Video-Based Crowd Synthesis

Flagg, Matthew; Rehg, James M.

doi:10.1109/tvcg.2012.317

Cited by 20 publications

(11 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some recent works have been proposed to synthesize crowd videos with realistic microscale behavior [28].…”

Section: ) Entertainmentmentioning

confidence: 99%

“…After this phase, subregion patches of low probability under the associated MDT are considered anomalies. Given patch x 1:τ , the distribution of the hidden state sequence s τ 1 under the i th DT component, p S|X (s 1:τ |x 1:τ , z = i), is estimated with a Kalman filter and smoother [29], [30], as discussed in [28]. The value of the temporal anomaly map at location l is the negative-log probability of the most-likely state sequence for the patch at l…”

Section: Normalcy and Anomaly Modelingmentioning

confidence: 99%

See 1 more Smart Citation

Crowded Scene Analysis: A Survey

Chang

Wang

et al. 2015

IEEE Trans. Circuits Syst. Video Technol.

446

201

View full text Add to dashboard Cite

Abstract-Automated scene analysis has been a topic of great interest in computer vision and cognitive science. Recently, with the growth of crowd phenomena in the real world, crowded scene analysis has attracted much attention. However, the visual occlusions and ambiguities in crowded scenes, as well as the complex behaviors and scene semantics, make the analysis a challenging task. In the past few years, an increasing number of works on crowded scene analysis have been reported, covering different aspects including crowd motion pattern learning, crowd behavior and activity analysis, and anomaly detection in crowds. This paper surveys the state-of-the-art techniques on this topic. We first provide the background knowledge and the available features related to crowded scenes. Then, existing models, popular algorithms, evaluation protocols, as well as system performance are provided corresponding to different aspects of crowded scene analysis. We also outline the available datasets for performance evaluation. Finally, some research problems and promising future directions are presented with discussions.

show abstract

“…Some recent works have been proposed to synthesize crowd videos with realistic microscale behavior [28].…”

Section: ) Entertainmentmentioning

confidence: 99%

Section: Normalcy and Anomaly Modelingmentioning

confidence: 99%

Crowded Scene Analysis: A Survey

Chang

Wang

et al. 2015

IEEE Trans. Circuits Syst. Video Technol.

446

201

View full text Add to dashboard Cite

show abstract

“…The simplest way to solve this problem is informing users that the video is used for visualization and asking them to neglect the background issue. Another approach is to take a picture of the place, in which the traffic situations over there will be visualized, and replace the background with content provided by the picture [27]. The achievement of this objective should consider the consistent of viewpoints and seamless blending.…”

Section: Limitationsmentioning

confidence: 99%

Traffic situation visualization based on video composition

Hsieh

Wang

2016

Computers & Graphics

View full text Add to dashboard Cite

a b s t r a c tVehicle detectors (VDs) are usually distributed in a road network to detect macroscopic traffic situations. These detectors provide global information such as vehicle flows, average speed, and road occupancy. Given that the collected statistic data are difficult for citizens to interpret, we visualize the data by providing users with realistic traffic videos. To achieve this aim, our system collects the surveillance videos and VD data that represent the traffic situation of a position. It then builds the connection between these two types of data. Considering the distribution of VDs is much denser than that of surveillance cameras, for those road segments with a VD but without a surveillance camera, one can utilize our system to synthesize videos for visually depicting the traffic situations over there. That is, we estimate vehicle flows from a video and apply the regression model to build the mapping between the flows and VD data. After that, given by a VD dataset, our system retrieves videos that match the VD data and seamlessly composes them to synthesize a traffic video. The evaluations and the experimental results demonstrate the feasibility of our system.

show abstract

“…However, the PoseShop system didn't work very well on dealing with the accurate spatial topology relationship between the background scene and synthesized objects so that geometric consistency criteria can't be matched. Flagg et al [9] presented a system for capture, analysis, synthesis, and control of video-based crowds. They introduced crowd tubes samples and constraint violations with a conflict graph to avoid collisions.…”

Section: Related Workmentioning

confidence: 99%

Autonomous Driving Simulation for Unmanned Vehicles

Zhao

Liu

Zhang

et al. 2015

2015 IEEE Winter Conference on Applications of Computer Vision

View full text Add to dashboard Cite

Human can judge driver's driving ability by observing the vehicle motion in different traffic scenes. Identically, driving behavior can be the main basis for evaluating the performance of an unmanned vehicle in both field test and simulation test. Although simulation test avoids disadvantages of field test, existing simulation systems lack traffic scene data with perception granularity of visual sensors. In order for realizing vehicle-in-loop simulation, simulation technique of driving behaviors must be able to exhibit actual motion of unmanned vehicles. In this paper, we propose an automatic approach of simulating autonomous driving behaviors of vehicles in traffic scene represented by image sequences. Different from general simulation systems, we use actual traffic environment data to build the traffic scene and simulate the driving behaviors. After the proposed method was embedded in scene browser, a typical traffic scene including the intersections was chosen for virtual vehicle to execute the driving tasks of lane change, overtaking, slowing down and stop, right turn and U-Turn. The experimental results show that different driving behaviors of vehicles in typical traffic scene can be exhibited smoothly and realistically. Our method can also be used for generating simulation data of traffic scenes that are difficult to collect.

show abstract

Video-Based Crowd Synthesis

Cited by 20 publications

References 36 publications

Crowded Scene Analysis: A Survey

Crowded Scene Analysis: A Survey

Traffic situation visualization based on video composition

Autonomous Driving Simulation for Unmanned Vehicles

Contact Info

Product

Resources

About