Infrared Sensation-Based Salient Targets Enhancement Methods in Low-Visibility Scenes
Thermal imaging is an important technology in low-visibility environments, and due to the blurred edges and low contrast of infrared images, enhancement processing is of vital importance. However, to some extent, the existing enhancement algorithms based on pixel-level information ignore the salient...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/15/5835 |
| _version_ | 1797440617544941568 |
|---|---|
| author | Hongjun Tan Dongxiu Ou Lei Zhang Guochen Shen Xinghua Li Yuqing Ji |
| author_facet | Hongjun Tan Dongxiu Ou Lei Zhang Guochen Shen Xinghua Li Yuqing Ji |
| author_sort | Hongjun Tan |
| collection | DOAJ |
| description | Thermal imaging is an important technology in low-visibility environments, and due to the blurred edges and low contrast of infrared images, enhancement processing is of vital importance. However, to some extent, the existing enhancement algorithms based on pixel-level information ignore the salient feature of targets, the temperature which effectively separates the targets by their color. Therefore, based on the temperature and pixel features of infrared images, first, a threshold denoising model based on wavelet transformation with bilateral filtering (WTBF) was proposed. Second, our group proposed a salient components enhancement method based on a multi-scale retinex algorithm combined with frequency-tuned salient region extraction (MSRFT). Third, the image contrast and noise distribution were improved by using salient features of orientation, color, and illuminance of night or snow targets. Finally, the accuracy of the bounding box of enhanced images was tested by the pre-trained and improved object detector. The results show that the improved method can reach an accuracy of 90% of snow targets, and the average precision of car and people categories improved in four low-visibility scenes, which demonstrates the high accuracy and adaptability of the proposed methods of great significance for target detection, trajectory tracking, and danger warning of automobile driving. |
| first_indexed | 2024-03-09T12:10:49Z |
| format | Article |
| id | doaj.art-84705c1acbd3470181c3d5cf2153483a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T12:10:49Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-84705c1acbd3470181c3d5cf2153483a2023-11-30T22:52:10ZengMDPI AGSensors1424-82202022-08-012215583510.3390/s22155835Infrared Sensation-Based Salient Targets Enhancement Methods in Low-Visibility ScenesHongjun Tan0Dongxiu Ou1Lei Zhang2Guochen Shen3Xinghua Li4Yuqing Ji5School of Transportation Engineering, Tongji University, No. 4800 Caoan Road, Shanghai 201804, ChinaSchool of Transportation Engineering, Tongji University, No. 4800 Caoan Road, Shanghai 201804, ChinaSchool of Transportation Engineering, Tongji University, No. 4800 Caoan Road, Shanghai 201804, ChinaSchool of Transportation Engineering, Tongji University, No. 4800 Caoan Road, Shanghai 201804, ChinaSchool of Transportation Engineering, Tongji University, No. 4800 Caoan Road, Shanghai 201804, ChinaSchool of Transportation Engineering, Tongji University, No. 4800 Caoan Road, Shanghai 201804, ChinaThermal imaging is an important technology in low-visibility environments, and due to the blurred edges and low contrast of infrared images, enhancement processing is of vital importance. However, to some extent, the existing enhancement algorithms based on pixel-level information ignore the salient feature of targets, the temperature which effectively separates the targets by their color. Therefore, based on the temperature and pixel features of infrared images, first, a threshold denoising model based on wavelet transformation with bilateral filtering (WTBF) was proposed. Second, our group proposed a salient components enhancement method based on a multi-scale retinex algorithm combined with frequency-tuned salient region extraction (MSRFT). Third, the image contrast and noise distribution were improved by using salient features of orientation, color, and illuminance of night or snow targets. Finally, the accuracy of the bounding box of enhanced images was tested by the pre-trained and improved object detector. The results show that the improved method can reach an accuracy of 90% of snow targets, and the average precision of car and people categories improved in four low-visibility scenes, which demonstrates the high accuracy and adaptability of the proposed methods of great significance for target detection, trajectory tracking, and danger warning of automobile driving.https://www.mdpi.com/1424-8220/22/15/5835infrared imagewavelet transformmulti-scale retinex algorithmsalient regiondeep learningtarget detection |
| spellingShingle | Hongjun Tan Dongxiu Ou Lei Zhang Guochen Shen Xinghua Li Yuqing Ji Infrared Sensation-Based Salient Targets Enhancement Methods in Low-Visibility Scenes Sensors infrared image wavelet transform multi-scale retinex algorithm salient region deep learning target detection |
| title | Infrared Sensation-Based Salient Targets Enhancement Methods in Low-Visibility Scenes |
| title_full | Infrared Sensation-Based Salient Targets Enhancement Methods in Low-Visibility Scenes |
| title_fullStr | Infrared Sensation-Based Salient Targets Enhancement Methods in Low-Visibility Scenes |
| title_full_unstemmed | Infrared Sensation-Based Salient Targets Enhancement Methods in Low-Visibility Scenes |
| title_short | Infrared Sensation-Based Salient Targets Enhancement Methods in Low-Visibility Scenes |
| title_sort | infrared sensation based salient targets enhancement methods in low visibility scenes |
| topic | infrared image wavelet transform multi-scale retinex algorithm salient region deep learning target detection |
| url | https://www.mdpi.com/1424-8220/22/15/5835 |
| work_keys_str_mv | AT hongjuntan infraredsensationbasedsalienttargetsenhancementmethodsinlowvisibilityscenes AT dongxiuou infraredsensationbasedsalienttargetsenhancementmethodsinlowvisibilityscenes AT leizhang infraredsensationbasedsalienttargetsenhancementmethodsinlowvisibilityscenes AT guochenshen infraredsensationbasedsalienttargetsenhancementmethodsinlowvisibilityscenes AT xinghuali infraredsensationbasedsalienttargetsenhancementmethodsinlowvisibilityscenes AT yuqingji infraredsensationbasedsalienttargetsenhancementmethodsinlowvisibilityscenes |