自适应纹理区域的多尺度融合立体匹配算法

doi:10.3778/j.issn.1002-8331.2205-0215

摘要/Abstract

摘要： 针对传统立体匹配算法匹配精度低，且单一代价函数不能同时应对强纹理区域、弱纹理和无纹理区域的问题，提出一种自适应纹理区域的多尺度融合立体匹配算法。首先设置自适应阈值，将图像划分为强纹理区域、弱纹理和无纹理区域，采用不同的尺度信息融合计算代价，在强纹理区域采用AD与Census相结合计算代价，在弱纹理和无纹理区域采用AD与梯度相结合计算代价；在代价聚合部分，为了解决传统十字臂区域构建过程不能根据不同像素点动态调整臂长的问题，弱化灰度值约束条件，同时添加多阈值梯度约束条件，增加弱纹理和无纹理区域的十字臂长，显著优化弱纹理和无纹理区域聚合过程，达到降低误匹配率的目的；最终通过视差计算和多步视差优化得到视差图。在Middlebury测试平台上进行实验，选择不同光照、不同曝光和无失真三种情况，对比不同代价函数的匹配精度，从而提出多尺度融合代价函数；同时和其他七种主流算法对比代价聚合后的匹配精度，实验结果表明，所提算法较于ELAS，最终平均误匹配率下降3.57个百分点；相较于LESC，实时性相对更强。相比单一的代价函数和聚合方式的立体匹配算法，此算法对不同纹理区域的适应性强，具有很好的鲁棒性。

关键词: 机器视觉, 自适应纹理划分, 立体匹配, 多尺度融合, 聚合十字臂构建

Abstract: Aiming at the problem that the traditional stereo matching algorithm has low matching accuracy and a single cost function can not deal with strong texture region, weak texture region and non texture region at the same time, a multi-scale stereo matching algorithm based on adaptive texture region is proposed. Firstly, the adaptive threshold is set to divide the image into strong texture region, weak texture region and no texture region. Different scale information fusion is used to calculate the cost. In the strong texture region, AD and census are used to calculate the cost, and in the weak texture region and no texture region, AD and gradient are used to calculate the cost. In the cost aggregation part, in order to solve the problem that the traditional cross arm region construction process can not dynamically adjust the arm length according to different pixels, the gray value constraint is weakened, and the multi-threshold gradient constraint is added to increase the cross arm length of weak texture and non texture regions, so as to significantly optimize the aggregation process of weak texture and non texture regions, that can reduce the false matching rate. Finally, the disparity map is obtained by disparity calculation and multi-step disparity optimization. The experiment is carried out on the Middlebury test platform. The matching accuracy of different cost functions is compared under three conditions：different illumination, different exposure and no distortion, so the multi-scale fusion cost function is proposed. At the same time, compared with the other seven mainstream algorithms, the experimental results show that the proposed algorithm has a final average mismatch rate of 3.57 percentage points lower than ELAS. Compared with LESC, this algorithm has relatively stronger real-time performance. Compared with the single cost function and aggregation stereo matching algorithm, this algorithm has strong adaptability to different texture regions and good robustness.

Key words: machine vision, adaptive texture partition, stereo matching, multi-scale fusion, aggregate cross arm construction

陈艺, 于纪言, 于洪森. 自适应纹理区域的多尺度融合立体匹配算法[J]. 计算机工程与应用, 2023, 59(18): 198-206.

CHEN Yi, YU Jiyan, YU Hongsen. Multi-Scale Fusion Stereo Matching Algorithm Based on Adaptive Texture Region[J]. Computer Engineering and Applications, 2023, 59(18): 198-206.

参考文献

[1] 胡春生，闫小鹏，魏红星，等.基于立体视觉的目标检测与轨迹预测研究综述[J].计算机工程与应用，2022，58（3）：50-65.
HU C S，YAN X P，WEI H X，et al.Survey of target detection and trajectory prediction based on stereo vision[J].Computer Engineering and Applications，2022，58（3）：50-65.
[2] 刘越，仲小清，付金宇，等.基于混合优化方法的立体匹配算法[J].系统工程与电子技术，2020，42（12）：2692-2699.
LIU Y，ZHONG X Q，FU J Y，et al.Stereo matching algorithm based on hybrid optimization method[J].Systems Engineering and Electronics，2020，42（12）：2692-2699.
[3] 李锵，段子阳，张一帆，等.基于跨尺度随机游走的立体匹配算法[J].华南理工大学学报（自然科学版），2020，48（1）：84-92.
LI Q，DUAN Z Y，ZHANG Y F，et al.Stereo matching algorithm based on cross-scale random walk[J].Journal of South China University of Technology（Natural Science Edition），2020，48（1）：84-92.
[4] FU Y，LAI K，CHEN W，et al.A pixel pair-based encoding pattern for stereo matching via an adaptively weighted cost[J].IET Image Processing，2021，15（4）：908-917.
[5] HAMZAH R A，IBRAHIM H.Improvement of stereo matching algorithm based on sum of gradient magnitude differences and semi-global method with refinement step[J].Electronics Letters，2018，54（14）：876-877.
[6] SUN X，MEI X，JIAO S，et al.Real-time local stereo via edge-aware disparity propagation[J].Pattern Recognition Letters，2014，49：201-206.
[7] 闫利，王芮，刘华，等.基于改进代价计算和自适应引导滤波的立体匹配[J].光学学报，2018，38（11）：257-267.
YAN L，WANG R，LIU H，et al.Stereo matching method based on improved cost computation and adaptive guided filter[J].Acta Optica Sinica，2018，38（11）：257-267.
[8] ZHU S，YAN L.Local stereo matching algorithm with efficient matching cost and adaptive guided image filter[J].Visual Computer，2017，33（9）：1087-1102.
[9] PHUC HONG N，AHN C W.Stereo matching methods for imperfectly rectified stereo images[J].Symmetry-Basel，2019，11（4）.
[10] 冯彬彬，蒋新华，林俊杰，等.基于FPGA的实时SGM匹配算法研究与实现[J].计算机工程与应用，2017，53（22）：163-168.
FENG B B，JIANG X H，LIN J J，et al.Research and implementation of real-time semi global matching algorithm based on FPGA stereo vision[J].Computer Engineering and Applications，2017，53（22）：163-168.
[11] ZHANG J，ZHANG Y，WANG C，et al.Binocular stereo matching algorithm based on MST cost aggregation[J].Mathematical Biosciences and Engineering，2021，18（4）：3215-3226.
[12] YAO M，OUYANG W，XU B.Hybrid cost aggregation for dense stereo matching[J].Multimedia Tools and Applications，2020，79（31/32）：23189-23202.
[13] 宋嘉菲，张浩东.轻量级自适应上采样立体匹配[J].计算机工程与应用，2022，58（16）：139-146.
SONG J F，ZHANG H D.Lightweight adaptive upsampling module for stereo matching[J].Computer Engineering and Applications，2022，58（16）：139-146.
[14] XU Y，ZHAO Y，YANG K，et al.A novel adaptive shape support window based cost aggregation method for local stereo matching[C]//IEEE International Conference on Imaging Systems and Techniques（IST）/IEEE International School on Imaging，2014：376-380.
[15] 畅雅雯，赵冬青，单彦虎.多特征融合和自适应聚合的立体匹配算法研究[J].计算机工程与应用，2021，57（23）：219-225.
CHANG Y W，ZHAO D Q，SHAN Y H.Research on stereo matching algorithm based on multi-feature fusion and adaptive aggregation[J].Computer Engineering and Applications，2021，57（23）：219-225.
[16] HAMZAH R A，IBRAHIM H，ABU HASSAN A H.Stereo matching algorithm based on per pixel difference adjustment，iterative guided filter and graph segmentation[J].Journal of Visual Communication and Image Representation，2017，42：145-160.
[17] 孔令寅，朱江平，应三丛.基于引导图像和自适应支持域的立体匹配[J].光学学报，2020，40（9）：86-98.
KONG L Y，ZHU J P，YING S C.Stereo matching based on guidance image and adaptive support region[J].Acta Optica Sinica，2020，40（9）：86-98.
[18] CHENG X，ZHAO Y，YANG W，et al.LESC：superpixel cut-based local expansion for accurate stereo matching[J].IET Image Processing，2022，16（2）：470-484.
[19] JELLAL R A，LANGE M，WASSERMANN B，et al.LS-ELAS：line segment based efficient large scale stereo matching[C]//2017 IEEE International Conference on Robotics and Automation（ICRA），2017：146-152.
[20] LIU H，CAI Y，ZHOU S，et al.Stereo matching with multi-scale based on anisotropic match cost[J].Concurrency and Computation-Practice & Experience，2020，32（24）.
[21] GUO X，WANG Y J，FU D H，et al.A weight guided filtering matching algorithm combining three measures[J].Computer Engineering and Science，2019，41（6）：1044-1049.
[22] YAO P，ZHANG H，XUE Y，et al.As-global-as-possible stereo matching with adaptive smoothness prior[J].IET Image Processing，2019，13（1）：98-107.
[23] RATHNAYAKA P，PARK S Y.iGG-MBS：iterative guided-gaussian multi-baseline stereo matching[J].IEEE Access，2020，8：99205-99218.
[24] KONG L，ZHU J，YING S.Stereo matching based on guidance image and adaptive support region[J].Acta Optica Sinica，2020，40（9）.