基于混合优化方法的立体匹配算法

doi:10.3969/j.issn.1001-506X.2020.12.04

摘要/Abstract

摘要：

为了改善线性生长算法获得视差图可靠性差的问题,提出了一种基于混合优化方法的立体匹配算法。该算法综合考虑了计算效率和图像可靠性,将视差匹配转换为多目标优化问题,通过提出的基于模拟退火的鸽群优化算法求解此优化问题,从而实现视差阈值的自适应调节,并获取相应的根点的最优视差值。所提出的混合优化方法较好地克服了局部寻优和全局寻优方法易受初值影响且收敛速度慢的缺点。此外,为了进一步提高视差图可靠性,利用滤波法去除不可靠的视差。仿真结果表明,该算法可以获得更多深度信息,提高了线性生长算法计算视差图的可靠性和鲁棒性。

关键词: 立体匹配, 视差图, 自适应调节, 鸽群算法, 模拟退火算法

Abstract:

A stereo matching algorithm based on the hybrid optimization method is proposed to improve the low reliability of the disparity map obtained by the linear growth algorithm. Considering the calculation efficiency and the image reliability comprehensively, the proposed algorithm converts disparity matching into a multi-objective optimization problem. This optimization problem is solved by the pigeon-inspired optimization algorithm based on simulated annealing for realizing the adaptive adjustment of the disparity threshold and obtaining the optimal disparity value of the corresponding root point. The proposed hybrid optimization method overcomes the shortcomings of the local and the global optimization methods, which are vulnerable to initial values and have slow convergence. In addition, the filtering method is used to remove unreliable disparity for further improving the reliability of the disparity map. The simulation results show that the algorithm can get more depth informations, which enhances the reliability and the robustness of the disparity map calculated by the linear growth algorithm.

Key words: stereo matching, disparity map, self-adaptive adjustment, pigeon-inspired algorithm, simulated annealing algorithm

中图分类号:

TP301

刘越, 仲小清, 付金宇, 李想. 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.

Yue LIU, Xiaoqing ZHONG, Jinyu FU, Xiang LI. Stereo matching algorithm based on hybrid optimization method[J]. Systems Engineering and Electronics, 2020, 42(12): 2692-2699.

图/表 9

图1

图2

图3

图4

图5

图6

图7

表1

表2

参考文献 30

1	LI H B , GAO Y K , HUANG Z Y , et al. Stereo matching based on multi-scale fusion and multi-type support regions[J]. Journal of the Optical Society of America A, 2019, 36 (9): 1523- 1533.
2	WU G C , LI Y P , HUANG Y H , et al. Joint view synthesis and disparity refinement for stereo matching[J]. Frontiers of Computer Science, 2019, 13 (6): 1337- 1352.
3	TANAKA M , KATO R , FUJITA T . Review of fractal analysis of fracture surfaces in various materials using three-dimensional images reconstructed by stereo matching method[J]. Strength, Fracture and Complexity, 2020, 12 (2/4): 143- 162.
4	ZHU S P , YAN L N . Local stereo matching algorithm with efficient matching cost and adaptive guided image filter[J]. The Visual Computer, 2017, 33 (9): 1087- 1102.
5	PARK M , YOON K . Learning and selecting confidence mea-sures for robust stereo matching[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2019, 41 (6): 1397- 1411.
6	赵婕, 谢刚. 图像区域分割中的无监督图割方法[J]. 系统工程与电子技术, 2015, 37 (6): 1431- 1436.
	ZHAO J , XIE G . Unsupervised graph cuts for image region segmentation[J]. Systems Engineering and Electronics, 2015, 37 (6): 1431- 1436.
7	SUN J , ZHENG N N , SHUM H Y . Stereo matching using belief propagation[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2003, 25 (7): 787- 800.
8	HATWIB M , SUMEET D , JOEL E W K , et al. An adaptive feature extraction model for classification of thyroid lesions in ultrasound images[J]. Pattern Recognition Letters, 2020, 131, 463- 473.
9	STEFANO L D , MARCHIONNI M , MATTOCCIA S . A fast area-based stereo matching algorithm[J]. Image and Vision Computing, 2004, 22 (12): 983- 1005.
10	张岩, 李建增, 李德良, 等. 快速自适应鲁棒性尺度不变的特征检测子[J]. 系统工程与电子技术, 2017, 39 (6): 1406- 1413.
	ZHANG Y , LI J Z , LI D L , et al. Fast adaptive robust invariant scalable feature detector[J]. Systems Engineering and Electronics, 2017, 39 (6): 1406- 1413.
11	HONG C S , KIM M J , KIM J H , et al. Feasibility of hybrid TomoHelical and TomoDirect-based volumetric gradient matching technique for total body irradiation[J]. Radiation Oncology, 2019, 14 (11): 257- 267.
12	KANG J H , CHEN L , DENG F , et al. Context pyramidal network for stereo matching regularized by disparity gradients[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 157, 201- 215.
13	王新艳, 潘巍, 王月莲, 等. 基于全局差错能量函数的立体匹配算法[J]. 计算机工程, 2017, 43 (7): 244- 249.
	WANG X Y , PAN W , WANG Y L , et al. Stereo matching algorithm based on global error energy function[J]. Computer Engineering, 2017, 43 (7): 244- 249.
14	TENG L , LI H , YIN S L , et al. Improved krill group-based region growing algorithm for image segmentation[J]. International Journal of Image and Data Fusion, 2019, 10 (4): 327- 341.
15	LOTOV A V , RYABIKOV A I . Launch pad method in multiextremal multiobjective optimization problems[J]. Computational Mathematics and Mathematical Physics, 2019, 59 (12): 2041- 2056.
16	ANISHA G , RITESH S , NIBARAN D , et al. Multiobjective optimization for recognition of isolated handwritten indic scripts[J]. Pattern Recognition Letters, 2019, 128, 318- 325.
17	KENT E , YUCRA Q , CARLA N L , et al. An exact algorithm for the blocks relocation problem with new lower bounds[J]. Computers and Operations Research, 2018, 99, 206- 217.
18	MOHAMMAD Y . Introducing a heuristic approach to enhance the reliability of system safety assessment[J]. Quality and Reliability Engineering International, 2019, 35 (8): 2612- 2638.
19	JENA R K . Extended mean-variance portfolio optimization model: a comparative study among swarm intelligence algorithms[J]. International Journal of Accounting and Financial Reporting, 2019, 9 (2): 184- 198.
20	WANG S G . Improved swarm intelligence algorithm for protein folding prediction[J]. Cluster Computing, 2019, 22 (6): 14125- 14134.
21	PRASUN B M . Graphical intuition to duality in linear programming[J]. Operations Management Education Review, 2018, 12, 123- 132.
22	LIN X Y , LI H L . Adaptive control strategy extracted from dynamic programming and combined with driving pattern recognition for SPHEB[J]. International Journal of Automotive Technology, 2019, 20 (5): 1009- 1022.
23	ARABINDA T . A lagrangean relaxation approach to course timetabling[J]. Taylor & Francis, 2017, 31 (7): 599- 603.
24	LI J , XIA Y , LI B , et al. A pseudo-dynamic search ant colony optimization algorithm with improved negative feedback mechanism to solve TSP[J]. Cognitive Systems Research, 2020, 62, 1- 9.
25	吴虎胜, 张凤鸣, 吴庐山. 一种新的群体智能算法--狼群算法[J]. 系统工程与电子技术, 2013, 35 (11): 2430- 2438.
	WU H S , ZHANG F M , WU L S . New swarm intelligence algorithm-wolf pack algorithm[J]. Systems Engineering and Electronics, 2013, 35 (11): 2430- 2438.
26	CUI Z H , ZHANG J J , WANG Y C , et al. A pigeon-inspired optimization algorithm for many-objective optimization poblems[J]. Science China (Information Sciences), 2019, 62 (7): 131- 138.
27	QIU H X , DUAN H B . A multi-objective pigeon-inspired optimization approach to UAV distributed flocking among obstacles[J]. Information Sciences, 2020, 509, 515- 529.
28	WANG Y , ZHANG G B , ZHANG X F . Multilevel image thresholding using tsallis entropy and cooperative pigeon-inspired optimization bionic algorithm[J]. Journal of Bionic Engineering, 2019, 16 (5): 954- 964.
29	NOVITA H , INDRA W , STEFFAN X , et al. Itinerary recommendation generation using enhanced simulated annealing algorithm[J]. Procedia Computer Science, 2019, 157, 605- 612.
30	DIAZ C R , DELGADO S D R , CAGANOVA D , et al. Joint programming of production-maintenance tasks: a simulated annealing-based method[J]. International Journal of Simulation Modeling, 2019, 18 (4): 666- 677.

算法	滤波前	滤波后
GEMM算法	0.002 771	0.070 116
LG算法	0.000 928	0.034 620
本文算法	0.005 520	0.120 746

初值	可靠性
d₀=10, Th_d0=10	0.126 173
d₀=20, Th_d0=30	0.121 654
d₀=30, Th_d0=50	0.121 807
d₀=40, Th_d0=70	0.120 836

[1]	余婧, 雍恩米, 陈汉洋, 郝东, 张显才. 面向多无人机协同对地攻击的双层任务规划方法[J]. 系统工程与电子技术, 2022, 44(9): 2849-2857.
[2]	张彦, 叶春茂, 李璋峰, 鲁耀兵. 多种转发干扰下的脉内脉间波形综合优化设计[J]. 系统工程与电子技术, 2022, 44(5): 1495-1501.
[3]	彭妍, 郭君斌, 于传强, 李静波. 基于视差范围估计和改进代价的半全局匹配[J]. 系统工程与电子技术, 2022, 44(2): 394-400.
[4]	弋佳东, 杨洁. 基于IFOA-SA-BP神经网络的雷达信号识别[J]. 系统工程与电子技术, 2020, 42(12): 2735-2741.
[5]	汪民乐, 范阳涛. 基于效果的常规导弹火力分配模型智能求解算法[J]. 系统工程与电子技术, 2017, 39(11): 2509-2514.
[6]	李岸达, 何桢, 何曙光. 基于GSA的复杂产品关键质量特性识别[J]. 系统工程与电子技术, 2015, 37(9): 2073-2079.
[7]	鄢青青, 沈怀荣, 邵琼玲. 基于遗传-模拟退火算法的空间目标地基监视调度方法[J]. 系统工程与电子技术, 2015, 37(12): 2764-2771.
[8]	姚佩阳1，万路军1,2，孙鹏1，周翔翔3. 基于RHP-IVFSA的多智能体编组#br# 任务分配动态优化[J]. 系统工程与电子技术, 2014, 36(7): 1309-1319.
[9]	赵永波, 李慧, 覃春淼. 基于GASA算法的DFCW-LFM波形设计[J]. 系统工程与电子技术, 2014, 36(11): 2186-2191.
[10]	王慧颖，王文彬. 基于改进搜索策略的混合蜂群算法[J]. 系统工程与电子技术, 2014, 36(10): 2094-2101.
[11]	龚树凤，贲德，潘明海. 基于HGSAA的机会阵雷达离散频率编码波形设计[J]. 系统工程与电子技术, 2013, 35(9): 1854-1860.
[12]	董鹏，杨超，冷静. 战区装备保障点动态选址决策模型及算法[J]. Journal of Systems Engineering and Electronics, 2011, 33(8): 1804-1809.
[13]	麻士东, 龚光红, 韩亮, 宋晓. 目标分配的蚁群-模拟退火算法及其改进[J]. Journal of Systems Engineering and Electronics, 2011, 33(5): 1182-.
[14]	李文, 陈英武, 李菊芳, 姚锋. 基于快速模拟退火的遥感数据处理调度方法[J]. Journal of Systems Engineering and Electronics, 2011, 33(2): 334-338.
[15]	王慧林，黄小军，马满好，邱涤珊. 电子侦察卫星任务调度方法[J]. Journal of Systems Engineering and Electronics, 2010, 32(8): 1695-1699.