Gradient-based steering for vision-based crowd simulation algorithms

Dutra, Teofilo B.; Marques, Ricardo; Cavalcante-Neto, Joaquim Bento; Vidal, Creto Augusto; Pettré, Julien

doi:10.1111/cgf.13130

Cited by 51 publications

(51 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We now provide a qualitative comparison of our algorithm, and more specifically the collision avoidance function (Eq. 16), with RVO2 [vdBGLM11] and the model proposed by Dutra et al [DMCN∗17]. We chose those two approaches because they are good representative of two categories of approaches: velocity‐based and vision‐based approach.…”

Section: Discussionmentioning

confidence: 99%

Character navigation in dynamic environments based on optical flow

López

Chaumette

Marchand

et al. 2019

Computer Graphics Forum

View full text Add to dashboard Cite

Steering and navigation are important components of character animation systems to enable them to autonomously move in their environment. In this work, we propose a synthetic vision model that uses visual features to steer agents through dynamic environments. Our agents perceive optical flow resulting from their relative motion with the objects of the environment. The optical flow is then segmented and processed to extract visual features such as the focus of expansion and time‐to‐collision. Then, we establish the relations between these visual features and the agent motion, and use them to design a set of control functions which allow characters to perform object‐dependent tasks, such as following, avoiding and reaching. Control functions are then combined to let characters perform more complex navigation tasks in dynamic environments, such as reaching a goal while avoiding multiple obstacles. Agent's motion is achieved by local minimization of these functions. We demonstrate the efficiency of our approach through a number of scenarios. Our work sets the basis for building a character animation system which imitates human sensorimotor actions. It opens new perspectives to achieve realistic simulation of human characters taking into account perceptual factors, such as the lighting conditions of the environment.

show abstract

Section: Discussionmentioning

confidence: 99%

Character navigation in dynamic environments based on optical flow

López

Chaumette

Marchand

et al. 2019

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…Tu et al [Tu and Terzopoulos 1994] searched to reproduce the entire locomotion system of fishes and was improved later by Terzopoulos et al [Terzopoulos and Rabie 1995]. Ondrej et al [Ondřej et al 2010] and Dutra et al [Dutra et al 2017] presented collision avoidance models using synthetic vision. Most of the previous methods perceive geometrical information that is then processed to steer agents.…”

Section: Vision-based Character Steeringmentioning

confidence: 99%

“…Most solutions are based on a geometric formulation of the problem, solved by applying systems of rules or by defining energy function that guide the agent towards its goal while avoiding obstacles. More recent approaches simulate the visual perception of agents [Ondřej et al 2010] [Dutra et al 2017], and made finally possible to control the locomotion of an agent solely on the basis of information about the optical flow generated by its movement relative to the environment [López et al 2019]. We base our current work on this previous result.…”

Section: Introductionmentioning

confidence: 99%

Attracted by light: vision-based steering virtual characters among dark and light obstacles

López

Chaumette

Marchand

et al. 2019

Motion, Interaction and Games

View full text Add to dashboard Cite

This paper introduces the use of numerical optical flow (OF) in vision-based steering techniques-that control characters locomotion trajectories by using a simulation of their visual perception. In contrast with synthetic OF that was previously used, numerical OF is sensitive to the contrast of objects, and provides, for example, uncertain results in dark areas. Thus, we here propose a locomotion control technique which is robust to such uncertainty: dark areas in the scene are processed as obstacles, that however may be traversed in case of necessity. As demonstrated in various scenarios, this tends to make character avoiding darkest areas, or traversing them more carefully, as it can be observed for real humans. CCS CONCEPTS • Computing methodologies → Modeling and simulation; Model development and analysis; Model verification and validation; Animation.

show abstract

“…Recently, synthetic vision‐based approaches have also been introduced, which can more closely match human behavior and have made formation crowd simulation more realistic . However, to obtain real data is time consuming.…”

Section: Related Workmentioning

confidence: 99%

Hierarchical planning‐based crowd formation

Liu

Wang

Liu

et al. 2019

Computer Animation & Virtual

View full text Add to dashboard Cite

Team formation with realistic crowd simulation behavior is a challenge in computer graphics, multiagent control, and social simulation. In this study, we propose a framework of crowd formation via hierarchical planning, which includes cooperative-task, coordinated-behavior, and action-control planning. In cooperative-task planning, we improve the grid potential field to achieve global path planning for a team. In coordinated-behavior planning, we propose a time-space table to arrange behavior scheduling for a movement. In action-control planning, we combine the gaze-movement angle model and fuzzy logic control to achieve agent action. Our method has several advantages. (1) The hierarchical architecture is guaranteed to match the human decision process from high to low intelligence. (2) The agent plans his behavior only with the local information of his neighbor; the global intelligence of the group emerges from these local interactions.(3) The time-space table fully utilizes three-dimensional information. Our method is verified using crowds of various densities, from sparse to dense, employing quantitative performance measures. The approach is independent of the simulation model and can be extended to other crowd simulation tasks.

show abstract

Gradient-based steering for vision-based crowd simulation algorithms

Cited by 51 publications

References 38 publications

Character navigation in dynamic environments based on optical flow

Character navigation in dynamic environments based on optical flow

Attracted by light: vision-based steering virtual characters among dark and light obstacles

Hierarchical planning‐based crowd formation

Contact Info

Product

Resources

About