WFSCA-YOLO: Robust Object Detection for Terrestrial Optical Sensing Under Atmospheric Degradation via a Wavelet-Driven Frequency–Spatial Co-Awareness Framework.
Saved in:
| Title: | WFSCA-YOLO: Robust Object Detection for Terrestrial Optical Sensing Under Atmospheric Degradation via a Wavelet-Driven Frequency–Spatial Co-Awareness Framework. |
|---|---|
| Authors: | Yan, Jiabao1 (AUTHOR), Xu, Qihang1,2 (AUTHOR), Zheng, Zhian1 (AUTHOR) zhengzhian@csuft.edu.cn, Han, Xian-Hua2 (AUTHOR), Zhu, Junjie1 (AUTHOR), Lin, Yanhua1 (AUTHOR) |
| Source: | Remote Sensing. May2026, Vol. 18 Issue 10, p1667. 23p. |
| Subjects: | Wavelet transforms, Feature extraction, Optical sensors, Real-time computing, Object recognition (Computer vision), Weather |
| Abstract: | Highlights: What are the main findings? A wavelet-driven frequency–spatial co-awareness framework preserves fog-weakened high-frequency edge and texture features during early feature extraction for robust terrestrial and near-ground optical sensing. The proposed framework improves detection accuracy while maintaining real-time inference under a unified FP32 speed benchmark, with only a slight batch-1 latency increase relative to the YOLOv8-s baseline. What are the implications of the main findings? WFSCA-Block complements spatial semantic modeling by preserving fog-weakened high-frequency edge and texture features. Preserving high-frequency edge and texture features supports practical low-visibility terrestrial sensing and monitoring tasks, including roadside observation and traffic-scene perception. Optical object detection under fog-induced atmospheric degradation remains a challenging problem for terrestrial sensing and monitoring systems. Atmospheric scattering reduces image contrast and attenuates high-frequency edge and texture features that are important for precise object localization, while standard downsampling in convolutional neural networks (CNNs) further amplifies this information loss during feature extraction. Existing spatial-domain methods largely improve pixel appearance or feature refinement without explicitly preserving fog-weakened high-frequency edge and texture features during feature extraction. To address this issue, we propose WFSCA-YOLO, a frequency-aware and feature-preserving detection framework with cross-domain fusion between frequency-domain details and spatial semantic responses. The framework introduces the Wavelet-driven Frequency–spatial Co-awareness Block (WFSCA-Block) into YOLOv8, where the Discrete Wavelet Transform (DWT) is used to decompose feature maps into multi-directional high-frequency subbands and preserve high-frequency edge and texture features degraded by atmospheric scattering. A Cross-Domain Feature Selector (CDFS) is further designed to adaptively recalibrate the fusion of frequency-domain details and spatial semantic responses under varying visibility conditions. Experiments on synthetic and real-world degraded optical benchmarks from near-ground scenes, namely Foggy Cityscapes and RTTS, show that WFSCA-YOLO consistently outperforms representative state-of-the-art methods, achieving 50.3% mAP@50 on Foggy Cityscapes (2.1 percentage points above the baseline) and a mean mAP@50 of 79.28% on RTTS over three independent runs. Under a unified FP32 batch-1 inference benchmark, WFSCA-YOLO runs at 134.76 FPS on an RTX 4090D, indicating real-time capability with only a slight latency increase relative to the YOLOv8-s baseline. These results indicate that preserving high-frequency edge and texture features is an effective strategy for robust perception under degraded visibility and offers practical potential for terrestrial sensing and monitoring platforms. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Highlights: What are the main findings? A wavelet-driven frequency–spatial co-awareness framework preserves fog-weakened high-frequency edge and texture features during early feature extraction for robust terrestrial and near-ground optical sensing. The proposed framework improves detection accuracy while maintaining real-time inference under a unified FP32 speed benchmark, with only a slight batch-1 latency increase relative to the YOLOv8-s baseline. What are the implications of the main findings? WFSCA-Block complements spatial semantic modeling by preserving fog-weakened high-frequency edge and texture features. Preserving high-frequency edge and texture features supports practical low-visibility terrestrial sensing and monitoring tasks, including roadside observation and traffic-scene perception. Optical object detection under fog-induced atmospheric degradation remains a challenging problem for terrestrial sensing and monitoring systems. Atmospheric scattering reduces image contrast and attenuates high-frequency edge and texture features that are important for precise object localization, while standard downsampling in convolutional neural networks (CNNs) further amplifies this information loss during feature extraction. Existing spatial-domain methods largely improve pixel appearance or feature refinement without explicitly preserving fog-weakened high-frequency edge and texture features during feature extraction. To address this issue, we propose WFSCA-YOLO, a frequency-aware and feature-preserving detection framework with cross-domain fusion between frequency-domain details and spatial semantic responses. The framework introduces the Wavelet-driven Frequency–spatial Co-awareness Block (WFSCA-Block) into YOLOv8, where the Discrete Wavelet Transform (DWT) is used to decompose feature maps into multi-directional high-frequency subbands and preserve high-frequency edge and texture features degraded by atmospheric scattering. A Cross-Domain Feature Selector (CDFS) is further designed to adaptively recalibrate the fusion of frequency-domain details and spatial semantic responses under varying visibility conditions. Experiments on synthetic and real-world degraded optical benchmarks from near-ground scenes, namely Foggy Cityscapes and RTTS, show that WFSCA-YOLO consistently outperforms representative state-of-the-art methods, achieving 50.3% mAP@50 on Foggy Cityscapes (2.1 percentage points above the baseline) and a mean mAP@50 of 79.28% on RTTS over three independent runs. Under a unified FP32 batch-1 inference benchmark, WFSCA-YOLO runs at 134.76 FPS on an RTX 4090D, indicating real-time capability with only a slight latency increase relative to the YOLOv8-s baseline. These results indicate that preserving high-frequency edge and texture features is an effective strategy for robust perception under degraded visibility and offers practical potential for terrestrial sensing and monitoring platforms. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 20724292 |
| DOI: | 10.3390/rs18101667 |
