基于快速区域建议网络的图像多目标分割算法

doi:10.6040/j.issn.1672-3961.0.2017.592

摘要/Abstract

摘要： 针对传统方法在语义分割中存在大量冗余、结果重叠,造成图像分割算法的结果正确率、鲁棒性较差等问题,提出一种基于快速区域建议网络的图像多目标分割算法。使用选择性搜索(selective search, SS)算法给出初始候选框;采用快速区域建议网络从初始候选框中分类出初始分割框;使用图割算法(GrabCut)从初始分割框中分割出多目标。为了验证本研究算法,采用ImageNet上预训练的VGG16模型,分别使用COCO数据集和CityScapes数据集的训练数据对VGG16模型微调,使用测试数据进行语义分割和多目标图像分割。与YOLO(you only look once,)算法相比,本算法在两个数据集上的平均正确率分别提高了2.16%和1.55%。GrabCut算法在快速区域建议网络的初始分割框上,对多目标的分割更精确,鲁棒性更强。本研究构建的算法通过区域建议网络的得分筛选多目标分割的候选框,保留高得分的候选框来提升图像多目标分割的精度,在多目标的模式识别场合中拥有广泛前景。

关键词: GrabCut算法, selective search算法, 图像分割, 多目标分割, 快速区域建议网络

Abstract: Aim at the shortage of a large amount of redundancy and overlaps of conventional semantic segmentation algorithm, these shortages caused the image segmentation results getting lower accuracy and robust. A new algorithm of multi-objects image segmentation based on faster region proposal networks was proposed. A selective search algorithm was used to get the initial proposal boxes; a faster region proposal network was used to get initial image segmentation boxes. In order to validate our proposed algorithm, the VGG16 models that pre-trained on ImageNet was used on this problem. By using COCO dataset and Cityscapes dataset, the model was well fine-tuned. The test dataset was used for testing semantic segmentation and image segmentation. Compared with YOLO algorithm, the experimental results showed that our proposed algorithm increased mAP of 2.16% and 1.55%. The initial image segmentation boxes by faster region proposal networks were best fitted by GrabCut, multi-objects segmentation results were more accurate and robust. Our proposed algorithm got higher accuracy by sacrifice little time consumption, which got more application scenes in multi-object patterns recognition.

Key words: GrabCut algorithm, faster region proposal network(Faster RPN), selective search algorithm, muti-objects segmentation, image segmentation

中图分类号:

TP391

黄劲潮. 基于快速区域建议网络的图像多目标分割算法[J]. 山东大学学报(工学版), 2018, 48(4): 20-26.

HUANG Jinchao. A new method for muti-objects image segmentation based on faster region proposal networks[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2018, 48(4): 20-26.

参考文献 20

[1]	姜枫,顾庆,郝慧珍,等.基于内容的图像分割方法综述[J].软件学报,2017,28(1):160-183. JIANG Feng, GU Qing, HAO Huizhen, et al. An overview of content-based image segmentation methods[J]. Journal of Software, 2017, 28(1):160-183.
[2]	刘金平,陈青,张进,等.基于集成学习的交互式图像分割[J].电子学报,2016,44(7):1649-1655. LIU Jinping, CHEN Qing, ZHANG Jin, et al. Interactive image segmentation based on integrated learning[J]. Journal of Electronics, 2016, 44(7):1649-1655.
[3]	陈海鹏,申铉京,龙建武,等.采用高斯拟合的全局阈值算法阈值优化框架[J].计算机研究与发展, 2016, 53(4): 892-903. CHEN Haipeng, SHEN Xuanjing, LONG Jianwu, et al. The global threshold optimization framework of gaussian fitting is adopted[J]. Journal of Computer Research and Development, 2016, 53(4):892-903.
[4]	申铉京,张赫,陈海鹏,等.快速递归多阈值分割算法[J].吉林大学学报(工学版),2016,46(2):528-534. SHEN Xuanjing, ZHANG He, CHEN Haipeng, et al. Fast recursive multi-threshold segmentation algorithm[J]. Journal of Jilin University(Engineering and Technology Edition), 2016, 46(2):528-534.
[5]	钱超,张晓林.基于稳定特征点和SLIC超像素分割的快速立体匹配[J].电子设计工程,2016,24(23):146-148,152. QIAN Chao, ZHANG Xiaolin. Fast stereo matching based on stable feature point and SLIC hyperpixel segmentation[J]. Electronic Design Engineering, 2016, 24(23):146-148,152.
[6]	王春波,董红斌,印桂生,等.基于Hadoop的超像素分割算法[J].计算机应用,2016,36(11):2985-2992. WANG Chunbo, DONG Hongbin, YIN Guisheng, et al. Hyperpixel segmentation algorithm based on Hadoop[J]. Journal of Computer Applications, 2016, 36(11):2985-2992.
[7]	WANG X, LI H, BICHOT C E, et al. A graph-cut approach to image segmentation using an affinity graph based on l 0-sparse representation of features[C] //2013 20th IEEE International Conference on Image Processing(ICIP). Melbourne, Australia: IEEE, 2013: 4019-4023.
[8]	REGO Liviane, SUMAILI Jean, MIRANDA Vladimiro, et al. Mean shift densification of scarce data sets in short-term electric power load forecasting for special days[J]. Electrical Engineering, 2017, 99(3):881-898.
[9]	REDMON Joseph, DIVVALA Santosh, GIRSHICK Ross, et al. You only look once: unified, real-time object detection[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE, 2016:3213-3219.
[10]	REN Shaoqing, HE Kaiming, ROSS Girshick, et al. Object detection networks on convolutional feature maps[J]. IEEE transactions on pattern analysis and machine intelligence, 2017, 39(7): 1476-1481.
[11]	LI Z, TANG J. Weakly supervised deep metric learning for community-contributed image retrieval[J]. IEEE Transactions on Multimedia, 2015, 17(11): 1989-1999.
[12]	CROMMELINCK S, BENNETT R, GERKE M, et al. SLIC superpixels for object delineation from UAV data[C] //ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Lund, Sweden: Directory of Open Access Journals, 2017(4): 9-16.
[13]	LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553): 436-444.
[14]	ZOPH Barret,VASUDEVAN Vijay, SHLENS Jonathon, et al. Learning transferable architectures for scalable image recognition[J]. arXiv preprint arXiv:1707.07012(2017).
[15]	SCHMIDHUBER J. Deep learning in neural networks: An overview[J]. Neural networks, 2015, 61: 85-117.
[16]	YU, SHAODE. Efficient segmentation of a breast in B-mode ultrasound tomography using three-dimensional GrabCut(GC3D)[J]. Sensors,2017,17(8): 1827.
[17]	LIN T Y, MAIRE M, BELONGIE S,et al. Microsoft coco: common objects in context[C] //European Conference on Computer Vision. Zurich: Springer International Publishing, 2014: 740-755.
[18]	CORDTS M, OMRAN M, RANMOS S. The cityscapes dataset for semantic urban scene understanding[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE, 2016: 3213-3223.
[19]	NOWOZIN S. Optimal decisions from probabilistic models: the intersection-over-union case[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Columbus, USA: IEEE, 2014: 548-555.
[20]	REDMON Joseph, FARHADI Ali. YOLO9000: better, faster, stronger[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE, 2017:1384-1392.

相关文章 15

[1]	刘全金,嵇文,胡浪涛,黄汇磊,杨瑞,李翔,高泽文,魏本征. 基于双解码器的医学图像分割模型[J]. 山东大学学报 (工学版), 2024, 54(6): 8-18.
[2]	岳仁峰,张嘉琦,刘勇,范学忠,李琮琮,孔令鑫. 基于颜色和纹理特征的立体车库锈蚀检测技术[J]. 山东大学学报 (工学版), 2024, 54(3): 64-69.
[3]	高泽文,王建,魏本征. 基于混合偏移轴向自注意力机制的脑胶质瘤分割算法[J]. 山东大学学报 (工学版), 2024, 54(2): 80-89.
[4]	董璐璐,宋金涛,魏伟波,潘振宽. 多相图像分割变分模型的标签函数提升方法[J]. 山东大学学报 (工学版), 2022, 52(4): 54-68.
[5]	郝晋一,李鹏程,黄艺美,李金屏. 基于穿线法的轮胎X光图像畸变检测[J]. 山东大学学报 (工学版), 2022, 52(3): 9-17.
[6]	董新宇,陈瀚阅,李家国,孟庆岩,邢世和,张黎明. 基于多方法融合的非监督彩色图像分割[J]. 山东大学学报 (工学版), 2019, 49(2): 96-101.
[7]	李璐,范文涛,杜吉祥. 基于Markov随机场的Student's t混合模型的脑MR图像分割[J]. 山东大学学报(工学版), 2017, 47(3): 49-55.
[8]	胡金戈,唐雁. 基于视觉中心转移的视觉显著性检测方法[J]. 山东大学学报(工学版), 2017, 47(3): 27-33.
[9]	樊淑炎, 丁世飞. 基于多尺度的改进Graph cut算法[J]. 山东大学学报(工学版), 2016, 46(1): 28-33.
[10]	于海晶1,2, 李桂菊1*. 基于差分盒维数的彩色烟雾图像识别[J]. 山东大学学报(工学版), 2014, 44(1): 35-40.
[11]	戚世乐,王美清. 自适应分割弱边缘的活动轮廓模型[J]. 山东大学学报(工学版), 2013, 43(6): 17-20.
[12]	管燕,李存华*,仲兆满,孙兰兰. 化学分子结构图分割算法[J]. 山东大学学报(工学版), 2012, 42(5): 65-70.
[13]	张新明, 毛文涛, 李振云. 二阶广义概率的二维Otsu阈值分割[J]. 山东大学学报(工学版), 2012, 42(1): 25-33.
[14]	王丽娅, 潘振宽, 魏伟波*, 刘存良, 张志梅, 王钰. 多相图像分割的交替凸松弛优化及其Split Bregman算法[J]. 山东大学学报(工学版), 2011, 41(2): 40-45.
[15]	王新沛1,刘常春1*,白曈2. 基于均值距离的图像分割方法[J]. 山东大学学报(工学版), 2010, 40(4): 36-41.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed