Synthetic Crowd and Pedestrian Generator for Deep Learning Problems

Khadka, Anish; Remagnino, Paolo; Argyriou, Vasileios

doi:10.1109/icassp40776.2020.9053301

Cited by 8 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This synthesis of PB principles and DL models is not an isolated endeavor. Alahi et al [5] and Khadka et al [25] utilized simulated data from PB models for training DL algorithms. Antonucci et al [26] embedded a PB model directly into the DL architecture.…”

Section: Related Workmentioning

confidence: 99%

Toward Better Pedestrian Trajectory Predictions: The Role of Density and Time-to-Collision in Hybrid Deep-Learning Algorithms

Korbmacher,

Tordeux

2024

Sensors

View full text Add to dashboard Cite

Predicting human trajectories poses a significant challenge due to the complex interplay of pedestrian behavior, which is influenced by environmental layout and interpersonal dynamics. This complexity is further compounded by variations in scene density. To address this, we introduce a novel dataset from the Festival of Lights in Lyon 2022, characterized by a wide range of densities (0.2–2.2 ped/m2). Our analysis demonstrates that density-based classification of data can significantly enhance the accuracy of predictive algorithms. We propose an innovative two-stage processing approach, surpassing current state-of-the-art methods in performance. Additionally, we utilize a collision-based error metric to better account for collisions in trajectory predictions. Our findings indicate that the effectiveness of this error metric is density-dependent, offering prediction insights. This study not only advances our understanding of human trajectory prediction in dense environments, but also presents a methodological framework for integrating density considerations into predictive modeling, thereby improving algorithmic performance and collision avoidance.

show abstract

Section: Related Workmentioning

confidence: 99%

Toward Better Pedestrian Trajectory Predictions: The Role of Density and Time-to-Collision in Hybrid Deep-Learning Algorithms

Korbmacher,

Tordeux

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…A popular application of data generation can be found in the training of autonomous vehicles for the augmentation of data for scenarios that are not sufficiently represented in the available data set [256], [257]. In [258], [255], [33], the authors apply the social force model to generate a synthetic data-set for the training of neural networks and setting of hyper-parameters. Knowledge-guided design of architecture is another possibility to improve the DL algorithms with knowledge.…”

Section: A the Hybrid Approachmentioning

confidence: 99%

Review of Pedestrian Trajectory Prediction Methods: Comparing Deep Learning and Knowledge-based Approaches

Korbmacher¹,

Tordeux²

2021

Preprint

View full text Add to dashboard Cite

In crowd scenarios, predicting trajectories of pedestrians is a complex and challenging task depending on many external factors. The topology of the scene and the interactions between the pedestrians are just some of them. Due to advancements in data-science and data collection technologies deep learning methods have recently become a research hotspot in numerous domains. Therefore, it is not surprising that more and more researchers apply these methods to predict trajectories of pedestrians. This paper compares these relatively new deep learning algorithms with classical knowledge-based models that are widely used to simulate pedestrian dynamics. It provides a comprehensive literature review of both approaches, explores technical and application oriented differences, and addresses open questions as well as future development directions. Our investigations point out that the pertinence of knowledge-based models to predict local trajectories is nowadays questionable because of the high accuracy of the deep learning algorithms. Nevertheless, the ability of deep-learning algorithms for large-scale simulation and the description of collective dynamics remains to be demonstrated. Furthermore, the comparison shows that the combination of both approaches (the hybrid approach) seems to be promising to overcome disadvantages like the missing explainability of the deep learning approach.

show abstract

“…Chai et al(2020) uses neural network model to successfully generate a continuous crowd video with diverse crowd behaviors. A crowd data synthesis tool based on real image scene is proposed by Khadka et al(2020). Based on graphics tools, the real image scenes can be used to generate data sets for a variety of computer vision-related problems.…”

Section: Introductionmentioning

confidence: 99%

A Multi-Scenario Crowd Data Synthesis Based On Building Information Modeling

Huang¹,

Gao²,

Ke³

et al. 2022

Proceedings of the 29th EG-ICE International Workshop on Intelligent Computing in Engineering

View full text Add to dashboard Cite

Deep learning methods have proven to be effective in the field of crowd analysis recently. Nonetheless, the performance of deep learning models is affected by the inadequacy of training datasets. Because of policy implications and privacy restrictions, crowd data is commonly difficult to access. In order to overcome the difficulty of insufficient dataset, the previous work used to synthesize labelled crowd data in outdoor scenes and virtual games. However, these methods perform data synthesis with limited environmental information and inflexible crowd rules, usually in unauthentic environment. In this paper, a tool for synthesizing crowd data in BIM models with multiple scenes is proposed. This tool can make full use of the comprehensive information of real-world buildings, and conduct crowd simulations by setting behavior rules. The synthesized dataset is used for data augmentation for crowd analysis problems and the experimental results clearly confirm the effectiveness of the tool.

show abstract

Synthetic Crowd and Pedestrian Generator for Deep Learning Problems

Cited by 8 publications

References 17 publications

Toward Better Pedestrian Trajectory Predictions: The Role of Density and Time-to-Collision in Hybrid Deep-Learning Algorithms

Toward Better Pedestrian Trajectory Predictions: The Role of Density and Time-to-Collision in Hybrid Deep-Learning Algorithms

Review of Pedestrian Trajectory Prediction Methods: Comparing Deep Learning and Knowledge-based Approaches

A Multi-Scenario Crowd Data Synthesis Based On Building Information Modeling

Contact Info

Product

Resources

About