Ship Detection and Tracking in Inland Waterways Using Improved YOLOv3 and Deep SORT

Yang Jie,Lilianasimwe Leonidas,Munsif Ali,Farhan Mumtaz

doi:10.3390/sym13020308

Yang Jie, Lilianasimwe Leonidas + Show 2 more

Open Access

https://doi.org/10.3390/sym13020308

Copy DOI

Journal: Symmetry	Publication Date: Feb 12, 2021
Citations: 28	License type: CC BY 4.0

Affiliation: Wuhan University of Technology, Quaid-i-Azam University

Abstract

Ship detection and tracking is an important task in video surveillance in inland waterways. However, ships in inland navigation are faced with accidents such as collisions. For collision avoidance, we should strengthen the monitoring of navigation and the robustness of the entire system. Hence, this paper presents ship detection and tracking of ships using the improved You Only Look Once version 3 (YOLOv3) detection algorithm and Deep Simple Online and Real-time Tracking (Deep SORT) tracking algorithm. Three improvements are made to the YOLOv3 target detection algorithm. Firstly, the Kmeans clustering algorithm is used to optimize the initial value of the anchor frame to make it more suitable for ship application scenarios. Secondly, the output classifier is modified to a single Softmax classifier to suit our ship dataset which has three ship categories and mutual exclusion. Finally, Soft Non-Maximum Suppression (Soft-NMS) is introduced to solve the deficiencies of the Non-Maximum Suppression (NMS) algorithm when screening candidate frames. Results showed the mean Average Precision (mAP) and Frame Per Second (FPS) of the improved algorithm are increased by about 5% and 2, respectively, compared with the existing YOLOv3 detecting Algorithm. Then the improved YOLOv3 is applied in Deep Sort and the performance result of Deep Sort showed that, it has greater performance in complex scenes, and is robust to interference such as occlusion and camera movement, compared to state of art algorithms such as KCF, MIL, MOSSE, TLD, and Median Flow. With this improvement, it will help in the safety of inland navigation and protection from collisions and accidents.

Highlights

In recent years, with the rapid development of computer vision and artificial intelligence, the intelligent video surveillance system has been gradually applied in various fields including in inland waterways
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations
From the study of this article it can be seen that the proposed You Only Look Once version 3 (YOLOv3) algorithm compared with the YOLOv3 algorithm, the mean Average Precision (mAP), and frame per second (FPS) of the improved algorithm are increased by about 5% and 2, respectively

Summary

Introduction

With the rapid development of computer vision and artificial intelligence, the intelligent video surveillance system has been gradually applied in various fields including in inland waterways. The core of an intelligent video surveillance system is the moving object detection algorithm and tracking algorithm. There are many traditional detection methods proposed by researchers. These algorithms have three common processes, including region selection [1], feature extraction [2]. Region selection generally uses a sliding window method to traverse the image globally. This causes a lot of detection redundancy and has high time complexity

Objectives

Methods

Results

Discussion

Conclusion