You'll never walk alone: Modeling social behavior for multi-target tracking

Pellegrini, Stefano; Ess, Andreas; Schindler, Konrad; Gool, Luc Van

doi:10.1109/iccv.2009.5459260

Cited by 1,105 publications

(1,046 citation statements)

References 22 publications

Supporting

Mentioning

1,042

Contrasting

Order By: Relevance

“…The time gap between observations is also taken into account in order to be able to work at any frame rate, therefore velocity measures are used instead of distances. The velocities are mapped to probabilities with a Gauss error function as shown in Equation (10), assuming the pedestrians cannot exceed a maximum velocity V max . The effect of parameter V max is detailed in Section 5.1.…”

Section: Tracking With Linear Programmingmentioning

confidence: 99%

“…Red = probability distribution if cost depends linearly on the velocity. Green = probability distribution if the relation of cost and velocities is expressed by Equation (10). An V max = 7m/s is used in the experiments.…”

Section: Tracking With Linear Programmingmentioning

confidence: 99%

“…The idea is that if two pedestrians are close to each other over a reasonable period of time, they are likely to belong to the same group. From the training sequence in [10], we learn the distance and speed probability distributions of the members of a group P g vs. individual pedestrians P i . If m and n are two trajectories which appear on the scene at t = [0, N ], we compute the flag G m,n that indicates if m and n belong to the same group.…”

Section: Group Modelmentioning

confidence: 99%

“…Though each object can be tracked separately, recent works have proven that tracking objects jointly and taking into consideration their interaction can give much better results in complex scenes. Current research is mainly focused on two aspects to exploit the interaction between pedestrians: the use of a global optimization strategy [8,9] and a social motion model [10,11]. The focus of this paper is to marry the concepts of global optimization and social and grouping behavior to obtain a robust tracker able to work in crowded scenarios.…”

Section: Introductionmentioning

confidence: 99%

“…These have been defined in what is called the Social Force Model (SFM) [21], which has been used for abnormal crowd behavior detection [22], crowd simulation [23] and has only recently been applied to multiple people tracking: in [24], an energy minimization approach is used to predict the future position of each pedestrian considering all the terms of the social force model. In [10] and [25], the social forces are included in the motion model of the Kalman or Extended Kalman filter. In [26] a method is presented to detect small groups of people in a crowd, but it is only recently that grouping behavior has been included in a tracking framework [11,27,28].…”

Section: Related Workmentioning

confidence: 99%

See 4 more Smart Citations

Exploiting Pedestrian Interaction via Global Optimization and Social Behaviors

Leal-Taixé

Pons-Moll

Rosenhahn

2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Multiple people tracking consists in detecting the subjects at each frame and matching these detections to obtain full trajectories. In semi-crowded environments, pedestrians often occlude each other, making tracking a challenging task. Tracking methods mostly work with the assumption that each pedestrian moves independently unaware of the objects or the other pedestrians around it. In the real world though, it is clear that when walking in a crowd, pedestrians try to avoid collisions, keep a close distance to a group of friends or avoid static obstacles in the scene. In this paper, we present an approach which includes the interaction between pedestrians in two ways: first, including social and grouping behavior as a physical model within the tracking system, and second, using a global optimization scheme which takes into account all trajectories and all frames to solve the data association problem . Results are presented on three challenging publicly available datasets, showing our method outperforms state-of-the-art tracking systems. We also make a thorough analysis of the effect of the parameters of the proposed tracker as well as its robustness against noise, outliers and missing data.

show abstract

Section: Tracking With Linear Programmingmentioning

confidence: 99%

Section: Tracking With Linear Programmingmentioning

confidence: 99%

Section: Group Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Exploiting Pedestrian Interaction via Global Optimization and Social Behaviors

Leal-Taixé

Pons-Moll

Rosenhahn

2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

DeepORCA: Realistic crowd simulation for varying scenes

Mao

Meng

et al. 2022

Computer Animation & Virtual

View full text Add to dashboard Cite

Crowd simulation is a challenging problem, aiming to generate realistic pedestrians motions in virtual environment. Nowadays, ORCA is a widely used simulation algorithm in practice because of its stable and efficient performance. However, this algorithm cannot regenerate continuity and diversity of pedestrian motions in real data, leading to defects in motion fidelity. Otherwise, trajectory prediction methods based on deep learning have progressed in real pedestrians movement patterns mining. However, they are rarely applied in simulation due to the lack of ability to avoid collision and adapt to manufactured scenarios. Our work proposes a simulation method DeepORCA that integrates ORCA with a CVAE-based velocity probability generator, which can model motion continuity, variable intentions, and scene semantics. Moreover, DeepORCA converts the velocity optimization into quadratic programming, which accelerates the calculation while maintaining the collision-avoidance ability of ORCA. In the experiments of real and artificial scenes, our method produces more realistic crowd simulation results than ORCA quantitatively and qualitatively, while keeps the computational efficiency at the same order of magnitude.

show abstract

ORCANet: Differentiable multi‐parameter learning for crowd simulation

Zhang

Wang

et al. 2022

Computer Animation & Virtual

View full text Add to dashboard Cite

Realistic crowd simulation has always been an important research field in computer graphics. While both agent-based motion models and data-driven behavior models have made some progress, they are still suffering from either huge effort of multi-parameter tuning or limited realistic motion. In this article, we propose a novel and differentiable multi-parameter learning method for crowd simulation, which is called ORCANet. The main idea is to learn from real data and inverse evaluating the multi-parameter for subsequent simulation.ORCANet uses classic optimal reciprocal collision avoidance (ORCA) as a basic motion model which is integrated into the deep learning framework. Addressing the feature of linear programming and non-differentiable operation, a Gaussian kernel is added to approximate the role of neighbor distance in collision avoidance, which turns the original discrete operation into a fully differentiable forward simulation. Furthermore, we leverage ORCANet to optimize the multi-parameter combination in synthetic and real-world datasets. ORCANet is proved to rapidly converge to correct parameter values and regenerate the input synthetic sequence. Moreover, experiments on real-world datasets by the metric of pedestrian trajectories verified that a more realistic crowd simulation has been generated through ORCANet.

show abstract

You'll never walk alone: Modeling social behavior for multi-target tracking

Cited by 1,105 publications

References 22 publications

Exploiting Pedestrian Interaction via Global Optimization and Social Behaviors

Exploiting Pedestrian Interaction via Global Optimization and Social Behaviors

DeepORCA: Realistic crowd simulation for varying scenes

ORCANet: Differentiable multi‐parameter learning for crowd simulation

Contact Info

Product

Resources

About