preserving. To solve this drawback, the gradient mask guided joint filtering(GMGJF)algorithm is proposed. The Sobel gradient transform is used to obtain the boundary direction information,and the hole region of the depth images was utilized to generate the hole mask.Furthermore, taking the boundary direction and the cavity mask as the guidance, the color image was jointed to perform iterative Gaussian filtering and hole filling on the depth image. Experimental results show that the peak signal to noise ratio(PSNR)and the structural similarity index measure(SSIM) of GMGJF algorithm are improved by at least 3.50% and 1.07% respectively, compared with the iterative median filter( IMF), guided filter (GF) and joint bilateral filter(JBF) algorithms , it has both the strongest ability of denoising and hole filling, and can remain the boundary features best, which is good for feature extraction and target recognition of depth image.

参考文献

[1] BUDZAN S, KASPRZYK J. Fusion of 3D laser scanner and depth images for obstacle recognition in mobile applications［J］. Optics and Lasers in Engineering, 2016, 77(7): 230-240.

[2] 杨鸿, 钱堃, 戴先中, 等. 基于Kinect传感器的移动机器人室内环境三维地图创建［J］. 东南大学学报: (自然科学版),2013, 43(s1): 183-187.

YANG Hong, QIAN Kun, DAI Xianzhong, et al. Kinect-based 3D indoor environment map building for mobile robot［J］. Journal of Southeast University: Natural Science Edition, 2013,43(s1): 183-187.

[3] 秦超龙, 宋爱国, 吴常铖, 等. 基于Unity 3D与Kinect的康复训练机器人情景交互系统［J］. 仪器仪表学报, 2017, 38(3): 530-536.

QIN Chaolong, SONG Aiguo, WU Changcheng, et al. Scenario interaction system of rehabilitation training robot based on Unity 3D and Kinect［J］. Chinese Journal of Scientific Instrument, 2017, 38(3): 530-536.

[4] TANG S, ZHU Q, CHEN W, et al. Enhanced RGB-D mapping method for detailed 3D indoor and outdoor modeling［J］. Sensors, 2016, 16(10): 1589.

[5] 郭连朋, 陈向宁, 刘彬,等. 基于Kinect传感器多深度图像融合的物体三维重建［J］. 应用光学, 2014(5): 811-816.

GUO Lianpeng, CHEN Xiangning, LIU Bin, et al. 3D-object reconstruction based on depth images by Kinect sensor［J］. Journal of Applied Optics, 2014,35(5): 811-816.

[6] MALLICK T, DAS P P, MAJUMDAR A K. Characterizations of noise in kinect depth images: A review［J］. Sensors Journal IEEE, 2014, 14(6): 1731-1740.

[7] LIU R, LI B, HUANG Z, et al. Hole filling using joint bilateral filtering for moving object segmentation［J］. Journal of Electronic Imaging, 2014, 23(6): 063021.

[8] 李知菲, 陈源. 基于联合双边滤波器的Kinect深度图像滤波算法［J］. 计算机应用, 2014, 34(8): 2231-2234.

LI Zhifei, CHEN Yuan. Kinect depth image filtering algorithm based on joint bilateral filter［J］. Journal of Computer Applications, 2014, 34(8): 2231-2234.

[9] JUNG S W. Enhancement of image and depth map using adaptive joint trilateral filter［J］. IEEE Transactions on Circuits and Systems for Video Technology, 2013, 23(2): 258-269.

[10] XIAGN X, YAN Z, NAN C, et al. A modified joint trilateral filter based depth map refinement method［C］.US: IEEE,2016.

[11] BAPAT A, RAVI A, RAMAN S. An iterative, non-local approach for restoring depth maps in RGB-D images［C］. US: IEEE, 2015.

[12] YANG Q, AHUJA N, YANG R, et al. Fusion of median and bilateral filtering for range image upsampling［J］. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society, 2013, 22(12): 4841-4852.

[13] HORNG Y R, TSENG Y C, CHANG T S. Stereoscopic images generation with directional Gaussian filter［C］. US: IEEE,2010.

[14] SCHARSTEIN D, PAL C. Learning conditional random fields for stereo［C］.US: IEEE,2007.

[15] HIRSCHMULLER H, SCHARSTEIN D. Evaluation of cost functions for stereo matching［C］.US: IEEE,2007.

[16] 钱钧, 李良福, 周锋飞,等. 基于结构特征引导滤波的深度图像增强算法研究［J］. 应用光学, 2016, 37(2): 203-208.

QIAN Jun, LI Liangfu, ZHOU Fengfei, et al. Depth image enhancement algorithm based on structure feature guidance filter［J］. Journal of Applied Optics, 2016, 37(2): 203-208.

周自顾, 曹杰, 郝群, 高泽东, 肖宇晴. 保留边界特征的深度图像增强算法研究[J]. 应用光学, 2018, 39(2): 200. Zhou Zigu, Cao Jie, Hao Qun, Gao Zedong, Xiao Yuqing. Depth image enhancement algorithm for preserving boundary[J]. Journal of Applied Optics, 2018, 39(2): 200.

保留边界特征的深度图像增强算法研究

关于本站 Cookie 的使用提示

全站搜索

保留边界特征的深度图像增强算法研究

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索