Next Article in Journal
Overview of Binary Locally Repairable Codes for Distributed Storage Systems
Next Article in Special Issue
Fallen People Detection Capabilities Using Assistive Robot
Previous Article in Journal
Accelerometer-Based Gyroscope Drift Compensation Approach in a Dual-Axial Stabilization Platform
Previous Article in Special Issue
Automatic Scene Recognition through Acoustic Classification for Behavioral Robotics
Open AccessArticle

Online Learned Siamese Network with Auto-Encoding Constraints for Robust Multi-Object Tracking

School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
*
Author to whom correspondence should be addressed.
Electronics 2019, 8(6), 595; https://doi.org/10.3390/electronics8060595
Received: 3 May 2019 / Revised: 22 May 2019 / Accepted: 22 May 2019 / Published: 28 May 2019
(This article belongs to the Special Issue Machine Learning Techniques for Assistive Robotics)
Multi-object tracking aims to estimate the complete trajectories of objects in a scene. Distinguishing among objects efficiently and correctly in complex environments is a challenging problem. In this paper, a Siamese network with an auto-encoding constraint is proposed to extract discriminative features from detection responses in a tracking-by-detection framework. Different from recent deep learning methods, the simple two layers stacked auto-encoder structure enables the Siamese network to operate efficiently only with small-scale online sample data. The auto-encoding constraint reduces the possibility of overfitting during small-scale sample training. Then, the proposed Siamese network is improved to extract the previous-appearance-next vector from tracklet for better association. The new feature integrates the appearance, previous, and next stage motions of an element in a tracklet. With the new features, an online incremental learned tracking framework is established. It contains reliable tracklet generation, data association to generate complete object trajectories, and tracklet growth to deal with missing detections and to enhance the new feature for tracklet. Benefiting from discriminative features, the final trajectories of objects can be achieved by an efficient iterative greedy algorithm. Feature experiments show that the proposed Siamese network has advantages in terms of both discrimination and correctness. The system experiments show the improved tracking performance of the proposed method. View Full-Text
Keywords: multi-object tracking; Siamese network; discriminative feature; online learning multi-object tracking; Siamese network; discriminative feature; online learning
Show Figures

Figure 1

MDPI and ACS Style

Liu, P.; Li, X.; Liu, H.; Fu, Z. Online Learned Siamese Network with Auto-Encoding Constraints for Robust Multi-Object Tracking. Electronics 2019, 8, 595.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
  • Externally hosted supplementary file 1
    Doi: 10.5281/zenodo.2653140
    Link: https://zenodo.org/record/2653140
    Description: Experimental codes are uploaded. Since the manuscript has not been published. We set the access constraints. The access condition is the status of reviewer.
Back to TopTop