基于自适应SLIC的人体标准姿势图像分割
|
摘要
为了提高在复杂背景下人体图像分割的精度,提出了一种新的人体图像分割算法.该算法针对简单线性迭代算法(SLIC)在进行超像素块分割时需指定像素块个数的问题,借鉴CV能量模型,通过将图片极小化为多个区域进行水平集迭代分割,从而构造出自适应的超像素块,使得分割后的每个超像素块更贴合图像中的单个色块.然后结合人体平均模板,在图片上标记出感兴趣的人体标准姿势区域,提高了算法对复杂背景的抗干扰能力.最后利用k-means聚类算法将每个超像素块作为节点进行聚类,实现标准人体图像分割.在不同环境下采集多组图片进行实验,结果表明:该算法在保证了图像分割效率的情况下,提高了人体标准姿势的分割精度,对色度丰富的复杂背景抗干扰能力强.
In order to improve the accuracy of human body image segmentation under complex background, a new human body image segmentation algorithm is proposed. This algorithm solves the problem of specifying the number of pixel blocks in the super-pixel block segmentation for the simple linear iterative algorithm(SLIC). By referring to the CV energy model, it is constructed by minimizing the image into multiple regions for horizontal set iterative segmentation.The adaptive super-pixel block is made such that each super-pixel block after the segmentation fits a single color block in the image. Then combined with the human body average template, the human body standard posture area of interest is marked on the picture, which improves the anti-interference ability of the algorithm against the complex background.Finally, each super-pixel block is clustered as a node by k-means clustering algorithm to realize standard human body image segmentation. The experiment is carried out by collecting multiple sets of pictures in different environments. The results show that the proposed algorithm improves the segmentation accuracy of the human body's standard posture and ensures strong anti-interference ability for complex backgrounds with rich chroma.
In order to improve the accuracy of human body image segmentation under complex background, a new human body image segmentation algorithm is proposed. This algorithm solves the problem of specifying the number of pixel blocks in the super-pixel block segmentation for the simple linear iterative algorithm(SLIC). By referring to the CV energy model, it is constructed by minimizing the image into multiple regions for horizontal set iterative segmentation.The adaptive super-pixel block is made such that each super-pixel block after the segmentation fits a single color block in the image. Then combined with the human body average template, the human body standard posture area of interest is marked on the picture, which improves the anti-interference ability of the algorithm against the complex background.Finally, each super-pixel block is clustered as a node by k-means clustering algorithm to realize standard human body image segmentation. The experiment is carried out by collecting multiple sets of pictures in different environments. The results show that the proposed algorithm improves the segmentation accuracy of the human body's standard posture and ensures strong anti-interference ability for complex backgrounds with rich chroma.
引文
1Wachinger C,Toews M,Langs G,et al.Keypoint transfer for fast whole-body segmentation.IEEE Transactions on Medical Imaging,2018,29(7):1-12.
2Aguilar WG,Luna MA,Moya JF,et al.Pedestrian detection for UAVs using cascade classifiers with meanshift.Proceedings of the 11th IEEE International Conference on Semantic Computing.San Diego,CA,USA,2017:509-514.
3Levinshtein A,Stere A,Kutulakos KN,et al.TurboPixels:Fast superpixels using geometric flows.IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(12):2290-2297.[doi:10.1109/TPAMI.2009.96]
4Wu HS,Wu YL,Zhang SL,et al.Cartoon image segmentation based on improved SLIC superpixels and adaptive region propagation merging.Proceedings of 2016 IEEE International Conference on Signal and Image Processing.Beijing,China,2016:277-281.
5Chan TF,Vese LA.Active contours without edges.IEEE Transactions on Image Processing,2001,10(2):266-277.[doi:10.1109/83.902291]
6Ngo TA,Carneiro G.Fully automated non-rigid segmentation with distance regularized level set evolution initialized and constrained by deep-structured inference.Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition.Columbus,OH,USA,2014:3118-3125.
7Kim G,Sim JY.Depth guided selection of adaptive region of interest for grabcut-based image segmentation.Proceedings of 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference.Jeju,South Korea,2016:1-4.
8Shelhamer E,Long J,Darrell T.Fully convolutional networks for semantic segmentation.IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):640-651.[doi:10.1109/TPAMI.2016.2572683]
9Jiang HZ,Learned-Miller E.Face detection with the faster RCNN.Proceedings of the 12th IEEE International Conference on Automatic Face&Gesture Recognition.Washington,DC,USA,2017:650-657.
10Li XM,Dou Q,Chen H,et al.3D multi-scale FCN with random modality voxel dropout learning for intervertebral disc localization and segmentation from multi-modality MR images.Medical Image Analysis,2018,45:41-54.[doi:10.1016/j.media.2018.01.004]
11Babenko B,Yang MH,Belongie S.Visual tracking with online multiple instance learning.Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition.Miami,FL,USA,2009:983-990.
12Dai JF,He KM,Sun J.BoxSup:Exploiting bounding boxes to supervise convolutional networks for semantic segmentation.Proceedings of 2015 IEEE International Conference on Computer Vision.Santiago,Chile,2015:1635-1643.
13张建伟,葛琦.基于局部统计信息的快速CV模型MR图像分割.中国图象图形学报,2010,15(1):69-74.
14朱欣娟,熊小亚.基于改进ASM模型的人体特征点定位和建模方法.系统仿真学报,2015,27(2):286-294.
15Nimisha,Gill R,Kaur I.Segmentation of retinal area by adaptive SLIC superpixel.Proceedings of the 1st International Conference on Power Electronics,Intelligent Control and Energy Systems.Delhi,India,2016:1-5.
16Wang B,Gao XB,Tao DC,et al.A nonlinear adaptive level set for image segmentation.IEEE Transactions on Cybernetics,2014,44(3):418-428.[doi:10.1109/TCYB.2013.2256891]
17赵鑫,汪维家,曾雅云,等.改进的模块PCA人脸识别新算法.计算机工程与应用,2015,51(2):161-164.[doi:10.3778/j.issn.1002-8331.1303-0095]
18Luo JJ,Jiao LC,Lozano JA.A sparse spectral clustering framework via multiobjective evolutionary algorithm.IEEETransactions on Evolutionary Computation,2016,20(3):418-433.[doi:10.1109/TEVC.2015.2476359]
2Aguilar WG,Luna MA,Moya JF,et al.Pedestrian detection for UAVs using cascade classifiers with meanshift.Proceedings of the 11th IEEE International Conference on Semantic Computing.San Diego,CA,USA,2017:509-514.
3Levinshtein A,Stere A,Kutulakos KN,et al.TurboPixels:Fast superpixels using geometric flows.IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(12):2290-2297.[doi:10.1109/TPAMI.2009.96]
4Wu HS,Wu YL,Zhang SL,et al.Cartoon image segmentation based on improved SLIC superpixels and adaptive region propagation merging.Proceedings of 2016 IEEE International Conference on Signal and Image Processing.Beijing,China,2016:277-281.
5Chan TF,Vese LA.Active contours without edges.IEEE Transactions on Image Processing,2001,10(2):266-277.[doi:10.1109/83.902291]
6Ngo TA,Carneiro G.Fully automated non-rigid segmentation with distance regularized level set evolution initialized and constrained by deep-structured inference.Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition.Columbus,OH,USA,2014:3118-3125.
7Kim G,Sim JY.Depth guided selection of adaptive region of interest for grabcut-based image segmentation.Proceedings of 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference.Jeju,South Korea,2016:1-4.
8Shelhamer E,Long J,Darrell T.Fully convolutional networks for semantic segmentation.IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):640-651.[doi:10.1109/TPAMI.2016.2572683]
9Jiang HZ,Learned-Miller E.Face detection with the faster RCNN.Proceedings of the 12th IEEE International Conference on Automatic Face&Gesture Recognition.Washington,DC,USA,2017:650-657.
10Li XM,Dou Q,Chen H,et al.3D multi-scale FCN with random modality voxel dropout learning for intervertebral disc localization and segmentation from multi-modality MR images.Medical Image Analysis,2018,45:41-54.[doi:10.1016/j.media.2018.01.004]
11Babenko B,Yang MH,Belongie S.Visual tracking with online multiple instance learning.Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition.Miami,FL,USA,2009:983-990.
12Dai JF,He KM,Sun J.BoxSup:Exploiting bounding boxes to supervise convolutional networks for semantic segmentation.Proceedings of 2015 IEEE International Conference on Computer Vision.Santiago,Chile,2015:1635-1643.
13张建伟,葛琦.基于局部统计信息的快速CV模型MR图像分割.中国图象图形学报,2010,15(1):69-74.
14朱欣娟,熊小亚.基于改进ASM模型的人体特征点定位和建模方法.系统仿真学报,2015,27(2):286-294.
15Nimisha,Gill R,Kaur I.Segmentation of retinal area by adaptive SLIC superpixel.Proceedings of the 1st International Conference on Power Electronics,Intelligent Control and Energy Systems.Delhi,India,2016:1-5.
16Wang B,Gao XB,Tao DC,et al.A nonlinear adaptive level set for image segmentation.IEEE Transactions on Cybernetics,2014,44(3):418-428.[doi:10.1109/TCYB.2013.2256891]
17赵鑫,汪维家,曾雅云,等.改进的模块PCA人脸识别新算法.计算机工程与应用,2015,51(2):161-164.[doi:10.3778/j.issn.1002-8331.1303-0095]
18Luo JJ,Jiao LC,Lozano JA.A sparse spectral clustering framework via multiobjective evolutionary algorithm.IEEETransactions on Evolutionary Computation,2016,20(3):418-433.[doi:10.1109/TEVC.2015.2476359]