BlabberSeg：面向嵌入式设备的实时开放词汇航空图像分割
BlabberSeg: Real-Time Embedded Open-Vocabulary Aerial Segmentation
AI总结：
BlabberSeg 通过复用 CLIPSeg 的提示与模型特征，在 Jetson Orin AGX 上实现 16.78 Hz 的实时开放词汇航空分割，速度提升 927.41% 且精度损失极小。
摘要：
实时航空图像分割在无人驾驶飞行器（UAV）的环境感知中发挥着重要作用。我们提出了 BlabberSeg，这是一个基于 CLIPSeg 优化的视觉-语言模型，用于 UAV 在机载端对航空图像进行实时处理。BlabberSeg 通过复用提示特征和模型特征来提高 CLIPSeg 的效率，在降低计算开销的同时实现实时开放词汇航空分割。我们使用动态开放词汇增强智能安全着陆（DOVESEI）框架，在一个安全着陆场景中验证了 BlabberSeg，该框架结合了视觉伺服和开放词汇分割。BlabberSeg 显著降低了计算成本，在 NVIDIA Jetson Orin AGX（64GB）上速度提升了 927.41%（16.78 Hz），而原始 CLIPSeg 为 1.81 Hz，在精度损失可忽略的情况下（相对于 CLIPSeg 的正确分割区域比例为 2.1%）实现了实时航空分割。BlabberSeg 的源代码已开源并可在网上获取。
英文摘要：
Real-time aerial image segmentation plays an important role in the environmental perception of Uncrewed Aerial Vehicles (UAVs). We introduce BlabberSeg, an optimized Vision-Language Model built on CLIPSeg for on-board, real-time processing of aerial images by UAVs. BlabberSeg improves the efficiency of CLIPSeg by reusing prompt and model features, reducing computational overhead while achieving real-time open-vocabulary aerial segmentation. We validated BlabberSeg in a safe landing scenario using the Dynamic Open-Vocabulary Enhanced SafE-Landing with Intelligence (DOVESEI) framework, which uses visual servoing and open-vocabulary segmentation. BlabberSeg reduces computational costs significantly, with a speed increase of 927.41% (16.78 Hz) on a NVIDIA Jetson Orin AGX (64GB) compared with the original CLIPSeg (1.81Hz), achieving real-time aerial segmentation with negligible loss in accuracy (2.1% as the ratio of the correctly segmented area with respect to CLIPSeg). BlabberSeg's source code is open and available online.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
