Using convolutional neural networks for image semantic segmentation and object detection

Convolutional neural networks are widely used for feature extraction in the fields of object detection and image segmentation. However, traditional CNN models often struggle to ensure accuracy in high noise environments. A study proposes an enhanced CNN model to improve its ability to recognize targ...

Full description

Saved in:
Bibliographic Details
Main Authors: Shuangmei Li, Chengning Huang
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Systems and Soft Computing
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772941924001017
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850249173391114240
author Shuangmei Li
Chengning Huang
author_facet Shuangmei Li
Chengning Huang
author_sort Shuangmei Li
collection DOAJ
description Convolutional neural networks are widely used for feature extraction in the fields of object detection and image segmentation. However, traditional CNN models often struggle to ensure accuracy in high noise environments. A study proposes an enhanced CNN model to improve its ability to recognize targets of different scales. This model combines multi-scale perceptual aggregation and feature alignment (MPAFA) mechanisms. This new method effectively combines low-level and high-level features, which helps to better identify objects of different sizes. The experimental results show that the proposed model achieved a segmentation accuracy of 99.6 % on the Cityscapes dataset, and maintained an accuracy of 97.3 % even with increased noise. Further experiments have shown that the model outperforms existing methods in terms of accuracy and recall. The experimental results show that the model exhibits excellent performance in object detection and segmentation tasks. This study provides a more effective strategy for processing complex images by optimizing network structure and enhancing feature fusion.
format Article
id doaj-art-3e9bd92bdb8c48db8c588f91666b2105
institution OA Journals
issn 2772-9419
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Systems and Soft Computing
spelling doaj-art-3e9bd92bdb8c48db8c588f91666b21052025-08-20T01:58:33ZengElsevierSystems and Soft Computing2772-94192024-12-01620017210.1016/j.sasc.2024.200172Using convolutional neural networks for image semantic segmentation and object detectionShuangmei Li0Chengning Huang1Corresponding author.; School of Computer and Communication Engineering, Nanjing Tech University Pujiang Institute, Nanjing, 211200, PR ChinaSchool of Computer and Communication Engineering, Nanjing Tech University Pujiang Institute, Nanjing, 211200, PR ChinaConvolutional neural networks are widely used for feature extraction in the fields of object detection and image segmentation. However, traditional CNN models often struggle to ensure accuracy in high noise environments. A study proposes an enhanced CNN model to improve its ability to recognize targets of different scales. This model combines multi-scale perceptual aggregation and feature alignment (MPAFA) mechanisms. This new method effectively combines low-level and high-level features, which helps to better identify objects of different sizes. The experimental results show that the proposed model achieved a segmentation accuracy of 99.6 % on the Cityscapes dataset, and maintained an accuracy of 97.3 % even with increased noise. Further experiments have shown that the model outperforms existing methods in terms of accuracy and recall. The experimental results show that the model exhibits excellent performance in object detection and segmentation tasks. This study provides a more effective strategy for processing complex images by optimizing network structure and enhancing feature fusion.http://www.sciencedirect.com/science/article/pii/S2772941924001017Convolutional neural networkFeature alignmentSpatial attentionSemantic segmentationObject detection
spellingShingle Shuangmei Li
Chengning Huang
Using convolutional neural networks for image semantic segmentation and object detection
Systems and Soft Computing
Convolutional neural network
Feature alignment
Spatial attention
Semantic segmentation
Object detection
title Using convolutional neural networks for image semantic segmentation and object detection
title_full Using convolutional neural networks for image semantic segmentation and object detection
title_fullStr Using convolutional neural networks for image semantic segmentation and object detection
title_full_unstemmed Using convolutional neural networks for image semantic segmentation and object detection
title_short Using convolutional neural networks for image semantic segmentation and object detection
title_sort using convolutional neural networks for image semantic segmentation and object detection
topic Convolutional neural network
Feature alignment
Spatial attention
Semantic segmentation
Object detection
url http://www.sciencedirect.com/science/article/pii/S2772941924001017
work_keys_str_mv AT shuangmeili usingconvolutionalneuralnetworksforimagesemanticsegmentationandobjectdetection
AT chengninghuang usingconvolutionalneuralnetworksforimagesemanticsegmentationandobjectdetection