Learning super-resolution and pyramidal convolution residual network for vehicle re-identification
Abstract Vehicle re-identification (Vehicle Re-ID) aims at retrieving and tracking the specified target vehicle with multiple other cameras, which can provide help in checking violations and catching fugitives, but there are still the following problems that need to be solved urgently. First, the ex...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-11-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-024-77973-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850062316123455488 |
|---|---|
| author | Mengxue Liu Weidong Min Qing Han Hongyue Xiang Meng Zhu |
| author_facet | Mengxue Liu Weidong Min Qing Han Hongyue Xiang Meng Zhu |
| author_sort | Mengxue Liu |
| collection | DOAJ |
| description | Abstract Vehicle re-identification (Vehicle Re-ID) aims at retrieving and tracking the specified target vehicle with multiple other cameras, which can provide help in checking violations and catching fugitives, but there are still the following problems that need to be solved urgently. First, the existing collected Vehicle Re-ID data often have low resolution and blur in local regions, so that the Vehicle Re-ID algorithm cannot accurately extract subtle feature representations. In addition, small features are easy to cause the disappearance of features under the operation of a large convolution kernel, which makes the model unable to capture and learn subtle features, resulting in inaccurate judgment of vehicles. In this study, we propose a Vehicle Re-ID method based on super resolution and pyramidal convolution residual network. Firstly, a super-resolution image generation network leveraging generative adversarial networks (GANs) is proposed. This network employs both content loss and adversarial loss as optimization criteria, ensuring an efficient transformation from a low-resolution image into a super-resolution counterpart, while meticulously preserving intricate high-frequency details. Then, multi levels of pyramidal convolution operations are designed to generate multi-scale features, which can capture information on different scales. Moreover, the concept of residual learning is applied between the multi levels of pyramidal convolution operations to expedite model optimization and enhance recognition capabilities. Ultimately, the double pyramidal convolutions are meticulously employed on both the original image and the super-resolution image, yielding low-noise feature representations and intricate semantic information respectively. By seamlessly fusing these two diverse sources of information, the resultant combined features exhibit heightened discrimination capabilities and significantly bolster the robustness of image features. In order to verify the effectiveness of the proposed method, extensive experiments are carried out on VeRi-776 and VehicleID datasets. The experimental results show that the method proposed in this paper effectively captures the detail information of vehicle images, accurately distinguishes the subtle differences between different vehicles of the same type, and is superior to state-of-the-art methods. |
| format | Article |
| id | doaj-art-e27dd608d8934d08a9ab6810b57959f3 |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-e27dd608d8934d08a9ab6810b57959f32025-08-20T02:49:57ZengNature PortfolioScientific Reports2045-23222024-11-0114111410.1038/s41598-024-77973-8Learning super-resolution and pyramidal convolution residual network for vehicle re-identificationMengxue Liu0Weidong Min1Qing Han2Hongyue Xiang3Meng Zhu4School of Mathematics and Computer Science, Nanchang UniversitySchool of Mathematics and Computer Science, Nanchang UniversitySchool of Mathematics and Computer Science, Nanchang UniversitySchool of Mathematics and Computer Science, Nanchang UniversitySchool of Mathematics and Computer Science, Nanchang UniversityAbstract Vehicle re-identification (Vehicle Re-ID) aims at retrieving and tracking the specified target vehicle with multiple other cameras, which can provide help in checking violations and catching fugitives, but there are still the following problems that need to be solved urgently. First, the existing collected Vehicle Re-ID data often have low resolution and blur in local regions, so that the Vehicle Re-ID algorithm cannot accurately extract subtle feature representations. In addition, small features are easy to cause the disappearance of features under the operation of a large convolution kernel, which makes the model unable to capture and learn subtle features, resulting in inaccurate judgment of vehicles. In this study, we propose a Vehicle Re-ID method based on super resolution and pyramidal convolution residual network. Firstly, a super-resolution image generation network leveraging generative adversarial networks (GANs) is proposed. This network employs both content loss and adversarial loss as optimization criteria, ensuring an efficient transformation from a low-resolution image into a super-resolution counterpart, while meticulously preserving intricate high-frequency details. Then, multi levels of pyramidal convolution operations are designed to generate multi-scale features, which can capture information on different scales. Moreover, the concept of residual learning is applied between the multi levels of pyramidal convolution operations to expedite model optimization and enhance recognition capabilities. Ultimately, the double pyramidal convolutions are meticulously employed on both the original image and the super-resolution image, yielding low-noise feature representations and intricate semantic information respectively. By seamlessly fusing these two diverse sources of information, the resultant combined features exhibit heightened discrimination capabilities and significantly bolster the robustness of image features. In order to verify the effectiveness of the proposed method, extensive experiments are carried out on VeRi-776 and VehicleID datasets. The experimental results show that the method proposed in this paper effectively captures the detail information of vehicle images, accurately distinguishes the subtle differences between different vehicles of the same type, and is superior to state-of-the-art methods.https://doi.org/10.1038/s41598-024-77973-8 |
| spellingShingle | Mengxue Liu Weidong Min Qing Han Hongyue Xiang Meng Zhu Learning super-resolution and pyramidal convolution residual network for vehicle re-identification Scientific Reports |
| title | Learning super-resolution and pyramidal convolution residual network for vehicle re-identification |
| title_full | Learning super-resolution and pyramidal convolution residual network for vehicle re-identification |
| title_fullStr | Learning super-resolution and pyramidal convolution residual network for vehicle re-identification |
| title_full_unstemmed | Learning super-resolution and pyramidal convolution residual network for vehicle re-identification |
| title_short | Learning super-resolution and pyramidal convolution residual network for vehicle re-identification |
| title_sort | learning super resolution and pyramidal convolution residual network for vehicle re identification |
| url | https://doi.org/10.1038/s41598-024-77973-8 |
| work_keys_str_mv | AT mengxueliu learningsuperresolutionandpyramidalconvolutionresidualnetworkforvehiclereidentification AT weidongmin learningsuperresolutionandpyramidalconvolutionresidualnetworkforvehiclereidentification AT qinghan learningsuperresolutionandpyramidalconvolutionresidualnetworkforvehiclereidentification AT hongyuexiang learningsuperresolutionandpyramidalconvolutionresidualnetworkforvehiclereidentification AT mengzhu learningsuperresolutionandpyramidalconvolutionresidualnetworkforvehiclereidentification |