Small Object Detection in Traffic Scenes Based on Attention Feature Fusion
There are many small objects in traffic scenes, but due to their low resolution and limited information, their detection is still a challenge. Small object detection is very important for the understanding of traffic scene environments. To improve the detection accuracy of small objects in traffic s...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/9/3031 |
id |
doaj-47fc263e251145f0972b1abcfe06c0c1 |
---|---|
record_format |
Article |
spelling |
doaj-47fc263e251145f0972b1abcfe06c0c12021-04-26T23:01:31ZengMDPI AGSensors1424-82202021-04-01213031303110.3390/s21093031Small Object Detection in Traffic Scenes Based on Attention Feature FusionJing Lian0Yuhang Yin1Linhui Li2Zhenghao Wang3Yafu Zhou4Faculty of Vehicle Engineering and Mechanics, School of Automotive Engineering, Dalian University of Technology, Dalian 116024, ChinaFaculty of Vehicle Engineering and Mechanics, School of Automotive Engineering, Dalian University of Technology, Dalian 116024, ChinaFaculty of Vehicle Engineering and Mechanics, School of Automotive Engineering, Dalian University of Technology, Dalian 116024, ChinaFaculty of Vehicle Engineering and Mechanics, School of Automotive Engineering, Dalian University of Technology, Dalian 116024, ChinaFaculty of Vehicle Engineering and Mechanics, School of Automotive Engineering, Dalian University of Technology, Dalian 116024, ChinaThere are many small objects in traffic scenes, but due to their low resolution and limited information, their detection is still a challenge. Small object detection is very important for the understanding of traffic scene environments. To improve the detection accuracy of small objects in traffic scenes, we propose a small object detection method in traffic scenes based on attention feature fusion. First, a multi-scale channel attention block (MS-CAB) is designed, which uses local and global scales to aggregate the effective information of the feature maps. Based on this block, an attention feature fusion block (AFFB) is proposed, which can better integrate contextual information from different layers. Finally, the AFFB is used to replace the linear fusion module in the object detection network and obtain the final network structure. The experimental results show that, compared to the benchmark model YOLOv5s, this method has achieved a higher mean Average Precison (mAP) under the premise of ensuring real-time performance. It increases the mAP of all objects by 0.9 percentage points on the validation set of the traffic scene dataset BDD100K, and at the same time, increases the mAP of small objects by 3.5%.https://www.mdpi.com/1424-8220/21/9/3031traffic scenesobject detectionmulti-scale channel attentionattention feature fusion |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jing Lian Yuhang Yin Linhui Li Zhenghao Wang Yafu Zhou |
spellingShingle |
Jing Lian Yuhang Yin Linhui Li Zhenghao Wang Yafu Zhou Small Object Detection in Traffic Scenes Based on Attention Feature Fusion Sensors traffic scenes object detection multi-scale channel attention attention feature fusion |
author_facet |
Jing Lian Yuhang Yin Linhui Li Zhenghao Wang Yafu Zhou |
author_sort |
Jing Lian |
title |
Small Object Detection in Traffic Scenes Based on Attention Feature Fusion |
title_short |
Small Object Detection in Traffic Scenes Based on Attention Feature Fusion |
title_full |
Small Object Detection in Traffic Scenes Based on Attention Feature Fusion |
title_fullStr |
Small Object Detection in Traffic Scenes Based on Attention Feature Fusion |
title_full_unstemmed |
Small Object Detection in Traffic Scenes Based on Attention Feature Fusion |
title_sort |
small object detection in traffic scenes based on attention feature fusion |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2021-04-01 |
description |
There are many small objects in traffic scenes, but due to their low resolution and limited information, their detection is still a challenge. Small object detection is very important for the understanding of traffic scene environments. To improve the detection accuracy of small objects in traffic scenes, we propose a small object detection method in traffic scenes based on attention feature fusion. First, a multi-scale channel attention block (MS-CAB) is designed, which uses local and global scales to aggregate the effective information of the feature maps. Based on this block, an attention feature fusion block (AFFB) is proposed, which can better integrate contextual information from different layers. Finally, the AFFB is used to replace the linear fusion module in the object detection network and obtain the final network structure. The experimental results show that, compared to the benchmark model YOLOv5s, this method has achieved a higher mean Average Precison (mAP) under the premise of ensuring real-time performance. It increases the mAP of all objects by 0.9 percentage points on the validation set of the traffic scene dataset BDD100K, and at the same time, increases the mAP of small objects by 3.5%. |
topic |
traffic scenes object detection multi-scale channel attention attention feature fusion |
url |
https://www.mdpi.com/1424-8220/21/9/3031 |
work_keys_str_mv |
AT jinglian smallobjectdetectionintrafficscenesbasedonattentionfeaturefusion AT yuhangyin smallobjectdetectionintrafficscenesbasedonattentionfeaturefusion AT linhuili smallobjectdetectionintrafficscenesbasedonattentionfeaturefusion AT zhenghaowang smallobjectdetectionintrafficscenesbasedonattentionfeaturefusion AT yafuzhou smallobjectdetectionintrafficscenesbasedonattentionfeaturefusion |
_version_ |
1721507283275350016 |