Water surface object detection using panoramic vision based on improved single-shot multibox detector

Aofeng Li,Xufang Zhu,Shuo He,Jiawei Xia

doi:10.1186/s13634-021-00831-6

Abstract

In view of the deficiencies in traditional visual water surface object detection, such as the existence of non-detection zones, failure to acquire global information, and deficiencies in a single-shot multibox detector (SSD) object detection algorithm such as remote detection and low detection precision of small objects, this study proposes a water surface object detection algorithm from panoramic vision based on an improved SSD. We reconstruct the backbone network for the SSD algorithm, replace VVG16 with a ResNet-50 network, and add five layers of feature extraction. More abundant semantic information of the shallow feature graph is obtained through a feature pyramid network structure with deconvolution. An experiment is conducted by building a water surface object dataset. Results showed the mean Average Precision (mAP) of the improved algorithm are increased by 4.03%, compared with the existing SSD detecting Algorithm. Improved algorithm can effectively improve the overall detection precision of water surface objects and enhance the detection effect of remote objects.

Highlights

In recent years, the status of water transportation has been continuously improved in the field of transportation
With the continuous development of deep learning technology, object detection algorithms based on convolutional neural networks (CNN) have been proposed one after another, CNN is a kind of deep feedforward neural network, which has many
Detection speed has units of frames per second (FPS) as the evaluation index, i.e., the number of images the model can detect per second

Summary

Introduction

The status of water transportation has been continuously improved in the field of transportation. As the main tool of water transportation, ships have received extensive attention from all walks of life for their safe, green and efficient operations. The development of emerging technologies such as artificial intelligence, the Internet, and big data has set off a research boom in smart ships [1]. As an important component of intelligent ship environment perception, surface object detection technology is the prerequisite and foundation for unmanned and intelligent ships, and has gradually become a new hot spot in the current intelligent ship research field. With the continuous development of deep learning technology, object detection algorithms based on convolutional neural networks (CNN) have been proposed one after another, CNN is a kind of deep feedforward neural network, which has many The automatic detection of surface objects is of great significance for the distribution of surface vessels, effective management of ship parking, identification of information on passing vessels, and realization of automatic collision avoidance.

Methods

Results

Conclusion