直接处理原始拜耳图像，提升机器人视觉的效率与稳定性。
Keypoint Detection and Description for Raw Bayer Images
- 设计专用卷积核，直接在原始拜耳图像上操作，保留通道间信息。
- 在大旋转和尺度变化下表现更优，准确率高于现有算法。
- 适合资源受限的机器人系统，减少硬件与内存开销。
关键点检测与局部特征描述是机器人感知的基础任务，对SLAM、定位、特征匹配、位姿估计和3D建图等应用至关重要。现有方法多基于RGB图像，本文提出一种新网络，直接处理原始图像，无需经过图像信号处理器（ISP）。该方法显著降低硬件需求与内存消耗，适用于机器人视觉系统。通过设计两个专用卷积核，可在原始拜耳图像上直接进行卷积，保持通道间信息不丢失。实验表明，该网络在原始图像上优于现有算法，在大旋转和尺度变化下具有更高精度与稳定性。这是首个专为原始图像设计的关键点检测与特征描述网络，为资源受限环境提供更高效解决方案。
原文摘要 · Abstract (English)
Keypoint detection and local feature description are fundamental tasks in robotic perception, critical for applications such as SLAM, robot localization, feature matching, pose estimation, and 3D mapping. While existing methods predominantly operate on RGB images, we propose a novel network that directly processes raw images, bypassing the need for the Image Signal Processor (ISP). This approach significantly reduces hardware requirements and memory consumption, which is crucial for robotic vision systems. Our method introduces two custom-designed convolutional kernels capable of performing convolutions directly on raw images, preserving inter-channel information without converting to RGB. Experimental results show that our network outperforms existing algorithms on raw images, achieving higher accuracy and stability under large rotations and scale variations. This work represents the first attempt to develop a keypoint detection and feature description network specifically for raw images, offering a more efficient solution for resource-constrained environments.
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。