Filters








79,169 Hits in 3.5 sec

Understanding Trajectory Behavior: A Motion Pattern Approach [article]

Mahdi M. Kalayeh, Stephen Mussmann, Alla Petrakova, Niels da Vitoria Lobo, Mubarak Shah
2015 arXiv   pre-print
Mining the underlying patterns in gigantic and complex data is of great importance to data analysts. In this paper, we propose a motion pattern approach to mine frequent behaviors in trajectory data.  ...  Motion patterns, defined by a set of highly similar flow vector groups in a spatial locality, have been shown to be very effective in extracting dominant motion behaviors in video sequences.  ...  And finally, we intuitively introduce our motion pattern approach as a general tool for understanding trajectory behaviors.  ... 
arXiv:1501.00614v1 fatcat:zm2a7ow5y5b7bfe424k7cwzkg4

A Bayesian nonparametric approach to modeling motion patterns

Joshua Joseph, Finale Doshi-Velez, Albert S. Huang, Nicholas Roy
2011 Autonomous Robots  
The GP provides a flexible representation for each individual motion pattern, while the DP assigns observed trajectories to particular motion patterns.  ...  We propose modeling target motion patterns as a mixture of Gaussian processes (GP) with a Dirichlet process (DP) prior over mixture weights.  ...  Using a data-driven approach also side-steps the need to understand the target's motivations, which may appear irrational to an outside observer.  ... 
doi:10.1007/s10514-011-9248-x fatcat:2oylc5gm6vei3m2tu6o3hpylii

A Hierarchical Self-Organizing Approach for Learning the Patterns of Motion Trajectories

W. Hu, D. Xie, T. Tan
2004 IEEE Transactions on Neural Networks  
Trajectory analysis is one of the basic problems in behavior understanding, and the learning of trajectory patterns that can be used to detect anomalies and predict object trajectories is an interesting  ...  The understanding and description of object behav iors is a hot topic in computer vision.  ...  A Hierarchical Self-Organizing Approach for Learning the Patterns of Motion Trajectories Weiming Hu, Dan Xie, and Tieniu Tan, Senior Member, IEEE Abstract-The understanding and description of object behav  ... 
doi:10.1109/tnn.2003.820668 pmid:15387254 fatcat:qhb2ictlonalrgudz7o4nibmsy

A Novel Geometric Framework on Gram Matrix Trajectories for Human Behavior Understanding [article]

Anis Kacem, Mohamed Daoudi, Boulbaba Ben Amor, Stefano Berretti, and Juan Carlos Alvarez-Paiva
2018 arXiv   pre-print
) a temporal warping is performed on the trajectories, providing a geometry-aware (dis-)similarity measure between them; (3) finally, a pairwise proximity function SVM is used to classify them, incorporating  ...  Specifically, our approach involves three steps: (1) landmarks are first mapped into the Riemannian manifold of positive semidefinite matrices of fixed-rank to build time-parameterized trajectories; (2  ...  CONCLUSION In this paper, we have proposed a geometric approach for effectively modeling and classifying dynamic 2D and 3D landmark sequences for human behavior understanding.  ... 
arXiv:1807.00676v1 fatcat:7oxtoddyxveufd6c4vaeeqs6xm

Diverse and Admissible Trajectory Forecasting through Multimodal Context Understanding [article]

Seong Hyeon Park, Gyubok Lee, Manoj Bhat, Jimin Seo, Minseok Kang, Jonathan Francis, Ashwin R. Jadhav, Paul Pu Liang, Louis-Philippe Morency
2020 arXiv   pre-print
Multi-agent trajectory forecasting in autonomous driving requires an agent to accurately anticipate the behaviors of the surrounding vehicles and pedestrians, for safe and reliable decision-making.  ...  Due to partial observability in these dynamical scenes, directly obtaining the posterior distribution over future agent trajectories remains a challenging problem.  ...  as social, temporal motion behavior data.  ... 
arXiv:2003.03212v4 fatcat:e46fxq64izcqpe2pqpo3izxnw4

Understanding Sport Activities from Correspondences of Clustered Trajectories

Francesco Turchini, Lorenzo Seidenari, Alberto Del Bimbo
2015 2015 IEEE International Conference on Computer Vision Workshop (ICCVW)  
In this work we overcome this limitations and propose an approach that exploits the spatio-temporal structure of a video grouping local spatio-temporal features unsupervisedly.  ...  Our robust representation allows to measure video similarity making correspondences among arbitrary patterns.  ...  Single player activities are recognized using a boosting based approach and static and motion local features.  ... 
doi:10.1109/iccvw.2015.103 dblp:conf/iccvw/TurchiniSB15 fatcat:ainhxfzdubgpbbjywv2gvassym

Understanding interference experiments with polarized light through photon trajectories

A.S. Sanz, M. Davidović, M. Božić, S. Miret-Artés
2010 Annals of Physics  
Bohmian mechanics allows to visualize and understand the quantum-mechanical behavior of massive particles in terms of trajectories.  ...  This leads to a trajectory-based picture of the Arago-Fresnel laws for the interference of polarized light.  ...  ASS also thanks the Consejo Superior de Investigaciones Científicas (Spain) for a JAE-Doc Contract.  ... 
doi:10.1016/j.aop.2009.12.005 fatcat:hovbmnfbknc6dime6oznr7dete

Understanding intra-urban trip patterns from taxi trajectory data

Yu Liu, Chaogui Kang, Song Gao, Yu Xiao, Yuan Tian
2012 Journal of Geographical Systems  
The globally spatiotemporal patterns of trips exhibit a significant daily regularity.  ...  The observed patterns are attributed to the geographical heterogeneity of the study area, which makes the spatial distribution of trajectory stops to be non-uniform.  ...  Recently, GPSenabled floating cars 2 have provided an alternative approach to gathering large volumes of individual trajectories and studying individuals' behaviors and urban dynamics (Jiang et al. 2009  ... 
doi:10.1007/s10109-012-0166-z fatcat:gr5icfinsrawrhhpj64wyi3k2m

Trajectory-based Scene Understanding using Dirichlet Process Mixture Model [article]

Santhosh Kelathodi Kumaran, Debi Prosad Dogra, Partha Pratim Roy and Bidyut Baran Chaudhuri
2019 arXiv   pre-print
Appropriate modeling of a surveillance scene is essential for detection of anomalies in road traffic.  ...  If usual traffic paths are learned in a nonparametric way, manual interventions in road marking road can be avoided.  ...  Learning the normal trajectory patterns is the key to understand the traffic behavior at roadways.  ... 
arXiv:1803.06613v3 fatcat:d3euqqfcyraxtfbbdtpvgn4rqi

Learning Social Etiquette: Human Trajectory Understanding In Crowded Scenes [chapter]

Alexandre Robicquet, Amir Sadeghian, Alexandre Alahi, Silvio Savarese
2016 Lecture Notes in Computer Science  
In this paper, we argue that in order to enable the design of new target tracking or trajectory forecasting methods that can take full advantage of these rules, we need to have access to better data in  ...  real world outdoor environment such as a university campus.  ...  Our forecasting model is able to infer these navigation patterns hence better predict the trajectories of pedestrians.  ... 
doi:10.1007/978-3-319-46484-8_33 fatcat:hyo5krb36rcedbugd37gbf7vyy

Detecting anomalies in people's trajectories using spectral graph analysis

Simone Calderara, Uri Heinemann, Andrea Prati, Rita Cucchiara, Naftali Tishby
2011 Computer Vision and Image Understanding  
By representing the trajectories as sequences of transitions between nodes in a graph, shared individual trajectories capture only a small subspace of the possible trajectories on the graph.  ...  While video provides ample information for human inspectors, there is a great need for robust automated techniques that can efficiently detect anomalous behavior in streaming video from single or multiple  ...  We adopted a different approach, looking at the scene as a whole, i.e. accumulating the trajectories to create perception of the normal behavior in the scene.  ... 
doi:10.1016/j.cviu.2011.03.003 fatcat:vay7tyn7gzhcdlm6nvosrffgwq

Trajectory Learning for Activity Understanding: Unsupervised, Multilevel, and Long-Term Adaptive Approach

B. T. Morris, M. M. Trivedi
2011 IEEE Transactions on Pattern Analysis and Machine Intelligence  
This paper presents a framework for live video analysis in which the behaviors of surveillance subjects are described using a vocabulary learned from recurrent motion patterns, for real-time characterization  ...  The repetitive nature of object trajectories is utilized to automatically build activity models in a 3-stage hierarchical learning process.  ...  The trajectory database is clustered to find similar motion patterns without specifying those of interest.  ... 
doi:10.1109/tpami.2011.64 pmid:21422488 fatcat:zqs2aqb63jcefnghnx2jmzgpqm

Movement Matters! Understanding the Developmental Trajectory of Embodied Planning

Lisa Musculus, Azzurra Ruggeri, Markus Raab
2021 Frontiers in Psychology  
Thus, we argue that to fully understand and explain developmental changes, it is necessary to consider the interaction of motor and cognitive skills.  ...  ," implying that motor development is a crucial driving force of cognitive development, much more impactful than previously acknowledged.  ...  EMBODIED PLANNING: INTEGRATING THEORETICAL AND METHODOLOGICAL APPROACHES Motor Planning Motor planning is defined as the ability to organize motor behavior to accomplish an anticipated goal-directed  ... 
doi:10.3389/fpsyg.2021.633100 pmid:33995187 pmcid:PMC8113400 fatcat:7w3gj6qvibg5bhlpnhu3qladdy

A Hierarchical Pose-Based Approach to Complex Action Understanding Using Dictionaries of Actionlets and Motion Poselets

Ivan Lillo, Juan Carlos Niebles, Alvaro Soto
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
In this paper, we introduce a new hierarchical model for human action recognition using body joint locations.  ...  properties: (i) it can be trained with no spatial supervision, as it can automatically discover active body parts from temporal action annotations only; (ii) it jointly learns flexible representations for motion  ...  I.L. is supported by a PhD studentship from CONICYT.  ... 
doi:10.1109/cvpr.2016.218 dblp:conf/cvpr/LilloNS16 fatcat:lffts7ptevbulkolgp56m3mkh4

Understanding the geometry of transport: Diffusion maps for Lagrangian trajectory data unravel coherent sets

Ralf Banisch, Péter Koltai
2017 Chaos  
In this article, we provide a method for extracting coherent sets from possibly sparse Lagrangian trajectory data.  ...  The only a priori knowledge about the dynamics that we require is a locally valid notion of distance, which renders our method highly suitable for automated data analysis.  ...  process (Brownian motion).  ... 
doi:10.1063/1.4971788 pmid:28364763 fatcat:bdo36xvwyfbpfdyadm3vxyncqe
« Previous Showing results 1 — 15 out of 79,169 results