🤖 AI Summary
To address the insufficient robustness of object detection under low-visibility conditions—such as fog, smoke, and haze—this paper proposes a multi-stage detection framework that jointly incorporates the atmospheric scattering physical model and mechanisms of the human visual cortex. Innovatively, selective attention and environment-adaptive visual cues are embedded into the detection backbone, establishing a perception-driven, staged computational paradigm: (1) coarse detection to localize salient regions; (2) adaptive enhancement via a differentiable physics-based dehazing module; and (3) fine-grained detection modulated by attention, enabling end-to-end joint optimization. Evaluated on Foggy Cityscapes and RESIDE-beta (OTS/RTTS), the method achieves mAP gains of 8.2–12.7% over prior work, while operating at 1.9× the inference speed of current state-of-the-art methods. This significantly improves both detection accuracy and real-time performance for autonomous driving and security surveillance systems under complex meteorological conditions.
📝 Abstract
This study proposes a novel deep learning framework inspired by atmospheric scattering and human visual cortex mechanisms to enhance object detection under poor visibility scenarios such as fog, smoke, and haze. These conditions pose significant challenges for object recognition, impacting various sectors, including autonomous driving, aviation management, and security systems. The objective is to enhance the precision and reliability of detection systems under adverse environmental conditions. The research investigates the integration of human-like visual cues, particularly focusing on selective attention and environmental adaptability, to ascertain their impact on object detection's computational efficiency and accuracy. This paper proposes a multi-tiered strategy that integrates an initial quick detection process, followed by targeted region-specific dehazing, and concludes with an in-depth detection phase. The approach is validated using the Foggy Cityscapes, RESIDE-beta (OTS and RTTS) datasets and is anticipated to set new performance standards in detection accuracy while significantly optimizing computational efficiency. The findings offer a viable solution for enhancing object detection in poor visibility and contribute to the broader understanding of integrating human visual principles into deep learning algorithms for intricate visual recognition challenges.