Natural Landmark Detection of Mobile Robots Based on Bayesian Surprise of Salient Scenes
QIAN Kun,MA Xu-Dong,DAI Xian-Zhong,FANG Fang,YANG Hong
Key Laboratory of Measurement and Control of Complex Systems of Engineering of Ministry of Education,School of Automation,Southeast University,Nanjing 210096
Abstract:Nature landmark detection of mobile robot in unknown and unstructured environment is a basis of hierarchical environmental mapping. A natural landmark detection method is proposed based on Bayesian Surprise of salient scenes. Visual attention map of scene images is computed to guide the SURF feature sampling within the scope of salient regions. The improved spatial bag-of-words model (sBoW) is employed to construct the pattern vectors of scene appearance. Multivariate Polya model based on the spatial bag-of-words paradigm is proposed for representing the place,and the detection of landmarks corresponding to salient scenes is achieved by computing the surprise of sensor measurements. The experimental results validate the low miss alarm rate and false alarm rate of the nature landmark detection method in large-scale and complex environment,as well as the effectiveness of generating topological nodes with the combination of hierarchical SLAM method.
[1] Hwang S Y,Song J B. Monocular Vision-Based SLAM in Indoor Environment Using Corner,Lamp,and Door Features from Upward-Looking Camera. IEEE Trans on Industrial Electronics,2011,58(10): 4804-4812 [2] Chai Xiaojie,Wen Feng,Yuan Kui. Fast Vision-Based Object Segmentation for Natural Landmark Detection on Indoor Mobile Robot // Proc of the International Conference on Mechatronics and Automation. Beijing,China,2011: 2232-2237 [3] Hayet J B,Lerasle F,Devy M. A Visual Landmark Framework for Mobile Robot Navigation. Image and Vision Computing,2007,25(8): 1341-1351 [4] Choset H,Nagatani K. Topological Simultaneous Localization and Mapping (SLAM): Toward Exact Localization without Explicit Localization. IEEE Trans on Robotics and Automation,2001,17(2): 125-137 [5] Núez P,Vázquez-Martín R,del Toro J C,et al. Natural Landmark Extraction for Mobile Robot Navigation Based on an Adaptive Curvature Estimation. Robotics and Autonomous Systems,2008,56(3): 247-264 [6] Beeson P,Jong N K,Kuipers B. Towards Autonomous Topological Place Detection Using the Extended Voronoi Graph // Proc of the IEEE International Conference on Robotics and Automation. Barcelona,Spain,2005: 4373-4379 [7] Ranganathan A,Dellaert F. Bayesian Surprise and Landmark Detection // Proc of the IEEE International Conference on Robotics and Automation. Kobe,Japan,2009: 2017-2023 [8] Itti L,Baldi P. A Principled Approach to Detecting Surprising Events in Video // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego,USA,2005,I: 631-637 [9] Wang Lu,Cai Zixing. Visual Saliency Based Natural Landmarks Detection under Unknown Environments. Pattern Recognition and Artificial Intelligence. 2006,19(1): 100-105 (in Chinese) (王 璐,蔡自兴.未知环境中基于视觉显著性的自然路标检测.模式识别与人工智能,2006,19(1): 100-105) [10] Alvarez S,Vanrell M. Texton Theory Revisited: A Bag-of-Words Approach to Combine Textons. Pattern Recognition,2012,45(12): 4312-4325 [11] Siagian C,Itti L. Rapid Biologically-Inspired Scene Classification Using Features Shared with Visual Attention. IEEE Trans on Pattern Analysis and Machine Intelligence,2007,29(2): 300-312 [12] Frintrop S. VOCUS: A Visual Attention System for Object Detection and Goal-Directed Search. Ph.D Dissertation. Bonn,Germany: Rheinische Friedrich-Wilhelms-Universitt Bonn,2006 [13] Minka T P. Estimating a Dirichlet Distribution[EB/OL].[2012-07-30]. Research.microsoft.com/en-us/um/people/minka/papers/dinchlet/minka-dirichlet.pdf [14] Elkan C. Clustering Documents with an Exponential-Family Approximation of the Dirichlet Compound Multinomial Distribution // Proc of the 23rd International Conference on Machine Learning. Pittsburgh,USA,2006: 289-296 [15] Qian Kun,Ma Xudong,Dai Xianzhong,et al. A Layered SLAM Based Approach for Unknown Environment Hierarchical Mapping Building. Robot,2011,33(6): 736-741 (in Chinese) (钱 堃,马旭东,戴先中,等.基于层次化SLAM的未知环境级联地图模型创建方法.机器人,2011,33(6): 736-741)