Learning to Divide and Conquer for Online Multi-Target Tracking

09/14/2015
by   Francesco Solera, et al.
0

Online Multiple Target Tracking (MTT) is often addressed within the tracking-by-detection paradigm. Detections are previously extracted independently in each frame and then objects trajectories are built by maximizing specifically designed coherence functions. Nevertheless, ambiguities arise in presence of occlusions or detection errors. In this paper we claim that the ambiguities in tracking could be solved by a selective use of the features, by working with more reliable features if possible and exploiting a deeper representation of the target only if necessary. To this end, we propose an online divide and conquer tracker for static camera scenes, which partitions the assignment problem in local subproblems and solves them by selectively choosing and combining the best features. The complete framework is cast as a structural learning task that unifies these phases and learns tracker parameters from examples. Experiments on two different datasets highlights a significant improvement of tracking performances (MOTA +10 the art.

READ FULL TEXT

page 1

page 7

page 11

research
09/25/2021

Vehicle Detection and Tracking From Surveillance Cameras in Urban Scenes

Detecting and tracking vehicles in urban scenes is a crucial step in man...
research
03/06/2022

Reinstating Dlib Correlation Human Trackers Under Occlusions in Human Detection based Tracking

Human tracking in video feeds has been a popular research area, which co...
research
05/29/2019

Instance-Aware Representation Learning and Association for Online Multi-Person Tracking

Multi-Person Tracking (MPT) is often addressed within the detection-to-a...
research
11/12/2017

Evaluation of trackers for Pan-Tilt-Zoom Scenarios

Tracking with a Pan-Tilt-Zoom (PTZ) camera has been a research topic in ...
research
06/20/2018

Hide and Seek tracker: Real-time recovery from target loss

In this paper, we examine the real-time recovery of a video tracker from...
research
06/14/2011

Robust Mobile Object Tracking Based on Multiple Feature Similarity and Trajectory Filtering

This paper presents a new algorithm to track mobile objects in different...
research
10/07/2013

Online Unsupervised Feature Learning for Visual Tracking

Feature encoding with respect to an over-complete dictionary learned by ...

Please sign up or login with your details

Forgot password? Click here to reset