Instance Segmentation Algorithm of Urban Street Scene Based on Data Augmentation and Feature Enhancement

Urban street scene segmentation is a key technology in the field of intelligent transportation. For the objective factors in the urban street scene environment such as occlusion, small objects, etc. , a DF-SOLO(Data Augmentation and Feature Enhancement SOLO) instance segmentation algorithm of urb...

Full description

Saved in:
Bibliographic Details
Main Authors: LI Chengyan, CHE Zixuan, ZHENG Qisen
Format: Article
Language:zho
Published: Harbin University of Science and Technology Publications 2024-04-01
Series:Journal of Harbin University of Science and Technology
Subjects:
Online Access:https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2309
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849320970426253312
author LI Chengyan
CHE Zixuan
ZHENG Qisen
author_facet LI Chengyan
CHE Zixuan
ZHENG Qisen
author_sort LI Chengyan
collection DOAJ
description Urban street scene segmentation is a key technology in the field of intelligent transportation. For the objective factors in the urban street scene environment such as occlusion, small objects, etc. , a DF-SOLO(Data Augmentation and Feature Enhancement SOLO) instance segmentation algorithm of urban street scene based on data augmentation and feature enhancement is proposed. Aiming at the occlusion problem, the urban street view image is enhanced by the asymmetric self-encoder-decoder architecture. Compared with the traditional method, the processed image is closer to the real source data distribution. Aiming at the problem of small target segmentation in urban street scenes, the idea of feature weighting and feature fusion is introduced. The feature weighting module can assign different weights according to the importance of the features in the feature processing process, so as to improve the utilization rate of important features; the feature fusion module Multi-scale feature fusion is performed from a finer-grained perspective to solve the scale-sensitive problem and improve the descriptiveness of semantic features. Experiments on the Cityscapes dataset show that the proposed instance segmentation algorithm can improve the mAP value by 2. 1% and 2% respectively compared with the single-stage SOLO algorithm and the two-stage Mask R-CNN algorithm while ensuring real-time performance. Improved segmentation of small objects and occluded objects.
format Article
id doaj-art-e63fbaff738c4f6389b0bdf0b4b2ac57
institution Kabale University
issn 1007-2683
language zho
publishDate 2024-04-01
publisher Harbin University of Science and Technology Publications
record_format Article
series Journal of Harbin University of Science and Technology
spelling doaj-art-e63fbaff738c4f6389b0bdf0b4b2ac572025-08-20T03:49:54ZzhoHarbin University of Science and Technology PublicationsJournal of Harbin University of Science and Technology1007-26832024-04-012902253210.15938/j.jhust.2024.02.004Instance Segmentation Algorithm of Urban Street Scene Based on Data Augmentation and Feature EnhancementLI Chengyan0CHE Zixuan1ZHENG Qisen2School of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080 , ChinaSchool of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080 , ChinaSchool of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080 , China Urban street scene segmentation is a key technology in the field of intelligent transportation. For the objective factors in the urban street scene environment such as occlusion, small objects, etc. , a DF-SOLO(Data Augmentation and Feature Enhancement SOLO) instance segmentation algorithm of urban street scene based on data augmentation and feature enhancement is proposed. Aiming at the occlusion problem, the urban street view image is enhanced by the asymmetric self-encoder-decoder architecture. Compared with the traditional method, the processed image is closer to the real source data distribution. Aiming at the problem of small target segmentation in urban street scenes, the idea of feature weighting and feature fusion is introduced. The feature weighting module can assign different weights according to the importance of the features in the feature processing process, so as to improve the utilization rate of important features; the feature fusion module Multi-scale feature fusion is performed from a finer-grained perspective to solve the scale-sensitive problem and improve the descriptiveness of semantic features. Experiments on the Cityscapes dataset show that the proposed instance segmentation algorithm can improve the mAP value by 2. 1% and 2% respectively compared with the single-stage SOLO algorithm and the two-stage Mask R-CNN algorithm while ensuring real-time performance. Improved segmentation of small objects and occluded objects.https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2309instance segmentationsolo algorithmfeature extractiondata augmentationurban street scene
spellingShingle LI Chengyan
CHE Zixuan
ZHENG Qisen
Instance Segmentation Algorithm of Urban Street Scene Based on Data Augmentation and Feature Enhancement
Journal of Harbin University of Science and Technology
instance segmentation
solo algorithm
feature extraction
data augmentation
urban street scene
title Instance Segmentation Algorithm of Urban Street Scene Based on Data Augmentation and Feature Enhancement
title_full Instance Segmentation Algorithm of Urban Street Scene Based on Data Augmentation and Feature Enhancement
title_fullStr Instance Segmentation Algorithm of Urban Street Scene Based on Data Augmentation and Feature Enhancement
title_full_unstemmed Instance Segmentation Algorithm of Urban Street Scene Based on Data Augmentation and Feature Enhancement
title_short Instance Segmentation Algorithm of Urban Street Scene Based on Data Augmentation and Feature Enhancement
title_sort instance segmentation algorithm of urban street scene based on data augmentation and feature enhancement
topic instance segmentation
solo algorithm
feature extraction
data augmentation
urban street scene
url https://hlgxb.hrbust.edu.cn/#/digest?ArticleID=2309
work_keys_str_mv AT lichengyan instancesegmentationalgorithmofurbanstreetscenebasedondataaugmentationandfeatureenhancement
AT chezixuan instancesegmentationalgorithmofurbanstreetscenebasedondataaugmentationandfeatureenhancement
AT zhengqisen instancesegmentationalgorithmofurbanstreetscenebasedondataaugmentationandfeatureenhancement