Trajectory distributions: A new description of movement for trajectory prediction
Abstract Trajectory prediction is a fundamental and challenging task for numerous applications, such as autonomous driving and intelligent robots. Current works typically treat pedestrian trajectories as a series of 2D point coordinates. However, in real scenarios, the trajectory often exhibits rand...
Main Authors: | Pei Lv, Hui Wei, Tianxin Gu, Yuzhen Zhang, Xiaoheng Jiang, Bing Zhou, Mingliang Xu |
---|---|
Format: | Article |
Language: | English |
Published: |
SpringerOpen
2021-12-01
|
Series: | Computational Visual Media |
Subjects: | |
Online Access: | https://doi.org/10.1007/s41095-021-0236-6 |
Similar Items
-
A Method for LSTM-Based Trajectory Modeling and Abnormal Trajectory Detection
by: Yufan Ji, et al.
Published: (2020-01-01) -
Ship Trajectory Prediction: An Integrated Approach Using ConvLSTM-Based Sequence-to-Sequence Model
by: Wenxiong Wu, et al.
Published: (2023-07-01) -
A Method for Predicting Diverse Lane-Changing Trajectories of Surrounding Vehicles Based on Early Detection of Lane Change
by: Yuan-Yuan Ren, et al.
Published: (2022-01-01) -
A Dynamic and Static Context-Aware Attention Network for Trajectory Prediction
by: Jian Yu, et al.
Published: (2021-05-01) -
Unsupervised vessel trajectory reconstruction
by: Chih-Wei Chen, et al.
Published: (2023-03-01)