Object detection in smart indoor shopping using an enhanced YOLOv8n algorithm
Abstract This paper introduces an enhanced object detection algorithm tailored for indoor shopping applications, a critical component of smart cities and smart shopping ecosystems. The proposed method builds on the YOLOv8n algorithm by integrating a ParNetAttention module into the backbone's C2...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-12-01
|
| Series: | IET Image Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ipr2.13284 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846121451328897024 |
|---|---|
| author | Yawen Zhao Defu Yang Sheng Cao Bingyu Cai Maryamah Maryamah Mahmud Iwan Solihin |
| author_facet | Yawen Zhao Defu Yang Sheng Cao Bingyu Cai Maryamah Maryamah Mahmud Iwan Solihin |
| author_sort | Yawen Zhao |
| collection | DOAJ |
| description | Abstract This paper introduces an enhanced object detection algorithm tailored for indoor shopping applications, a critical component of smart cities and smart shopping ecosystems. The proposed method builds on the YOLOv8n algorithm by integrating a ParNetAttention module into the backbone's C2f module, creating the novel C2f‐ParNet structure. This innovation enhances feature extraction, crucial for detecting intricate details in complex indoor environments. Additionally, the channel‐wise attention‐recurrent feature extraction (CARAFE) module is incorporated into the neck network, improving target feature fusion and focus on objects of interest, thereby boosting detection accuracy. To optimize training efficiency, the model employs the Wise Intersection over Union (WIoUv3) as its regression loss function, accelerating data convergence and improving performance. Experimental results demonstrate the enhanced YOLOv8n achieves a mean average precision (mAP) at 50% threshold (mAP@50) of 61.2%, a 1.2 percentage point improvement over the baseline. The fully optimized algorithm achieves an mAP@50 of 65.9% and an F1 score of 63.5%, outperforming both the original YOLOv8n and existing algorithms. Furthermore, with a frame rate of 106.5 FPS and computational complexity of just 12.9 GFLOPs (Giga Floating‐Point Operations per Second), this approach balances high performance with lightweight efficiency, making it ideal for real‐time applications in smart retail environments. |
| format | Article |
| id | doaj-art-aae32b69f3ca48f19c733f271ccbb419 |
| institution | Kabale University |
| issn | 1751-9659 1751-9667 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj-art-aae32b69f3ca48f19c733f271ccbb4192024-12-16T04:00:31ZengWileyIET Image Processing1751-96591751-96672024-12-0118144745475910.1049/ipr2.13284Object detection in smart indoor shopping using an enhanced YOLOv8n algorithmYawen Zhao0Defu Yang1Sheng Cao2Bingyu Cai3Maryamah Maryamah4Mahmud Iwan Solihin5Faculty of Engineering Technology and Built Environment UCSI University Kuala Lumpur MalaysiaFaculty of Engineering Technology and Built Environment UCSI University Kuala Lumpur MalaysiaFaculty of Engineering Technology and Built Environment UCSI University Kuala Lumpur MalaysiaFaculty of Engineering Technology and Built Environment UCSI University Kuala Lumpur MalaysiaFaculty of Advanced Technology and Multidiscipline Universitas Airlangga Surabaya IndonesiaFaculty of Engineering Technology and Built Environment UCSI University Kuala Lumpur MalaysiaAbstract This paper introduces an enhanced object detection algorithm tailored for indoor shopping applications, a critical component of smart cities and smart shopping ecosystems. The proposed method builds on the YOLOv8n algorithm by integrating a ParNetAttention module into the backbone's C2f module, creating the novel C2f‐ParNet structure. This innovation enhances feature extraction, crucial for detecting intricate details in complex indoor environments. Additionally, the channel‐wise attention‐recurrent feature extraction (CARAFE) module is incorporated into the neck network, improving target feature fusion and focus on objects of interest, thereby boosting detection accuracy. To optimize training efficiency, the model employs the Wise Intersection over Union (WIoUv3) as its regression loss function, accelerating data convergence and improving performance. Experimental results demonstrate the enhanced YOLOv8n achieves a mean average precision (mAP) at 50% threshold (mAP@50) of 61.2%, a 1.2 percentage point improvement over the baseline. The fully optimized algorithm achieves an mAP@50 of 65.9% and an F1 score of 63.5%, outperforming both the original YOLOv8n and existing algorithms. Furthermore, with a frame rate of 106.5 FPS and computational complexity of just 12.9 GFLOPs (Giga Floating‐Point Operations per Second), this approach balances high performance with lightweight efficiency, making it ideal for real‐time applications in smart retail environments.https://doi.org/10.1049/ipr2.13284computer visionimage recognitionlearning (artificial intelligence)object detectionsupervised learning |
| spellingShingle | Yawen Zhao Defu Yang Sheng Cao Bingyu Cai Maryamah Maryamah Mahmud Iwan Solihin Object detection in smart indoor shopping using an enhanced YOLOv8n algorithm IET Image Processing computer vision image recognition learning (artificial intelligence) object detection supervised learning |
| title | Object detection in smart indoor shopping using an enhanced YOLOv8n algorithm |
| title_full | Object detection in smart indoor shopping using an enhanced YOLOv8n algorithm |
| title_fullStr | Object detection in smart indoor shopping using an enhanced YOLOv8n algorithm |
| title_full_unstemmed | Object detection in smart indoor shopping using an enhanced YOLOv8n algorithm |
| title_short | Object detection in smart indoor shopping using an enhanced YOLOv8n algorithm |
| title_sort | object detection in smart indoor shopping using an enhanced yolov8n algorithm |
| topic | computer vision image recognition learning (artificial intelligence) object detection supervised learning |
| url | https://doi.org/10.1049/ipr2.13284 |
| work_keys_str_mv | AT yawenzhao objectdetectioninsmartindoorshoppingusinganenhancedyolov8nalgorithm AT defuyang objectdetectioninsmartindoorshoppingusinganenhancedyolov8nalgorithm AT shengcao objectdetectioninsmartindoorshoppingusinganenhancedyolov8nalgorithm AT bingyucai objectdetectioninsmartindoorshoppingusinganenhancedyolov8nalgorithm AT maryamahmaryamah objectdetectioninsmartindoorshoppingusinganenhancedyolov8nalgorithm AT mahmudiwansolihin objectdetectioninsmartindoorshoppingusinganenhancedyolov8nalgorithm |