DeepAI AI Chat
Log In Sign Up

Multi-view Tracking Using Weakly Supervised Human Motion Prediction

10/19/2022
by   Martin Engilberge, et al.
EPFL
Tencent
0

Multi-view approaches to people-tracking have the potential to better handle occlusions than single-view ones in crowded scenes. They often rely on the tracking-by-detection paradigm, which involves detecting people first and then connecting the detections. In this paper, we argue that an even more effective approach is to predict people motion over time and infer people's presence in individual frames from these. This enables to enforce consistency both over time and across views of a single temporal frame. We validate our approach on the PETS2009 and WILDTRACK datasets and demonstrate that it outperforms state-of-the-art methods.

READ FULL TEXT

page 1

page 4

page 6

03/17/2020

Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wild

One major challenge for monocular 3D human pose estimation in-the-wild i...
12/02/2016

Globally Consistent Multi-People Tracking using Motion Patterns

Many state-of-the-art approaches to people tracking rely on detecting th...
12/09/2020

Self-supervised Human Detection and Segmentation via Multi-view Consensus

Self-supervised detection and segmentation of foreground objects in comp...
03/24/2022

Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videos

This paper addresses a new problem of weakly-supervised online action se...
09/27/2018

Multi-View Frame Reconstruction with Conditional GAN

Multi-view frame reconstruction is an important problem particularly whe...
11/25/2019

Estimating People Flows to Better Count them in Crowded Scenes

State-of-the-art methods for counting people in crowded scenes rely on d...