We describe a new semantic descriptor for robots to recognize visual places. The descriptor integrates image features and color information via the hull census transform (HCT) and image histogram indexing. Our approach extracts the semantic description based on the convex hull points and statistical calculation. The color histograms are then formed by four indices and added to the descriptor. The semantic codebook consists of several places with many image descriptors. Finally, a one-versus-one (OVO) multi-class support vector machine (SVM) is used to model the places. The proposed technique is achieved by using a high-level cue integration scheme based on the learning information over the color and feature space to optimally combine the weighted cues. It is suitable for visual place recognition, particularly for the images captured by an omnidirectional camera. The experimental results show that the codebook with less vectors is as robust as most popular codebooks under varying environments. The performance is evaluated and compared with several state-of-the-art descriptors.
AngeliAFilliatDDoncieuxSMeyerJ-A (2009) Visual topological slam and global localization. In International Conference on Robotics and Automation (ICRA), pp. 4300–4305.
2.
BaileyTNebotERosenblattJDurrant-WhyteH (1999) Robust distinctive place recognition for topological maps. In Proceedings of the International Conference on Field and Service Robotics, pp. 347–352.
3.
BayHTuytelaarsTGoolLV (2006) SURF: Speeded up robust features. In ECCV ’06: Proceedings of the 9th European Conference on Computer Vision-Part I, pp. 404–417.
4.
BooijOTerwijnBZivkovicZKroseB (2007) Navigation using an appearance based topological map. In International Conference on Robotics and Automation (ICRA), pp. 3927–3932.
CristianiniNShawe-TaylorJ (1999) An Introduction to Support Vector Machines: And Other Kernel-based Learning Methods. New York: Cambridge University Press.
7.
CumminsMNewmanP (2008) FAB-MAP: Probabilistic localization and mapping in the space of appearance. The International Journal of Robotics Research27: 647–665.
8.
EpsteinRHarrisAStanleyDKanwisherN (1999) The parahippocampal place area: recognition, navigation, or encoding?Neuron23: 115–125.
9.
FontanelliDSalarisPBeloFAWBicchA (2009) Visual appearance mapping for optimal vision based servoing. In Experimental Robotics: The 11th International Symposium, STAR 54. Berlin: Springer, pp. 353–362.
10.
HarrisCStephensM (1988) A combined corner and edge detector. Alvey Vision Conference15: 50.
11.
Javier TraverVBernardinoA (2009) A review of log-polar imaging for visual perception in robotics. In Robotics and Autonomous Systems.
12.
KeerthiSSundararajanSChangKHsiehCLinC (2008) A sequential dual method for large scale multi-class linear SVMs. In Proceeding of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 408–416.
13.
KoschanA (1997) Improving robot vision by color information. In Proceedings of the 7th International Conference on Artificial Intelligence and Information—Control Systems of Robots, pp. 247–258.
14.
LazebnikSSchmidCPonceJ (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2.
15.
LeeS-WKimY-MChoiSW (2000) Fast scene change detection using direct feature extraction from mpeg compressed videos. IEEE Transactions on Multimedia2: 240–254.
16.
LehmannERomanoJP (2005) Testing Statistical Hypotheses (3rd edn). New York, USA: Springer.
17.
LinHYWangML (2009) Generalized stereo for hybrid omnidirectional and perspective imaging. In Proceedings of the Workshop on Omnidirectional Vision, Camera Networks and Non-Classical Cameras (OMNIVIS 2009, in conjunction with ICCV 2009).
18.
LiuCShumH (2003) Kullback–Leibler boosting. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1.
19.
LiuMScaramuzzaDPradalierCSiegwartRChenQ (2009) Scene recognition with omnidirectional vision for topological map using lightweight adaptive descriptors. In Proceedings of the 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 116–121.
20.
LoweD (2001) Local feature view clustering for 3d object recognition. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1, pp. 682–688.
21.
Martínez MozosOStachnissCBurgardW (2005) Supervised learning of places from range data using adaboost. In Proceedings of the International Conference on Robotics and Automation (ICRA), pp. 1742–1747.
22.
NayarSK (1997a) Catadioptric omnidirectional camera. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 482–488.
23.
NayarSK (1997b) Omnidirectional video camera. In Proceedings of the DARPA Image Understanding Workshop, Vol. 1, pp. 235–242.
24.
NowakEJurieFTriggsB (2006) Sampling strategies for bag-of-features image classification. In Computer Vision—ECCV 2006, pp. 490–503.
25.
PatwardhanKSapiroGMorellasV (2008) Robust foreground detection in video using pixel layers. IEEE Transactions on Pattern Analysis and Machine Intelligence30: 746–751.
26.
PradeepVMedioniGWeilandJ (2009) Visual loop closing using multi-resolution SIFT grids in metric-topological SLAM. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1438–1445.
27.
PronobisACaputoB (2007) Confidence-based cue integration for visual place recognition. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), San Diego, CA.
28.
PronobisACaputoB (2009) COLD: COsy Localization Database. The International Journal of Robotics Research (IJRR)28: 588–594.
29.
PronobisACaputoBJensfeltPChristensenH (2006) A discriminative approach to robust visual place recognition. In IEEE/RSJ International Conference on Intelligent Robots and Systems.
30.
PronobisACaputoBJensfeltPChristensenH (2010a). A realistic benchmark for visual indoor place recognition. Robotics and Autonomous Systems58: 81–96.
31.
PronobisAMozosOCaputoB (2008) Svm-based discriminative accumulation scheme for place recognition. In Proceedings of the International Conference on Robotics and Automation (ICRA).
32.
PronobisAMozosOMCaputoBJensfeltP (2010b) Multi-modal semantic place classification. The International Journal of Robotics Research29: 298–320.
33.
QiuG (2002) Indexing chromatic and achromatic patterns for content-based colour image retrieval. Pattern Recognition35: 1675–1686.
34.
Ruiz-HernandezJACrowleyJLMelerALuxA (2009) Face recognition using tensors of census transform histograms from Gaussian features maps. In The British Machine Vision Conference.
35.
RyabkoBAstolaJ (2006) Universal codes as a basis for nonparametric testing of serial independence for time series. Journal of Statistical Planning and Inference136: 4119–4128.
36.
Silpa-AnanCHartleyR (2005) Visual localization and loop-back detection with a high resolution omnidirectional camera. In Workshop on Omnidirectional Vision.
37.
SwainMBallardD (1991) Color indexing. International Journal of Computer Vision7: 11–32.
38.
TagareHMcDermottDXiaoH (1998) Visual place recognition for autonomous robots. In International Conference on Robotics and Automation (ICRA).
39.
TominagaSFukudaTKimachiA. (2008). A high-resolution imaging system for omnidirectional illuminant estimation. Journal of Imaging Science and Technology52: 040907.
40.
TorralbaAMurphyKFreemanWRubinM (2003) Context-based vision system for place and object recognition. In Proceedings of the IEEE International Conference on Computer Vision.
41.
UllahMPronobisACaputoBLuoJJensfeltPChristensenH (2008) Towards robust place recognition for robot localization. In Proceedings of IEEE International Conference Robotics and Automation, pp. 530–537.
42.
UlrichINourbakhshI (2000) Appearance-based place recognition for topological localization. In IEEE International Conference on Robotics and Automation, Vol. 2, pp. 1023–1029.
43.
UrhanOGulluKErturkS (2007). Shot-cut detection for B&W archive films using best-fitting kernel. The International Journal of Electronics and Communications61: 463–468.
44.
UrhanOGulluMKErturkS (2006) Modified phase-correlation based robust hard-cut detection with application to archive film. IEEE Transactions on Circuits and Systems for Video Technology16: 753–770.
45.
ValgrenCLilienthalA (2008) Incremental spectral clus- tering and seasons: appearance-based localization in outdoor environments. In IEEE International Conference on Robotics and Automation, pp. 1856–1861.
46.
WangLCaiZ (2006) Place recognition based on saliency for topological localization. Journal of Central South University of Technology13: 536–541.
47.
WangMLLinHY (2009) Object recognition from omnidirectional visual sensing for mobile robot applications. In IEEE International Conference on Systems, Man, and Cybernetics (SMC 2009), pp. 1941–1946.
48.
WangM-LLinH-Y (2010) A hull census transform for scene change detection and recognition towards topological map building. In Proceedings of the 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Taipei, Taiwan.
49.
WrightWNimeroffI (1969) The rays are not coloured: essays on the science of vision and colour. Physics Today22: 85.
50.
WuJChristensenHIRehgJM (2009) Visual place categorization: problem, dataset, and algorithm. In Proceedings of IROS2009, pp. 4763–4770.
51.
YagiY (2004) Omnidirectional sensing and its applications. In Image Processing Technologies: Algorithms, Sensors, and Applications, p. 116.
52.
YimB-DLeeY-JSongJ-BChungW (2007) Mobile robot localization using fusion of object recognition and range information. In Proceedings of the IEEE International Conference Robotics and Automation, pp. 3533–3538.
53.
ZabihRWoodfillJ (1994) Non-parametric local transforms for computing visual correspondence. In Proceedings of European Conference on Computer Vision, pp. 151–158.
