Online multi-object tracking with convolutional neural networks

In this paper, we propose a novel online multi-object tracking (MOT) framework, which exploits features from multiple convolutional layers. In particular, we use the top layer to formulate a category-level classifier and use a lower layer to identify instances from one category under the intuition t...

Full description

Saved in:
Bibliographic Details
Published in2017 IEEE International Conference on Image Processing (ICIP) pp. 645 - 649
Main Authors Chen, Long, Ai, Haizhou, Shang, Chong, Zhuang, Zijie, Bai, Bo
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2017
Subjects
Appearance Model
Computational modeling
Convolutional Neural Network
Convolutional neural networks
Detectors
Feature extraction
Multi-object Tracking
Target tracking
Training
Online AccessGet full text
ISSN2381-8549
DOI10.1109/ICIP.2017.8296360

Cover

More Information
Summary:In this paper, we propose a novel online multi-object tracking (MOT) framework, which exploits features from multiple convolutional layers. In particular, we use the top layer to formulate a category-level classifier and use a lower layer to identify instances from one category under the intuition that lower layers contain much more details. To avoid the computational cost caused by online fine-tuning, we train our appearance model with an offline learning strategy using the historical appearance reserved for each object. We evaluate the proposed tracking framework on a popular MOT benchmark to demonstrate the effectiveness and the state-of-the-art performance of our tracker.
ISSN:2381-8549
DOI:10.1109/ICIP.2017.8296360