Can we learn where people come from? Retracing of origins in merging situations

• URL: http://arxiv.org/abs/2012.11527v1
• Date: Mon, 21 Dec 2020 17:42:14 GMT
• Title: Can we learn where people come from? Retracing of origins in merging situations
• Authors: Marion G\"odel and Luca Spataro and Gerta K\"oster
• Abstract summary: We use density heatmaps that can be derived from sensor data as input for a random forest regressor to predict the origin distributions. We study three different datasets: A simulated dataset, experimental data, and a hybrid approach with both experimental and simulated data.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: One crucial information for a pedestrian crowd simulation is the number of agents moving from an origin to a certain target. While this setup has a large impact on the simulation, it is in most setups challenging to find the number of agents that should be spawned at a source in the simulation. Often, number are chosen based on surveys and experience of modelers and event organizers. These approaches are important and useful but reach their limits when we want to perform real-time predictions. In this case, a static information about the inflow is not sufficient. Instead, we need a dynamic information that can be retrieved each time the prediction is started. Nowadays, sensor data such as video footage or GPS tracks of a crowd are often available. If we can estimate the number of pedestrians who stem from a certain origin from this sensor data, we can dynamically initialize the simulation. In this study, we use density heatmaps that can be derived from sensor data as input for a random forest regressor to predict the origin distributions. We study three different datasets: A simulated dataset, experimental data, and a hybrid approach with both experimental and simulated data. In the hybrid setup, the model is trained with simulated data and then tested on experimental data. The results demonstrate that the random forest model is able to predict the origin distribution based on a single density heatmap for all three configurations. This is especially promising for applying the approach on real data since there is often only a limited amount of data available.

Related papers

• Personalized Federated Learning via Active Sampling [50.456464838807115]
  This paper proposes a novel method for sequentially identifying similar (or relevant) data generators. Our method evaluates the relevance of a data generator by evaluating the effect of a gradient step using its local dataset. We extend this method to non-parametric models by a suitable generalization of the gradient step to update a hypothesis using the local dataset provided by a data generator.
  arXiv  Detail & Related papers  (2024-09-03T17:12:21Z)
• Diffusion posterior sampling for simulation-based inference in tall data settings [53.17563688225137]
  Simulation-based inference ( SBI) is capable of approximating the posterior distribution that relates input parameters to a given observation. In this work, we consider a tall data extension in which multiple observations are available to better infer the parameters of the model. We compare our method to recently proposed competing approaches on various numerical experiments and demonstrate its superiority in terms of numerical stability and computational cost.
  arXiv  Detail & Related papers  (2024-04-11T09:23:36Z)
• Diffusion Dataset Generation: Towards Closing the Sim2Real Gap for Pedestrian Detection [0.11470070927586014]
  We propose a novel method of synthetic data creation meant to close the sim2real gap for the pedestrian detection task. Our method uses a diffusion-based architecture to learn a real-world distribution which, once trained, is used to generate datasets. We show that training on a combination of generated and simulated data increases average precision by as much as 27.3% for pedestrian detection models in real-world data.
  arXiv  Detail & Related papers  (2023-05-16T12:33:51Z)
• Development of a Realistic Crowd Simulation Environment for Fine-grained Validation of People Tracking Methods [0.7223361655030193]
  This work develops an extension of crowd simulation (named CrowdSim2) and prove its usability in the application of people-tracking algorithms. The simulator is developed using the very popular Unity 3D engine with particular emphasis on the aspects of realism in the environment. Three methods of tracking were used to validate generated dataset: IOU-Tracker, Deep-Sort, and Deep-TAMA.
  arXiv  Detail & Related papers  (2023-04-26T09:29:58Z)
• Grounding Graph Network Simulators using Physical Sensor Observations [12.017054986629846]
  We integrate sensory information to ground Graph Network Simulators on real world observations. We predict the mesh state of deformable objects by utilizing point cloud data.
  arXiv  Detail & Related papers  (2023-02-23T09:06:42Z)
• Learning from aggregated data with a maximum entropy model [73.63512438583375]
  We show how a new model, similar to a logistic regression, may be learned from aggregated data only by approximating the unobserved feature distribution with a maximum entropy hypothesis. We present empirical evidence on several public datasets that the model learned this way can achieve performances comparable to those of a logistic model trained with the full unaggregated data.
  arXiv  Detail & Related papers  (2022-10-05T09:17:27Z)
• Mixed Effects Neural ODE: A Variational Approximation for Analyzing the Dynamics of Panel Data [50.23363975709122]
  We propose a probabilistic model called ME-NODE to incorporate (fixed + random) mixed effects for analyzing panel data. We show that our model can be derived using smooth approximations of SDEs provided by the Wong-Zakai theorem. We then derive Evidence Based Lower Bounds for ME-NODE, and develop (efficient) training algorithms.
  arXiv  Detail & Related papers  (2022-02-18T22:41:51Z)
• Towards Optimal Strategies for Training Self-Driving Perception Models in Simulation [98.51313127382937]
  We focus on the use of labels in the synthetic domain alone. Our approach introduces both a way to learn neural-invariant representations and a theoretically inspired view on how to sample the data from the simulator. We showcase our approach on the bird's-eye-view vehicle segmentation task with multi-sensor data.
  arXiv  Detail & Related papers  (2021-11-15T18:37:43Z)
• Feature Shift Detection: Localizing Which Features Have Shifted via Conditional Distribution Tests [12.468665026043382]
  In military sensor networks, users will want to detect when one or more of the sensors has been compromised. We first define a formalization of this problem as multiple conditional distribution hypothesis tests. For both efficiency and flexibility, we propose a test statistic based on the density model score function.
  arXiv  Detail & Related papers  (2021-07-14T18:23:24Z)
• Transfer learning suppresses simulation bias in predictive models built from sparse, multi-modal data [15.587831925516957]
  Many problems in science, engineering, and business require making predictions based on very few observations. To build a robust predictive model, these sparse data may need to be augmented with simulated data, especially when the design space is multidimensional. We combine recent developments in deep learning to build more robust predictive models from multimodal data.
  arXiv  Detail & Related papers  (2021-04-19T23:28:32Z)
• Testing the Safety of Self-driving Vehicles by Simulating Perception and Prediction [88.0416857308144]
  We propose an alternative to sensor simulation, as sensor simulation is expensive and has large domain gaps. We directly simulate the outputs of the self-driving vehicle's perception and prediction system, enabling realistic motion planning testing.
  arXiv  Detail & Related papers  (2020-08-13T17:20:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.