Improving Data Association by Joint Modeling of Pedestrian Trajectories and Groupings

By Stefano Pellegrini, Andreas Ess, Luc Van Gool. European Conference on Computer Vision, 2010

430 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/81b337f2006cd6c8d5fd148a56cab3e5a662d40d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Tracking the Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies (2017, background): “In these models, each object reacts to energy potentials caused by the interactions with other agents through forces (repulsion or attraction), while trying to keep a desired speed and motion direction [55, 3, 51, 71, 9, 58, 52].”
Part-based multiple-person tracking with partial occlusion handling (2012, methodology): “In table 1, we compare results with [3, 23, 15, 22, 14] using the results reported in [14].”
From Goals, Waypoints & Paths To Long Term Human Trajectory Forecasting (2020, methodology): “To project the data from meter into pixel space we use the provided homography matrices from the original dataset for the ETH [30] scenes ETH and HOTEL and create our own homography matrices for the UCY[23] scenes UNIV, ZARA1 and ZARA2.”
Peeking Into the Future: Predicting Future Person Activities and Locations in Videos (2019, methodology): “ETH [23] and UCY [16] are common datasets for person trajectory prediction benchmark [1, 7, 21, 26].”
Globally-optimal greedy algorithms for tracking a variable number of objects (2011, methodology): “Our contribution is grounded in a novel analysis of an integer linear program (ILP) formulation of multi-object tracking [14, 25, 3, 17, 2, 18].”
Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks (2018, methodology): “Over the past decades, this method has been often revisited [5, 6, 25, 26, 30, 31, 36, 46].”
GMCP-Tracker: Global Multi-object Tracking Using Generalized Minimum Clique Graphs (2012, methodology): “The authors of [7,8,9] use a similar approach; however the motion models are improved by incorporating social interaction using a social force model.”
Who are you with and where are you going? (2011, background): “A tracking application is included in [9].”
Social LSTM: Human Trajectory Prediction in Crowded Spaces (2016, methodology): “Neither, can it be predicted with simple ”repulsion” or ”attraction” functions (the traditional social forces models [24, 43, 73, 50]) This motivates us to build a model which can account for the behavior of other people within a large neighborhood, while predicting a person’s path.”
Video-Based Human Behavior Understanding: A Survey (2013, background): “The social interaction model proposed in [155] and [161] assumes that people behave consistently when walking in groups.”
Learning Social Etiquette: Human Trajectory Understanding In Crowded Scenes (2016, methodology): “For instance, two leading families of methods for target trajectory forecasting (Social Forces [14,15,1,2] and Gaussian Processes [16,17,12]) have shown promising results on existing datasets [18,11]; however, they have never been tested at scale and in real-world scenarios where multiple classes of”
Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion (2022, methodology): “Experimental results demonstrate the superiority of our method which achieves state-of-the-art performance on the Stanford Drone and ETH/UCY benchmarks.”
Visual Tracking: an Experimental Survey (2013, neutral): “Data association can be formulated as a frame-by-frame local optimization of bi-partite graph matching [8] or as a global optimization of a k-partite graph [5], by a minimum-cost flow [9] or by GMCP [7].”
Human motion trajectory prediction: a survey (2019, methodology): “…applications can beneﬁt from from long-term prediction models, as they allow to associate new observations with existing tracks (e.g. Pellegrini et al. (2009) 2010)) and to model long-term distributions over possible future positions of each person (Yen et al. 2008; Chung and Huang 2012).”
Multiple object tracking: A literature review (2014, neutral): “Employed Forces [2] repulsion, constancy, fidelity [85] repulsion, constancy, attraction, coherence [61] coherence [66] repulsion, coherence [115] constancy, fidelity, repulsion [116] constancy, coherence”
Core Challenges of Social Robot Navigation: A Survey (2021, methodology): “From exo-centric perspective, common approaches include probabilistic progression-based methods [16, 32, 81, 199, 283, 284], graph-based approaches [30, 67, 129, 186], clustering methods [80, 231], and social force model-based approaches [149, 173, 260].”
You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions (2019, background): “Beyond body pose, there is a growing interest in modeling human-human interactions [57, 23, 40] to predict pedestrian trajectories [1, 43, 2], analyze social behavior and group activities [43, 59, 6, 15, 23], and understand human-object interactions [61, 19, 12].”