Next Article in Journal
Energy-Efficient Fuzzy-Logic-Based Clustering Technique for Hierarchical Routing Protocols in Wireless Sensor Networks
Next Article in Special Issue
A Three-Dimensional Hough Transform-Based Track-Before-Detect Technique for Detecting Extended Targets in Strong Clutter Backgrounds
Previous Article in Journal
Track-Before-Detect Framework-Based Vehicle Monocular Vision Sensors
Previous Article in Special Issue
Behavioral Pedestrian Tracking Using a Camera and LiDAR Sensors on a Moving Vehicle
Open AccessArticle

Data Association for Multi-Object Tracking via Deep Neural Networks

1
School of Electrical Engineering and Computer Science, Gwanju Institute of Science and Technology, Gwangju 61005, Korea
2
School of Engineering, RMIT University, Melbourne, VIC 3000, Australia
*
Author to whom correspondence should be addressed.
Sensors 2019, 19(3), 559; https://doi.org/10.3390/s19030559
Received: 23 December 2018 / Revised: 22 January 2019 / Accepted: 25 January 2019 / Published: 29 January 2019
(This article belongs to the Special Issue Multiple Object Tracking: Making Sense of the Sensors)
With recent advances in object detection, the tracking-by-detection method has become mainstream for multi-object tracking in computer vision. The tracking-by-detection scheme necessarily has to resolve a problem of data association between existing tracks and newly received detections at each frame. In this paper, we propose a new deep neural network (DNN) architecture that can solve the data association problem with a variable number of both tracks and detections including false positives. The proposed network consists of two parts: encoder and decoder. The encoder is the fully connected network with several layers that take bounding boxes of both detection and track-history as inputs. The outputs of the encoder are sequentially fed into the decoder which is composed of the bi-directional Long Short-Term Memory (LSTM) networks with a projection layer. The final output of the proposed network is an association matrix that reflects matching scores between tracks and detections. To train the network, we generate training samples using the annotation of Stanford Drone Dataset (SDD). The experiment results show that the proposed network achieves considerably high recall and precision rate as the binary classifier for the assignment tasks. We apply our network to track multiple objects on real-world datasets and evaluate the tracking performance. The performance of our tracker outperforms previous works based on DNN and comparable to other state-of-the-art methods. View Full-Text
Keywords: multi-object tracking; data association; deep neural network; long short-term memory network multi-object tracking; data association; deep neural network; long short-term memory network
Show Figures

Figure 1

MDPI and ACS Style

Yoon, K.; Kim, D.Y.; Yoon, Y.-C.; Jeon, M. Data Association for Multi-Object Tracking via Deep Neural Networks. Sensors 2019, 19, 559.

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
Search more from Scilit
 
Search
Back to TopTop