Multi-Scale Safety Helmet Detection Based on SAS-YOLOv3-Tiny
In the practical application scenarios of safety helmet detection, the lightweight algorithm You Only Look Once (YOLO) v3-tiny is easy to be deployed in embedded devices because its number of parameters is small. However, its detection accuracy is relatively low, which is why it is not suitable for...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/11/8/3652 |
id |
doaj-6e5b1ec55d484a7cbd0587e6973dc486 |
---|---|
record_format |
Article |
spelling |
doaj-6e5b1ec55d484a7cbd0587e6973dc4862021-04-19T23:00:33ZengMDPI AGApplied Sciences2076-34172021-04-01113652365210.3390/app11083652Multi-Scale Safety Helmet Detection Based on SAS-YOLOv3-TinyRao Cheng0Xiaowei He1Zhonglong Zheng2Zhentao Wang3College of Mathematics and Computer Science, Zhejiang Normal University, Jinhua 321000, ChinaCollege of Mathematics and Computer Science, Zhejiang Normal University, Jinhua 321000, ChinaCollege of Mathematics and Computer Science, Zhejiang Normal University, Jinhua 321000, ChinaCollege of Mathematics and Computer Science, Zhejiang Normal University, Jinhua 321000, ChinaIn the practical application scenarios of safety helmet detection, the lightweight algorithm You Only Look Once (YOLO) v3-tiny is easy to be deployed in embedded devices because its number of parameters is small. However, its detection accuracy is relatively low, which is why it is not suitable for detecting multi-scale safety helmets. The safety helmet detection algorithm (named SAS-YOLOv3-tiny) is proposed in this paper to balance detection accuracy and model complexity. A light Sandglass-Residual (SR) module based on depthwise separable convolution and channel attention mechanism is constructed to replace the original convolution layer, and the convolution layer of stride two is used to replace the max-pooling layer for obtaining more informative features and promoting detection performance while reducing the number of parameters and computation. Instead of two-scale feature prediction, three-scale feature prediction is used here to improve the detection effect about small objects further. In addition, an improved spatial pyramid pooling (SPP) module is added to the feature extraction network to extract local and global features with rich semantic information. Complete-Intersection over Union (CIoU) loss is also introduced in this paper to improve the loss function for promoting positioning accuracy. The results on the self-built helmet dataset show that the improved algorithm is superior to the original algorithm. Compared with the original YOLOv3-tiny, the SAS-YOLOv3-tiny has significantly improved all metrics (including Precision (P), Recall (R), Mean Average Precision (mAP), F1) at the expense of only a minor speed while keeping fewer parameters and amounts of calculation. Meanwhile, the SAS-YOLOv3-tiny algorithm shows advantages in accuracy compared with lightweight object detection algorithms, and its speed is faster than the heavyweight model.https://www.mdpi.com/2076-3417/11/8/3652YOLOv3-tinyobject detectionattention mechanismdeep learningintelligent transportation |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Rao Cheng Xiaowei He Zhonglong Zheng Zhentao Wang |
spellingShingle |
Rao Cheng Xiaowei He Zhonglong Zheng Zhentao Wang Multi-Scale Safety Helmet Detection Based on SAS-YOLOv3-Tiny Applied Sciences YOLOv3-tiny object detection attention mechanism deep learning intelligent transportation |
author_facet |
Rao Cheng Xiaowei He Zhonglong Zheng Zhentao Wang |
author_sort |
Rao Cheng |
title |
Multi-Scale Safety Helmet Detection Based on SAS-YOLOv3-Tiny |
title_short |
Multi-Scale Safety Helmet Detection Based on SAS-YOLOv3-Tiny |
title_full |
Multi-Scale Safety Helmet Detection Based on SAS-YOLOv3-Tiny |
title_fullStr |
Multi-Scale Safety Helmet Detection Based on SAS-YOLOv3-Tiny |
title_full_unstemmed |
Multi-Scale Safety Helmet Detection Based on SAS-YOLOv3-Tiny |
title_sort |
multi-scale safety helmet detection based on sas-yolov3-tiny |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2021-04-01 |
description |
In the practical application scenarios of safety helmet detection, the lightweight algorithm You Only Look Once (YOLO) v3-tiny is easy to be deployed in embedded devices because its number of parameters is small. However, its detection accuracy is relatively low, which is why it is not suitable for detecting multi-scale safety helmets. The safety helmet detection algorithm (named SAS-YOLOv3-tiny) is proposed in this paper to balance detection accuracy and model complexity. A light Sandglass-Residual (SR) module based on depthwise separable convolution and channel attention mechanism is constructed to replace the original convolution layer, and the convolution layer of stride two is used to replace the max-pooling layer for obtaining more informative features and promoting detection performance while reducing the number of parameters and computation. Instead of two-scale feature prediction, three-scale feature prediction is used here to improve the detection effect about small objects further. In addition, an improved spatial pyramid pooling (SPP) module is added to the feature extraction network to extract local and global features with rich semantic information. Complete-Intersection over Union (CIoU) loss is also introduced in this paper to improve the loss function for promoting positioning accuracy. The results on the self-built helmet dataset show that the improved algorithm is superior to the original algorithm. Compared with the original YOLOv3-tiny, the SAS-YOLOv3-tiny has significantly improved all metrics (including Precision (P), Recall (R), Mean Average Precision (mAP), F1) at the expense of only a minor speed while keeping fewer parameters and amounts of calculation. Meanwhile, the SAS-YOLOv3-tiny algorithm shows advantages in accuracy compared with lightweight object detection algorithms, and its speed is faster than the heavyweight model. |
topic |
YOLOv3-tiny object detection attention mechanism deep learning intelligent transportation |
url |
https://www.mdpi.com/2076-3417/11/8/3652 |
work_keys_str_mv |
AT raocheng multiscalesafetyhelmetdetectionbasedonsasyolov3tiny AT xiaoweihe multiscalesafetyhelmetdetectionbasedonsasyolov3tiny AT zhonglongzheng multiscalesafetyhelmetdetectionbasedonsasyolov3tiny AT zhentaowang multiscalesafetyhelmetdetectionbasedonsasyolov3tiny |
_version_ |
1721519072112279552 |