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 letter, 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 22 Hz inference speed at the full 2048 × 1024 resolution, outperforming most existing RGB-D networks.

With the rapid development of high-speed communication and artificial intelligence technologies, human perception of real-world scenes is no longer limited to the use of small Field of View (FoV) and low-dimensional scene detection devices. Panoramic imaging emerges as the next generation of innovative intelligent instruments for environmental perception and measurement. However, while satisfying the need for large-FoV photographic imaging, panoramic imaging instruments are expected to have high resolution, no blind area, miniaturization, and multidimensional intelligent perception, and can be combined with artificial intelligence methods towards the next generation of intelligent instruments, enabling deeper understanding and more holistic perception of 360° real-world surrounding environments. Fortunately, recent advances in freeform surfaces, thin-plate optics, and metasurfaces provide innovative approaches to address human perception of the environment, offering promising ideas beyond conventional optical imaging. In this review, we begin with introducing the basic principles of panoramic imaging systems, and then describe the architectures, features, and functions of various panoramic imaging systems. Afterwards, we discuss in detail the broad application prospects and great design potential of freeform surfaces, thin-plate optics, and metasurfaces in panoramic imaging. We then provide a detailed analysis on how these techniques can help enhance the performance of panoramic imaging systems. We further offer a detailed analysis of applications of panoramic imaging in scene understanding for autonomous driving and robotics, spanning panoramic semantic image segmentation, panoramic depth estimation, panoramic visual localization, and so on. Finally, we cast a perspective on future potential and research directions for panoramic imaging instruments.

Pixel-wise semantic segmentation is capable of unifying most of driving scene perception tasks, and has enabled striking progress in the context of navigation assistance, where an entire surrounding sensing is vital. However, current mainstream semantic segmenters are predominantly benchmarked against datasets featuring narrow Field of View (FoV), and a large part of vision-based intelligent vehicles use only a forward-facing camera. In this paper, we propose a Panoramic Annular Semantic Segmentation (PASS) framework to perceive the whole surrounding based on a compact panoramic annular lens system and an online panorama unfolding process. To facilitate the training of PASS models, we leverage conventional FoV imaging datasets, bypassing the efforts entailed to create fully dense panoramic annotations. To consistently exploit the rich contextual cues in the unfolded panorama, we adapt our real-time ERF-PSPNet to predict semantically meaningful feature maps in different segments, and fuse them to fulfill panoramic scene parsing. The innovation lies in the network adaptation to enable smooth and seamless segmentation, combined with an extended set of heterogeneous data augmentations to attain robustness in panoramic imagery. A comprehensive variety of experiments demonstrates the effectiveness for real-world surrounding perception in a single PASS, while the adaptation proposal is exceptionally positive for state-of-the-art efficient networks.

Semantic segmentation (SS) is promising for outdoor scene perception in safety-critical applications like autonomous vehicles, assisted navigation and so on. However, traditional SS is primarily based on RGB images, which limits the reliability of SS in complex outdoor scenes, where RGB images lack necessary information dimensions to fully perceive unconstrained environments. As a preliminary investigation, we examine SS in an unexpected obstacle detection scenario, which demonstrates the necessity of multimodal fusion. Thereby, in this work, we present EAFNet, an Efficient Attention-bridged Fusion Network, to exploit complementary information coming from different optical sensors. Specifically, we incorporate polarization sensing to obtain supplementary information, considering its optical characteristics for robust representation of diverse materials. By using a single-shot polarization sensor, we build the first RGB-P dataset which consists of 394 annotated pixel-aligned RGB-polarization images. A comprehensive variety of experiments shows the effectiveness of EAFNet to fuse polarization and RGB information, as well as its flexibility to be adapted to other sensor combination scenarios.

Navigational assistance aims to help visually-impaired people to ambulate the environment safely and independently. This topic becomes challenging as it requires detecting a wide variety of scenes to provide higher level assistive awareness. Vision-based technologies with monocular detectors or depth sensors have sprung up within several years of research. These separate approaches have achieved remarkable results with relatively low processing time and have improved the mobility of impaired people to a large extent. However, running all detectors jointly increases the latency and burdens the computational resources. In this paper, we put forward seizing pixel-wise semantic segmentation to cover navigation-related perception needs in a unified way. This is critical not only for the terrain awareness regarding traversable areas, sidewalks, stairs and water hazards, but also for the avoidance of short-range obstacles, fast-approaching pedestrians and vehicles. The core of our unification proposal is a deep architecture, aimed at attaining efficient semantic understanding. We have integrated the approach in a wearable navigation system by incorporating robust depth segmentation. A comprehensive set of experiments prove the qualified accuracy over state-of-the-art methods while maintaining real-time speed. We also present a closed-loop field test involving real visually-impaired users, demonstrating the effectivity and versatility of the assistive framework.