通过自适应图像增强提升恶劣天气下目标检测的鲁棒性
ERUP-YOLO: Enhancing Object Detection Robustness for Adverse Weather Condition by Unified Image-Adaptive Processing
- 使用可微分滤波器实现端到端图像增强，适配后续检测任务
- 在雾天和低光照条件下，检测性能优于传统方法
- 无需针对数据定制参数，通用性强，适合实际部署
我们提出一种面向雾霾和低光照等恶劣天气的目标检测图像自适应增强方法。框架采用可微分预处理滤波器，针对后续检测任务优化图像质量。引入两种可微分滤波器：基于贝塞尔曲线的逐像素（BPW）滤波器和基于核的局部（KBL）滤波器，统一经典图像处理功能并提升检测性能。同时提出一种不依赖领域的数据增强策略，利用BPW滤波器生成多样化训练样本。该方法无需针对特定数据集调整滤波器组合、参数范围或数据增强方式。我们将该方法应用于YOLOv3，构建名为增强鲁棒性统一图像处理（ERUP-YOLO）的模型。在多个恶劣天气数据集上的实验表明，所提滤波器表达能力与传统方法相当或更优，且ERUP-YOLO在各类恶劣天气条件下均表现出更优的检测性能。
原文摘要 · Abstract (English)
We propose an image-adaptive object detection method for adverse weather conditions such as fog and low-light. Our framework employs differentiable preprocessing filters to perform image enhancement suitable for later-stage object detections. Our framework introduces two differentiable filters: a Bézier curve-based pixel-wise (BPW) filter and a kernel-based local (KBL) filter. These filters unify the functions of classical image processing filters and improve performance of object detection. We also propose a domain-agnostic data augmentation strategy using the BPW filter. Our method does not require data-specific customization of the filter combinations, parameter ranges, and data augmentation. We evaluate our proposed approach, called Enhanced Robustness by Unified Image Processing (ERUP)-YOLO, by applying it to the YOLOv3 detector. Experiments on adverse weather datasets demonstrate that our proposed filters match or exceed the expressiveness of conventional methods and our ERUP-YOLO achieved superior performance in a wide range of adverse weather conditions, including fog and low-light conditions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。