The tough challenges of object recognition in long-distance scene involves contour shape deformation invariant features construction. In this work, an effective contour shape descriptor integrating critical points structure and Scale-invariant Heat Kernel Signature (SI-HKS) is proposed for long-distance object recognition. We firstly propose a general feature fusion model. Then, we capture the object contour structure feature with Critical-points Inner-distance Shape Context (CP-IDSC). Meanwhile, we pull-in the SI-HKS for capturing the local deformation-invariant properties of 2D shape. Based on the integration of the above two feature descriptors, the fusion descriptor is compacted by mapping into a low dimensional subspace using the bags-of-features, allowing for an efficient Bayesian classifier recognition. The extensive experiments on synthetic turbulence-degraded shapes and real-life infrared image show that the proposed method outperformed other compared approaches in terms of the recognition precision and robustness.
XuX., YangP., LiuY., XianH. and XuB., Geometric distortion correction of long-range imaging containing moving objects, Journal of Optics21(10) (2018).
2.
LoweD., Distinctive image features from scale-invariant keypoints, International Journal of Computer Vision60 (2004), 91–110.
3.
ShenW., WangY., BaiX., WangH. and LateckiL.J., Shape clustering: common structure discovery, Pattern Recognition46(2) (2013), 539–550.
4.
RyuJ.B., LeeC.G. and ParkH.H., Formula for harris corner detector, Electronics Letters47(3) (2011), 180.
5.
TanH.L., GelfandS.B. and DelpE.J., A cost minimization approach to edge detection using simulated annealing, IEEE Transactions on Pattern Analysis & Machine Intelligence33(1) (1992), 3–18.
6.
BaiX. and LateckiL.J., Path similarity skeleton graph matching, IEEE Transactions on Pattern Analysis & Machine Intelligence30(7) (2008), 1282–1292.
7.
XieJ., HengP.A. and ShahM., Shape matching and modeling using skeletal context, Pattern Recognition41(5) (2008), 1756–1767.
8.
BelongieS., MalikJ. and PuzichaJ., Shape matching and object recognition using shape contexts, IEEE Transactions on Pattern Analysis and Machine Intelligence24 (2002), 509–522.
9.
SinghL.B. and HazarikaS.M., Enhanced Shape Context for Object Recognition. International Conference on Advanced Computing & Communications. IEEE (2008).
10.
LiM., ChenS. and ChenX., Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition [J]. 2019, DOI: 10.1109/ICME.2019.00078
11.
LiW., LiH., WuQ., ChenX. and NganK.N., Simultaneously detecting and counting dense vehicles from drone images, IEEE Transactions on Industrial Electronics66(12) (2019), 9651–9662.
12.
ChenS., ZhaoX., SunZ., et al., Shape Recognition with Recurrent Neural Network[M]// Artificial Intelligence and Security. 2019.
13.
MurugesanB., SarveswaranK., ShankaranarayanaS.M., RamK. and SivaprakasamM., Joint shape learning and segmentation for medical images using a minimalistic deep network (2019). https://arxiv.org/abs/1901.08824
14.
ThayananthanA., StengerB., TorrP.H.S. and CipollaR., Shape Context and Chamfer Matching in Cluttered Scenes, IEEE Conf on Computer Vision and Pattern RecognitionI (2003), 127–133.
15.
LingH. and JacobsD.W., Shape classification using the inner-distance, IEEE Transactions on Pattern Analysis & Machine Intelligence29(2) (2007), 286–299.
16.
WangX., FengB., BaiX., LiuW. and Jan LateckiL., Bag of contour fragments for robust shape classification, Pattern Recognition47(6) (2014), 2116–2125.
17.
ShenW., JiangY., GaoW., ZengD. and WangX., Shape recognition by bag of skeleton-associated contour parts, Pattern Recognition Letters83(P3) (2016), 321–329.
18.
AftabW., HostettlerR., FreitasA.D., ArvanehM. and MihaylovaL., Spatio-temporal gaussian process models for extended and group object tracking with irregular shapes, IEEE Transactions on Vehicular Technology68(3) (2019), 2137–2151.
19.
PriyankaS. and SudhakarM.S., Tetrakis square tiling-based triangulated feature descriptor aiding shape retrieval[J], Digital Signal Processing79 (2018), 125–135.
20.
GarcíaordásM.T., AlegregutiérrezE., GonzálezcastroV. and AlaizrodríguezR., Combining shape and contour features to improve tool wear monitoring in milling processes, International Journal of Production Research5 (2018), 1–13.
21.
BaiS., ZhouZ., WangJ., BaiX., LateckiL.J. and TianQ., Automatic ensemble diffusion for 3d shape and image retrieval, IEEE Transactions on Image Processing (2018), 1.
22.
YuL., XiaX., ZhouK. and ZhaoL., Affine invariant fusion feature extraction based on geometry descriptor and bit for object recognition, IET Image Processing13(1) (2019), 57–72.
23.
NieY., CaoX., LiP., ZhangQ., ZhangZ., LiG., et al., Interactive contour extraction via sketch-alike dense-validation optimization, IEEE Transactions on Circuits and Systems for Video Technology (99) (2019), 1.
24.
SunK.B. and SuperB.J., Classification of Contour Shapes Using Class Segment Sets, IEEE Computer Society Conference on Computer Vision & Pattern Recognition IEEE Computer Society (2005).
25.
YangX., YangX., ZengL. and LiuW., Shape classification using contour critical point sets, Journal of Nanjing University46(1) (2010), 47–55.
26.
SharvitD., ChanJ., TekH. and KimiaB.B., Symmetry-based indexing of image databases, Journal of Visual Communication and Image Representation9(4) (1998), 366–380.
27.
SebastianT.B., KleinP.N. and KimiaB.B., Recognition of Shapes by Editing Their Shock Graphs. IEEE Computer Society. (2004).
28.
ThomazC.E. and GiraldiG.A., A new ranking method for principal components analysis and its application to face image analysis, Image and Vision Computing28(6) (2010), 902–913.
29.
XuX., YangP., XianH. and LiuY., Robust moving objects detection in long-distance imaging through turbulent medium, (doi: 10.1088/2040-8986/aaf191), Infrared Physics & Technology. (2019).
Simo-SerraE., TorrasC. and Moreno-NoguerF., Dali: deformation and light invariant descriptor, International Journal of Computer Vision115(2) (2015), 136–154.
32.
BronsteinA.M., LitmanR., BronsteinM.M. and KokkinosI., Intrinsic shape context descriptors for deformable shapes. 2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society. (2012).
33.
BronsteinM.M. and KokkinosI., Scale-Invariant Heat Kernel Signatures for Non-Rigid Shape Recognition, The Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2010, San Francisco, CA, USA, (2010), 13–18 June 2010. IEEE.
34.
LeordeanuM. and HebertM., A spectral technique for correspondence problems using pairwise constraints, In International Conference on Computer Vision (2005), pp. 1482–1489.
35.
SunJ., OvsjanikovM. and GuibasL., A concise and provably informative multi-scale signature based on heat diffusion. In Eurographics Symposium on Geometry Processing, (2009), pp. 1383–1392.
36.
LingH. and JacobsD., Deformation invariant image matching. In International Conference on Computer Vision, (2005), pp. 1466–1473.
37.
GębalK., BærentzenJ.A., AanæsH. and LarsenR., Shape analysis using the auto diffusion function. In Proceedings of the Symposium on Geometry Processing, (2009), pp. 1405–1413.
38.
RustamovR., Laplace-beltrami eigenfunctions for deformation invariant shape representation. In Eurographics Symposium on Geometry Processing, (2007), pp. 225–233.
39.
BaiX., LiuW. and TuZ., Integrating Contour and Skeleton for Shape Classification, IEEE International Conference on Computer Vision Workshops IEEE, 2010.
40.
Fei-FeiL., FergusR. and PeronaR., Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories, CVIU106(1) (2007), 59–70.
41.
FelzenszwalbP. and SchwartzJ., Hierarchical matching of deformable shapes. In CVPR, Minneapolis, June 2007.
NealenA., FiberMesh : designing freeform surfaces with 3D curves. ACM Trans. on Graphics 26 (2007).
45.
FengL., et al. An Interactive 2D-to-3D Cartoon Modeling System. International Conference on Technologies for E-learning & Digital Entertainment Springer, Cham, 2016.
46.
FengL., YangX. and XiaoS., MagicToon: A 2D-to-3D creative cartoon modeling system with mobile AR. 2017 IEEE Virtual Reality (VR) IEEE Computer Society, 2017.
47.
OvsjanikovM., BronsteinA.M., BronsteinM.M. and GuibasL.J., Shape Google: A computer vision approach to isometry invariant shape retrieval. Computer Vision Workshops (ICCV Workshops), 2009 IEEE 12th International Conference on. IEEE (2009).
48.
GaoZ., LiY., SunY., YangJ., XiongH., ZhangH., et al., Motion tracking of the carotid artery wall from ultrasound image sequences: a nonlinear state-space approach, IEEE Transactions on Medical Imaging37(1) (2018), 273–283.
49.
GaoZ., LiuZ., et al., Learning the implicit strain reconstruction in ultrasound elastography using privileged information, Medical Image Analysis, 2019, DOI: 10.1016/j.media.2019.101534
50.
SakoeH. and ChibaS., Dynamic programming algorithm optimization for spoken word recognition, IEEE Transactions on Acoustics, Speech, and Signal Processing26(1) (2003), 43–49.
51.
XinghuaL., NianH., HuanfengS., YunjieF. and LiangpeiZ., A robust mosaicking procedure for high spatial resolution remote sensing images, ISPRS Journal of Photogrammetry and Remote Sensing109 (2015), 108–125.
52.
FengR., DuQ., LiX. and ShenH., Robust registration for remote sensing images by combining and localizing feature- and area-based methods, ISPRS Journal of Photogrammetry and Remote Sensing151 (2019), 15–26.
53.
LiX., ShenH., LiH. and ZhangL., Patch matching-based multitemporal group sparse representation for the missing information reconstruction of remote-sensing images, IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing9(8) (2016), 3629–3641.
54.
MaK., LiH., YongH., WangZ., MengD. and ZhangL., Robust multi-exposure image fusion: a structural patch decomposition approach, IEEE Transactions on Image Processing26(5) (2017), 2519–2532.
