Methods of Introducing Reference Objects into Images Obtained Using Hydroacoustic Systems of Computer Vision

Aleksandr Saenko,Andrey Mironov, Ekaterina Fomina

2024 International Russian Automation Conference (RusAutoCon)（2024）

Cited 0|Views1

Abstract

The purpose of the presented work is the development of neural networks to solve the problem of introducing an object with given geometric parameters in the images obtained using side (sector) scan sonars (SSS). As part of the study, there was conducted an experimental assessment of the effectiveness of applying the proposed comprehensive algorithm for the introduction of objects that puts into effect the use of the “Copy and Paste” method together with the neural network method of “Deep Painterly Harmonization”. In the course of the study, methods of visual subjective qualitative assessment and quantitative analysis were used to determine the effectiveness of the result of introducing of objects in the image. The evaluation criteria were the realism of the images obtained and the retention of the geometric parameters of the introduced reference objects. The results obtained allow for making a conclusion on the advantages and disadvantages of applying the proposed comprehensive algorithm with the use of each of the considered methods to solve the problem of introducing objects into sonar images. In the conclusion, on the basis of the conducted analysis, recommendations are proposed for selecting the most suitable method for introducing objects with specified parameters to the image of the side scan locator, taking into account specific needs and tasks.

Translated text

Key words

introduction of images,artificial neural networks,hydroacoustic systems of computer vision

求助PDF

上传PDF

Bibtex

AI Read Science

AI Summary

AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.

Example

Background

Key content

Introduction

Methods

Results

Related work

Fund

Key content

Pretraining has recently greatly promoted the development of natural language processing (NLP)
We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance

Upload PDF to Generate Summary

Must-Reading Tree

Example

Generate MRT to find the research sequence of this paper

Data Disclaimer

The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn

Chat Paper

【要点】：本文旨在开发神经网络以将具有给定几何参数的参考对象引入侧扫声纳（SSS）图像中，并通过实验评估了结合“复制和粘贴”方法与“深度绘画调和”神经网络方法的综合算法效果。

【方法】：研究采用了结合“复制和粘贴”方法与“深度绘画调和”神经网络的综合算法，以及视觉主观定性评估和定量分析的方法来评估引入对象的效果。

【实验】：通过实验评估了综合算法在引入对象到声纳图像中的有效性，使用了视觉主观定性和定量分析方法，具体结果未在摘要中列出，但结论是基于对引入对象图像的真实性和几何参数保留程度上的评估。文中未提及具体使用的数据集名称。