Tracking with local spatio-temporal motion patterns in extremely crowded scenes

2010 ◽  
Author(s):  
Louis Kratz ◽  
Ko Nishino
Keyword(s):  
Motion Patterns ◽  
Spatio Temporal ◽  
Crowded Scenes

scholarly journals Multimodal Interaction-Aware Trajectory Prediction in Crowded Space

2020 ◽  
Vol 34 (07) ◽  
pp. 11982-11989
Author(s):  
Xiaodan Shi ◽  
Xiaowei Shao ◽  
Zipei Fan ◽  
Renhe Jiang ◽  
Haoran Zhang ◽  
...  
Keyword(s):  
Multimodal Interaction ◽  
Autonomous Driving ◽  
Human Motion ◽  
Human Interaction ◽  
Trajectory Prediction ◽  
Motion Patterns ◽  
Mixture Density ◽  
Interacting Agents ◽  
Temporal Model ◽  
Spatio Temporal

Accurate human path forecasting in complex and crowded scenarios is critical for collision avoidance of autonomous driving and social robots navigation. It still remains as a challenging problem because of dynamic human interaction and intrinsic multimodality of human motion. Given the observation, there is a rich set of plausible ways for an agent to walk through the circumstance. To address those issues, we propose a spatio-temporal model that can aggregate the information from socially interacting agents and capture the multimodality of the motion patterns. We use mixture density functions to describe the human path and predict the distribution of future paths with explicit density. To integrate more factors to model interacting people, we further introduce a coordinate transformation to represent the relative motion between people. Extensive experiments over several trajectory prediction benchmarks demonstrate that our method is able to forecast various plausible futures in complex scenarios and achieves state-of-the-art performance.

scholarly journals Revealing sound-induced motion patterns in fish hearing structures in 4D: A standing wave tube-like setup designed for high-resolution time-resolved tomography

2021 ◽  
Author(s):  
Isabelle P. Maiditsch ◽  
Friedrich Ladich ◽  
Martin Heß ◽  
Christian M. Schlepütz ◽  
Tanja Schulz-Mirbach
Keyword(s):  
Standing Wave ◽  
Morphological Diversity ◽  
Wave Tube ◽  
Time Resolved ◽  
Motion Patterns ◽  
Bony Fishes ◽  
Spatial Dimensions ◽  
Spatio Temporal ◽  
Standing Wave Tube ◽  
Fish Hearing

Modern bony fishes possess a high morphological diversity in the auditory structures and their auditory capabilities. Yet, our knowledge of how the auditory structures such as the otoliths in the inner ears and the swim bladder work together remains elusive. Gathering experimental evidence on the in-situ motion of fish auditory structures while avoiding artifacts caused by surgical exposure of the structures has been challenging for decades. Synchrotron radiation-based tomography with high spatio-temporal resolution allows to study morphofunctional issues non-invasively in an unprecedented way. We therefore aimed to develop an approach that characterizes the moving structures in 4D (= three spatial dimensions+time). We designed a miniature standing wave tube-like setup to meet both the requirements of tomography and those of tank acoustics. With this new setup, we successfully visualized the motion of isolated otoliths and the auditory structures in zebrafish (Danio rerio) and the glass catfish (Kryptopterus vitreolus).

Sign in / Sign up

Export Citation Format

Share Document