Top-view Trajectories: A Pedestrian Dataset of Vehicle-Crowd Interaction from Controlled Experiments and Crowded Campus
The Ohio State University（俄亥俄州立大学）；Dalian University of Technology（大连理工大学）
Dongfang Yang, Linhui Li, Keith Redmill, Ümit Özgüner
备注：
This paper was accepted into the 30th IEEE Intelligent Vehicles Symposium. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses
Predicting the collective motion of a group of pedestrians (a crowd) under the vehicle influence is essential for the development of autonomous vehicles to deal with mixed urban scenarios where interpersonal interaction and vehicle-crowd interaction (VCI) are significant. This usually requires a model that can describe individual pedestrian motion under the influence of nearby pedestrians and the vehicle. This study proposed two pedestrian trajectory datasets, CITR dataset and DUT dataset, so that the pedestrian motion models can be further calibrated and verified, especially when vehicle influence on pedestrians plays an important role. CITR dataset consists of experimentally designed fundamental VCI scenarios (front, back, and lateral VCIs) and provides unique ID for each pedestrian, which is suitable for exploring a specific aspect of VCI. DUT dataset gives two ordinary and natural VCI scenarios in crowded university campus, which can be used for more general purpose VCI exploration. The trajectories of pedestrians, as well as vehicles, were extracted by processing video frames that come from a down-facing camera mounted on a hovering drone as the recording equipment. The final trajectories of pedestrians and vehicles were refined by Kalman filters with linear point-mass model and nonlinear bicycle model, respectively, in which xy-velocity of pedestrians and longitudinal speed and orientation of vehicles were estimated. The statistics of the velocity magnitude distribution demonstrated the validity of the proposed dataset. In total, there are approximate 340 pedestrian trajectories in CITR dataset and 1793 pedestrian trajectories in DUT dataset. The dataset is available at GitHub.
STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes
ShanghaiTech University（上海科技大学）；The Chinese University of Hong Kong（香港中文大学）；RWTH Aachen University（亚琛工业大学）；Shanghai AI Laboratory（上海人工智能实验室）；University of Kentucky（肯塔基大学）；University of Maryland at College Park（马里兰大学帕克分校）
PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes
Institute of Electronics, Chinese Academy of Sciences（中国科学院电子学研究所）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Depth-Guided Video Object Counting in Crowded Scenes
Harbin Institute of Technology (Weihai)（哈尔滨工业大学（威海））；City University of Hong Kong（香港城市大学）；University of Science and Technology of China（中国科学技术大学）；Harbin Institute of Technology Qingdao Research Institute（哈尔滨工业大学青岛研究院）
CrowdQuery: Density-Guided Query Module for Enhanced 2D and 3D Detection in Crowded Scenes
Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院）；Mercedes-Benz AG, Research and Development（梅赛德斯-奔驰集团，研发部门）；Intelligent Vehicles Group at TU Delft（代尔夫特理工大学智能车辆组）；Research Center for Information Technology (FZI)（信息科技研究中心）
Human Pose Estimation for Real-World Crowded Scenarios
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；Fraunhofer Institute for Optronics, System Technologies and Image Exploitation IOSB（弗劳恩霍夫光电、系统技术与图像利用研究所IOSB）
