论文标题
RGB-D语义细分的实时融合网络，结合了公路驾驶图像的意外障碍物检测
Real-time Fusion Network for RGB-D Semantic Segmentation Incorporating Unexpected Obstacle Detection for Road-driving Images
论文作者
论文摘要
由于深度卷积神经网络的成功，语义细分已经取得了惊人的进步。考虑到自动驾驶的需求，这些年的实时语义细分已成为研究热点。但是，尽管如今，尽管很容易访问的深度信息，但很少有实时的RGB-D融合语义分段研究。在本文中，我们提出了一个称为RFNET的实时融合语义分割网络，该网络有效利用了互补的跨模式信息。 RFNET在高效的网络体系结构的基础上，能够迅速运行，可以满足自动驾驶汽车的应用。多数据集训练可以杠杆化，以纳入意外的小障碍检测，丰富在现实世界中面临不可预见的危害所需的可识别类别。一组全面的实验证明了我们框架的有效性。在CityScapes上，我们的方法的表现优于先前的最先进的语义细分器，其准确性出色，并且在完整的2048x1024分辨率下具有22Hz推理速度，表现优于大多数现有的RGB-D网络。
Semantic segmentation has made striking progress due to the success of deep convolutional neural networks. Considering the demands of autonomous driving, real-time semantic segmentation has become a research hotspot these years. However, few real-time RGB-D fusion semantic segmentation studies are carried out despite readily accessible depth information nowadays. In this paper, we propose a real-time fusion semantic segmentation network termed RFNet that effectively exploits complementary cross-modal information. Building on an efficient network architecture, RFNet is capable of running swiftly, which satisfies autonomous vehicles applications. Multi-dataset training is leveraged to incorporate unexpected small obstacle detection, enriching the recognizable classes required to face unforeseen hazards in the real world. A comprehensive set of experiments demonstrates the effectiveness of our framework. On Cityscapes, Our method outperforms previous state-of-the-art semantic segmenters, with excellent accuracy and 22Hz inference speed at the full 2048x1024 resolution, outperforming most existing RGB-D networks.
