Abstract
Flame location based on binocular vision has some problems such as low matching accuracy, slow matching speed and so on. To solve the above problems, we propose stereo edge matching algorithm based on adaptive window and weight. Since image edge regions has rich information, an edge based adaptive window algorithm is proposed. For non-edge regions, adaptive weight algorithm based on row and column is accumulated separately, which is used to reduce computational complexity. Finally it gets the position of the flame according to disparity map. The experimental results show that the matching algorithm based on adaptive window and weight can locate the fire source. Its error is within 10 cm and the matching speed is higher and the effect is better.
Similar content being viewed by others
References
Hosni A, Bleyer M, Gelautz M (2010) Near real-time stereo with adaptive support weight approaches. Procdpvt
Zhang L, Seitz SM (2007) Estimating optimal parameters for MRF stereo from a single image pair. IEEE Transact Patt Analysis Mach Intell 29(2):331–342
Martull S, Peris M, Fukui K (2012) Realistic CG Stereo image dataset with ground truth disparity maps. Tech Rep Ieice Prmu 111:117–118
Xiong YF, Huang XQ, Li MQ et al (2017) Combustion diagnosis method based on stereo vision technology. Propulsion Technol 38(03):673–679
Chen W (2013) Binocular vision moving target tracking based on visible light and infrared camera. Nanjing University of Aeronautics and Astronautics, Nanjing
Zhang J, Pan JS, Wu YP et al (2009) Moving target tracking and measurement based on binocular vision. Comput Eng Appl 45(25):191–194
Nie, G.Y., Cheng, M.M., Liu, Y. et al. (2019) Multi-level context ultra-aggregation for stereo matching. IEEE CVPR
Zhou F (2013) Research and implementation of stereo matching algorithm in binocular vision. Dalian University of Technology, Dalian
Jing X (2013) Research on binocular stereo matching Technology in Computer Vision. Nanjing University of Science and Technology, Nanjing
Liu XQ (2011) Research on stereo matching algorithm based on binocular stereo vision. Central South University, Changsha
Zhu LJ, Wu JG, G X et al (2011) Research on Touch Technology Based on Binocular Vision. Microcomput Appl 30(1):26–28
Gao WS, Qian H, Chen P (2010) Human motion simulation based on binocular stereo vision. Comput Eng 36(24):158–160
Gong WB, Gu GH, Qian WX (2015) Stereo matching algorithm based on image segmentation and adaptive support weights. J Opt 35(02):62–69
Zhang K, Lu J, Lafruit G (2009) Cross-based local stereo matching using orthogonal integral images. IEEE Transact Circ Syst Vid Technol 19(7):1073–1079
Tombari F, Mattoccia S, Stefano LD et al (2009) Near real-time stereo based on effective cost aggregation[C] international conference on pattern recognition. IEEE:1–4
Birchfield S, Tomasi C (1999) Depth discontinuities by pixel-to-pixel stereo. Int J Comput Vis 35(3):269–293
Zhu SP, Li Z (2015) Stereo matching algorithm based on improved gradient and adaptive window. J Opt 35(1):115–123
Zhao, J., Cao, Y., Fan, D.P. et al. (2019) Contrast prior and fluid pyramid integration for RGBD salient object detection, IEEE CVPR
Ju, R., Ge, L., Geng, W. et al. (2014) Depth saliency based on anisotropic center-surround difference. IEEE International Conference on Image Processing (ICIP). IEEE
Yoon KJ, Kweon IS (2005) Locally adaptive support-weight approach for visual correspondence search[C] IEEE computer society conference on computer vision and pattern recognition. IEEE Comput Soc:924–931
Gao R (2014) Research on infrared binocular vision positioning system for tunnel fire. Chang’an University, Chang’an
Xi JM (2011) Research on automatic location method of large space fire based on binocular stereo vision. Chongqing University, Chongqing
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Jia, D., Wang, Z. & Liu, J. Research on flame location based on adaptive window and weight stereo matching algorithm. Multimed Tools Appl 79, 7875–7887 (2020). https://doi.org/10.1007/s11042-019-08601-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-019-08601-1