通过 ROI 压缩优化自动驾驶车辆远程操作中的交通标志与交通信号灯可见性
Optimizing traffic signs and lights visibility for the teleoperation of autonomous vehicles through ROI compression
AI总结：
本文提出面向自动驾驶远程驾驶的三级 CTU 带宽分配 HEVC ROI 压缩方法，利用语义分割突出交通标志与信号灯，最高提升 5.5 dB。
摘要：
自动驾驶车辆是应对交通拥堵、空气污染、事故以及时间和资源浪费的一种有前景的解决方案。然而，在极端情况下，可能需要远程驾驶员介入，以确保安全路边停车或完成完整的远程接管。在此类情况下，高质量的实时视频流对于实际远程驾驶至关重要。在一项初步研究中，我们已经提出了一种感兴趣区域（ROI）HEVC 数据压缩方法，其中图像被分割为 ROI 和背景两类，将更多带宽分配给 ROI，从而在以较低质量传输背景的同时，提升对驾驶至关重要类别的可见性。但是，将带宽转移到图像中较大的 ROI 部分并不能显著改善交通标志和交通信号灯的质量。本工作将 ROI 进一步划分为背景、弱 ROI 或强 ROI。这种基于仿真的方法使用由 Cognata 自动驾驶汽车仿真平台创建的照片级真实驾驶场景数据库。我们采用语义分割，根据每个像素类别对编码树单元（CTU）的压缩质量进行分类。背景 CTU 只能包含天空、树木、植被或建筑物类别。远程驾驶的必要对象包括道路、道路标线、汽车和行人等重要类别；最重要的是交通标志和交通信号灯。我们应用阈值来判定某一 CTU 中特定类别的像素数量是否足以宣布其属于强 ROI 或弱 ROI。随后，我们根据 CTU 类别分配带宽。结果表明，与仅进行背景和前景划分相比，交通标志（尤其是文字标志）以及交通信号灯的感知质量显著提升，最高可达 5.5 dB，同时弱 ROI 类别至少保持其原有质量。
英文摘要：
Autonomous vehicles are a promising solution to traffic congestion, air pollution, accidents, and wasted time and resources. However, remote driver intervention may be necessary for extreme situations to ensure safe roadside parking or complete remote takeover. In such cases, high-quality real-time video streaming is crucial for practical remote driving. In a preliminary study, we already presented a region of interest (ROI) HEVC data compression where the image was segmented into two categories of ROI and background, allocating more bandwidth to the ROI, yielding an improvement in the visibility of the classes that essential for driving while transmitting the background with lesser quality. However, migrating bandwidth to the large ROI portion of the image doesn't substantially improve the quality of traffic signs and lights. This work categorized the ROIs into either background, weak ROI, or strong ROI. The simulation-based approach uses a photo-realistic driving scenario database created with the Cognata self-driving car simulation platform. We use semantic segmentation to categorize the compression quality of a Coding Tree Unit (CTU) according to each pixel class. A background CTU can contain only sky, trees, vegetation, or building classes. Essentials for remote driving include significant classes such as roads, road marks, cars, and pedestrians. And most importantly, traffic signs and traffic lights. We apply thresholds to decide if the number of pixels in a CTU of a particular category is enough to declare it as belonging to the strong or weak ROI. Then, we allocate the bandwidth according to the CTU categories. Our results show that the perceptual quality of traffic signs, especially textual signs and traffic lights, improves significantly by up to 5.5 dB compared to the only background and foreground partition, while the weak ROI classes at least retain their original quality.
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。
