Results 1 - 10 of 36

Discrete-Continuous Optimization for Multi-Target Tracking

by Anton Andriyenko, Konrad Schindler, Stefan Roth
"... The problem of multi-target tracking is comprised of two distinct, but tightly coupled challenges: (i) the naturally discrete problem of data association, i.e. assigning image observations to the appropriate target; (ii) the naturally continuous problem of trajectory estimation, i.e. recovering the ..."
Abstract - Cited by 39 (5 self) - Add to MetaCart
The problem of multi-target tracking is comprised of two distinct, but tightly coupled challenges: (i) the naturally discrete problem of data association, i.e. assigning image observations to the appropriate target; (ii) the naturally continuous problem of trajectory estimation, i.e. recovering the trajectories of all targets. To go beyond simple greedy solutions for data association, recent approaches often perform multi-target tracking using discrete optimization. This has the disadvantage that trajectories need to be pre-computed or represented discretely, thus limiting accuracy. In this paper we instead formulate multi-target tracking as a discretecontinuous optimization problem that handles each aspect in its natural domain and allows leveraging powerful methods for multi-model fitting. Data association is performed using discrete optimization with label costs, yielding near optimality. Trajectory estimation is posed as a continuous fitting problem with a simple closed-form solution, which is used in turn to update the label costs. We demonstrate the accuracy and robustness of our approach with state-of-theart performance on several standard datasets. 1.
(Show Context)

Efficient track linking methods for track graphs using network-flow and set-cover techniques

by Zheng Wu, Thomas H. Kunz, Margrit Betke - In CVPR , 2011
"... This paper proposes novel algorithms that use networkflow and set-cover techniques to perform occlusion reasoning for a large number of small, moving objects in single or multiple views. We designed a track-linking framework for reasoning about short-term and long-term occlusions. We introduce a two ..."
Abstract - Cited by 23 (4 self) - Add to MetaCart
This paper proposes novel algorithms that use networkflow and set-cover techniques to perform occlusion reasoning for a large number of small, moving objects in single or multiple views. We designed a track-linking framework for reasoning about short-term and long-term occlusions. We introduce a two-stage network-flow process to automatically construct a “track graph ” that describes the track merging and splitting events caused by occlusion. To explain short-term occlusions, when local information is sufficient to distinguish objects, the process links trajectory segments through a series of optimal bipartite-graph matches. To resolve long-term occlusions, when global information is needed to characterize objects, the linking process computes a logarithmic approximation solution to the set cover problem. If multiple views are available, our method builds a track graph, independently for each view, and then simultaneously links track segments from each graph, solving a joint set cover problem for which a logarithmic approximation also exists. Through experiments on different datasets, we show that our proposed linear and integer optimization techniques make the track graph a particularly useful tool for tracking large groups of individuals in images. 1.
(Show Context)

Tracking a Large Number of Objects from Multiple Views

by Zheng Wu, Nickolay I. Hristov, Tyson L. Hedrick, Thomas H. Kunz, Margrit Betke
"... We propose a multi-object multi-camera framework for tracking large numbers of tightly-spaced objects that rapidly move in three dimensions. We formulate the problem of finding correspondences across multiple views as a multidimensional assignment problem and use a greedy randomized adaptive search ..."
Abstract - Cited by 16 (7 self) - Add to MetaCart
We propose a multi-object multi-camera framework for tracking large numbers of tightly-spaced objects that rapidly move in three dimensions. We formulate the problem of finding correspondences across multiple views as a multidimensional assignment problem and use a greedy randomized adaptive search procedure to solve this NPhard problem efficiently. To account for occlusions, we relax the one-to-one constraint that one measurement corresponds to one object and iteratively solve the relaxed assignment problem. After correspondences are established, object trajectories are estimated by stereoscopic reconstruction using an epipolar-neighborhood search. We embedded our method into a tracker-to-tracker multi-view fusion system that not only obtains the three-dimensional trajectories of closely-moving objects but also accurately settles track uncertainties that could not be resolved from single views due to occlusion. We conducted experiments to validate our greedy assignment procedure and our technique to recover from occlusions. We successfully track hundreds of flying bats and provide an analysis of their group behavior based on 150 reconstructed 3D trajectories. 1.
(Show Context)

Multi-model hypothesis group tracking and group size estimation

by Boris Lau, Kai O. Arras, Wolfram Burgard - International Journal of Social Robotics , 2010
"... Abstract — People in densely populated environments typi-cally form groups that split and merge. In this paper we track groups of people so as to reflect this formation pro-cess and gain efficiency in situations where maintaining the state of individual people would be intractable. We pose the group ..."
Abstract - Cited by 15 (2 self) - Add to MetaCart
Abstract — People in densely populated environments typi-cally form groups that split and merge. In this paper we track groups of people so as to reflect this formation pro-cess and gain efficiency in situations where maintaining the state of individual people would be intractable. We pose the group tracking problem as a recursive multi-hypothesis model selection problem in which we hypothesize over both, the partitioning of tracks into groups (models) and the association of observations to tracks (assignments). Model hypotheses that include split, merge, and continuation events are first generated in a data-driven manner and then validated by means of the assignment probabilities conditioned on the respective model. Observations are found by clustering points from a laser range finder given a background model and associated to existing group tracks using the minimum average Hausdorff distance. We further propose a method to estimate the number of people in groups based on the number of human-sized clusters. Experiments with a stationary and a moving platform show that, in populated environments, tracking groups is clearly more efficient than tracking people separately. The results also show a high accuracy in the estimation of group sizes. Our system runs in real-time on a typical desktop computer. I.
(Show Context)

Recognizing linked events: Searching the space of feasible explanations

by Dima Damen, David Hogg - In CVPR , 2009
"... The ambiguity inherent in a localized analysis of events from video can be resolved by exploiting constraints between events and examining only feasible global explanations. We show how jointly recognizing and linking events can be formulated as labeling of a Bayesian network. The framework can be e ..."
Abstract - Cited by 9 (1 self) - Add to MetaCart
The ambiguity inherent in a localized analysis of events from video can be resolved by exploiting constraints between events and examining only feasible global explanations. We show how jointly recognizing and linking events can be formulated as labeling of a Bayesian network. The framework can be extended to multiple linking layers, expressing explanations as compositional hierarchies. The best global explanation is the Maximum a Posteriori (MAP) solution over a set of feasible explanations. The search space is sampled using Reversible Jump Markov Chain Monte Carlo (RJMCMC). We propose a set of general move types that is extensible to multiple layers of linkage, and use simulated annealing to find the MAP solution given all observations. We provide experimental results for a challenging two-layer linkage problem, demonstrating the ability to recognise and link drop and pick events of bicycles in a rack over five days. 1.
(Show Context)

3d tracking by catadioptric vision based on particle filters

by Matteo Taiana, José Gaspar, Jacinto Nascimento, Re Bernardino, Pedro Lima - RoboCup International Symposium , 2007
"... Abstract. This paper presents a robust tracking system for autonomous robots equipped with omnidirectional cameras. The proposed method uses a 3D shape and color-based object model. This allows to tackle difficulties that arise when the tracked object is placed above the ground plane floor. Tracking ..."
Abstract - Cited by 7 (2 self) - Add to MetaCart
Abstract. This paper presents a robust tracking system for autonomous robots equipped with omnidirectional cameras. The proposed method uses a 3D shape and color-based object model. This allows to tackle difficulties that arise when the tracked object is placed above the ground plane floor. Tracking under these conditions has two major difficulties: first, observation with omnidirectional sensors largely deforms the target’s shape; second, the object of interest embedded in a dynamic scenario may suffer from occlusion, overlap and ambiguities. To surmount these difficulties, we use a 3D particle filter to represent the target’s state space: position and velocity with respect to the robot. To compute the likelihood of each particle the following features are taken into account: i) image color; ii) mismatch between target’s color and background color. We test the accuracy of the algorithm in a RoboCup Middle Size League scenario, both with static and moving targets. 1
(Show Context)

Moving object detection with laser scanners,” JFR

by Christoph Mertz, Luis E. Navarro-serment, Robert Maclachlan, Paul Rybski, Aaron Steinfeld, Christopher Urmson, Nicolas V, Martial Hebert, Chuck Thorpe, David Duggins, Jay Gowdy , 2012
"... The detection and tracking of moving objects is an essential task in robotics. The CMU-RI Navlab group has developed such a system that uses a laser scanner as its primary sensor. We will describe our algorithm and its use in several applications. Our system worked successfully on indoor and outdoor ..."
Abstract - Cited by 7 (0 self) - Add to MetaCart
The detection and tracking of moving objects is an essential task in robotics. The CMU-RI Navlab group has developed such a system that uses a laser scanner as its primary sensor. We will describe our algorithm and its use in several applications. Our system worked successfully on indoor and outdoor platforms and with several different kinds and configurations of two-dimensional and three-dimensional laser scanners. The applications vary from collision warning systems, people classification, observing human tracks, and input to a dynamic planner. Several of these systems were evaluated in live field tests and shown to be robust and reliable. C ○ 2012 Wiley Periodicals, Inc. 1.
(Show Context)

Tracking groups of people with a multi-model hypothesis tracker

by Boris Lau, Kai O. Arras, Wolfram Burgard - In ICRA’09: Proceedings of the 2009 IEEE international conference on Robotics and Automation , 2009
"... Abstract — People in densely populated environments typically form groups that split and merge. In this paper we track groups of people so as to reflect this formation process and gain efficiency in situations where maintaining the state of individual people would be intractable. We pose the group t ..."
Abstract - Cited by 6 (2 self) - Add to MetaCart
Abstract — People in densely populated environments typically form groups that split and merge. In this paper we track groups of people so as to reflect this formation process and gain efficiency in situations where maintaining the state of individual people would be intractable. We pose the group tracking problem as a recursive multi-hypothesis model selection problem in which we hypothesize over both, the partitioning of tracks into groups (models) and the association of observations to tracks (assignments). Model hypotheses that include split, merge, and continuation events are first generated in a datadriven manner and then validated by means of the assignment probabilities conditioned on the respective model. Observations are found by clustering points from a laser range finder given a background model and associated to existing group tracks using the minimum average Hausdorff distance. Experiments with a stationary and a moving platform show that, in populated environments, tracking groups is clearly more efficient than tracking people separately. Our system runs in real-time on a typical desktop computer. I.
(Show Context)

Simultaneous clustering and tracking unknown number of objects

by Katsuhiko Ishiguro, Takeshi Yamada, Naonori Ueda - In Proc. IEEE CVPR , 2008
"... In this paper, we present a novel on-line probabilistic generative model that simultaneously deals with both the clustering and the tracking of an unknown number of moving objects. The proposed model assumes that i) time series data are composed of a time-varying number of objects and that ii) each ..."
Abstract - Cited by 3 (0 self) - Add to MetaCart
In this paper, we present a novel on-line probabilistic generative model that simultaneously deals with both the clustering and the tracking of an unknown number of moving objects. The proposed model assumes that i) time series data are composed of a time-varying number of objects and that ii) each object is governed by a mixture of an unknown number of different patterns of dynamics. The problem of learning patterns of dynamics is formulated as the clustering of tracked objects based on a nonparametric Bayesian model with conjugate priors, and this clustering in turn improves the tracking. We present a particle filter for posterior estimation of simultaneous clustering and tracking. Through experiments with synthetic and real movie data, we confirmed that the proposed model successfully learned the hidden cluster patterns and obtained better tracking results than conventional models without clustering. 1.
(Show Context)

Multi-camera realtime 3d tracking of multiple flying animals

by Andrew D. Straw, Kristin Branson, Titus R. Neumann, Michael H. Dickinson - In: Proc. IEEE Internat. Conf. Computer Vision and Pattern Recognition , 2010
"... Automated tracking of animal movement allows analyses that would not otherwise be possible by providing great quantities of data. The additional capability of tracking in realtime— with minimal latency—opens up the experimental possibility of manipulating sensory feedback, thus allowing detailed ex- ..."
Abstract - Cited by 3 (0 self) - Add to MetaCart
Automated tracking of animal movement allows analyses that would not otherwise be possible by providing great quantities of data. The additional capability of tracking in realtime— with minimal latency—opens up the experimental possibility of manipulating sensory feedback, thus allowing detailed ex-plorations of the neural basis for control of behavior. Here we describe a new system capable of tracking the position and body orientation of animals such as flies and birds. The sys-tem operates with less than 40 msec latency and can track multiple animals simultaneously. To achieve these results, a multi target tracking algorithm was developed based on the Extended Kalman Filter and the Nearest Neighbor Standard Filter data association algorithm. In one implementation, an eleven camera system is capable of tracking three flies simul-
(Show Context)