Who did What at Where and When: Simultaneous Multi-Person Tracking and Activity Recognition

07/03/2018
by   Wenbo Li, et al.
2

We present a bootstrapping framework to simultaneously improve multi-person tracking and activity recognition at individual, interaction and social group activity levels. The inference consists of identifying trajectories of all pedestrian actors, individual activities, pairwise interactions, and collective activities, given the observed pedestrian detections. Our method uses a graphical model to represent and solve the joint tracking and recognition problems via multi-stages: (1) activity-aware tracking, (2) joint interaction recognition and occlusion recovery, and (3) collective activity recognition. We solve the where and when problem with visual tracking, as well as the who and what problem with recognition. High-order correlations among the visible and occluded individuals, pairwise interactions, groups, and activities are then solved using a hypergraph formulation within the Bayesian framework. Experiments on several benchmarks show the advantages of our approach over state-of-art methods.

READ FULL TEXT

page 1

page 10

page 11

page 13

research
10/30/2017

An Integrated Approach to Crowd Video Analysis: From Tracking to Multi-level Activity Recognition

We present an integrated framework for simultaneous tracking, group dete...
research
11/22/2018

Online Collective Animal Movement Activity Recognition

Learning the activities of animals is important for the purpose of monit...
research
07/01/2019

A Framework For Identifying Group Behavior Of Wild Animals

Activity recognition and, more generally, behavior inference tasks are g...
research
07/12/2022

Hunting Group Clues with Transformers for Social Group Activity Recognition

This paper presents a novel framework for social group activity recognit...
research
06/22/2021

PALMAR: Towards Adaptive Multi-inhabitant Activity Recognition in Point-Cloud Technology

With the advancement of deep neural networks and computer vision-based H...
research
09/20/2017

Latent Embeddings for Collective Activity Recognition

Rather than simply recognizing the action of a person individually, coll...
research
11/05/2017

Simultaneous Joint and Object Trajectory Templates for Human Activity Recognition from 3-D Data

The availability of low-cost range sensors and the development of relati...

Please sign up or login with your details

Forgot password? Click here to reset