Enhanced lightweight infrared object detection algorithm for assistive navigation in visually impaired individuals
Abstract This study introduces an advanced infrared scene detection algorithm, enhancing the YOLOv8 model for aiding visually impaired individuals in navigation. The focus is on the neck network, integrating attention scale sequences to boost multi‐level perception, particularly for small object det...
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/ipr2.13233 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850255726584266752 |
|---|---|
| author | Zhimin Bai Yang Yang Jian Wang Zhengyang Li Jiajun Wang Chunxin Liu |
| author_facet | Zhimin Bai Yang Yang Jian Wang Zhengyang Li Jiajun Wang Chunxin Liu |
| author_sort | Zhimin Bai |
| collection | DOAJ |
| description | Abstract This study introduces an advanced infrared scene detection algorithm, enhancing the YOLOv8 model for aiding visually impaired individuals in navigation. The focus is on the neck network, integrating attention scale sequences to boost multi‐level perception, particularly for small object detection. This is achieved by adding upsampling and downsampling in the P2 module. Additionally, the CIoU loss function is refined with Inner‐SIoU, elevating bounding box detection precision. A distinctive feature of the approach is its monocular distance and velocity measurement integration, which operates independently of external devices, providing direct navigation support for visually impaired people. Further, the enhanced YOLOv8 is adapted for mobile use, employing pruning and lightweight methods, which substantially enhance its practicality. The experimental results on the FLIR and WOTR datasets demonstrate that, compared to the original YOLOv8n, the improved algorithm has achieved a 2.1% and 3.2% increase in mAP0.5, respectively. Furthermore, the mAP0.5--0.95 has seen a 2.2% and 3.8% improvement. Concurrently, the model size has been reduced by 55% and 60%, and the number of parameters has decreased by 60% and 67%. Compared to other assistive travel methods for visually impaired individuals, our work demonstrates superior practicality. |
| format | Article |
| id | doaj-art-c850e0b0e32946d1ae760ba3c2fdf41b |
| institution | OA Journals |
| issn | 1751-9659 1751-9667 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Image Processing |
| spelling | doaj-art-c850e0b0e32946d1ae760ba3c2fdf41b2025-08-20T01:56:48ZengWileyIET Image Processing1751-96591751-96672024-12-0118144824484210.1049/ipr2.13233Enhanced lightweight infrared object detection algorithm for assistive navigation in visually impaired individualsZhimin Bai0Yang Yang1Jian Wang2Zhengyang Li3Jiajun Wang4Chunxin Liu5School of Computer ScienceNorth China Institute of Aerospace EngineeringLangfang ChinaResearch Laboratory of Systems Software EngineeringBeijing Aerospace Automatic Control InstituteBeijing ChinaSchool of Computer ScienceNorth China Institute of Aerospace EngineeringLangfang ChinaSchool of Computer ScienceNorth China Institute of Aerospace EngineeringLangfang ChinaSchool of Computer ScienceNorth China Institute of Aerospace EngineeringLangfang ChinaSchool of Computer ScienceNorth China Institute of Aerospace EngineeringLangfang ChinaAbstract This study introduces an advanced infrared scene detection algorithm, enhancing the YOLOv8 model for aiding visually impaired individuals in navigation. The focus is on the neck network, integrating attention scale sequences to boost multi‐level perception, particularly for small object detection. This is achieved by adding upsampling and downsampling in the P2 module. Additionally, the CIoU loss function is refined with Inner‐SIoU, elevating bounding box detection precision. A distinctive feature of the approach is its monocular distance and velocity measurement integration, which operates independently of external devices, providing direct navigation support for visually impaired people. Further, the enhanced YOLOv8 is adapted for mobile use, employing pruning and lightweight methods, which substantially enhance its practicality. The experimental results on the FLIR and WOTR datasets demonstrate that, compared to the original YOLOv8n, the improved algorithm has achieved a 2.1% and 3.2% increase in mAP0.5, respectively. Furthermore, the mAP0.5--0.95 has seen a 2.2% and 3.8% improvement. Concurrently, the model size has been reduced by 55% and 60%, and the number of parameters has decreased by 60% and 67%. Compared to other assistive travel methods for visually impaired individuals, our work demonstrates superior practicality.https://doi.org/10.1049/ipr2.13233computer visioninfrared imagingneural net architectureobject detection |
| spellingShingle | Zhimin Bai Yang Yang Jian Wang Zhengyang Li Jiajun Wang Chunxin Liu Enhanced lightweight infrared object detection algorithm for assistive navigation in visually impaired individuals IET Image Processing computer vision infrared imaging neural net architecture object detection |
| title | Enhanced lightweight infrared object detection algorithm for assistive navigation in visually impaired individuals |
| title_full | Enhanced lightweight infrared object detection algorithm for assistive navigation in visually impaired individuals |
| title_fullStr | Enhanced lightweight infrared object detection algorithm for assistive navigation in visually impaired individuals |
| title_full_unstemmed | Enhanced lightweight infrared object detection algorithm for assistive navigation in visually impaired individuals |
| title_short | Enhanced lightweight infrared object detection algorithm for assistive navigation in visually impaired individuals |
| title_sort | enhanced lightweight infrared object detection algorithm for assistive navigation in visually impaired individuals |
| topic | computer vision infrared imaging neural net architecture object detection |
| url | https://doi.org/10.1049/ipr2.13233 |
| work_keys_str_mv | AT zhiminbai enhancedlightweightinfraredobjectdetectionalgorithmforassistivenavigationinvisuallyimpairedindividuals AT yangyang enhancedlightweightinfraredobjectdetectionalgorithmforassistivenavigationinvisuallyimpairedindividuals AT jianwang enhancedlightweightinfraredobjectdetectionalgorithmforassistivenavigationinvisuallyimpairedindividuals AT zhengyangli enhancedlightweightinfraredobjectdetectionalgorithmforassistivenavigationinvisuallyimpairedindividuals AT jiajunwang enhancedlightweightinfraredobjectdetectionalgorithmforassistivenavigationinvisuallyimpairedindividuals AT chunxinliu enhancedlightweightinfraredobjectdetectionalgorithmforassistivenavigationinvisuallyimpairedindividuals |