Segmentation of Drivable Road Using Deep Fully Convolutional Residual Network with Pyramid Pooling

Detection and Control Framework for Unpiloted Ground Support Equipment within the Aircraft Stand

The rapid advancement in Unpiloted Robotic Vehicle technology has significantly influenced ground support operations at airports, marking a critical shift towards future development. This study presents a novel Unpiloted Ground Support Equipment (GSE) detection and control framework, comprising virtual channel delineation, boundary line detection, object detection, and navigation and docking control, to facilitate automated aircraft docking within the aircraft stand. Firstly, we developed a bespoke virtual channel layout for Unpiloted GSE, aligning with operational regulations and accommodating a wide spectrum of aircraft types. This layout employs turning induction markers to define essential navigation points, thereby streamlining GSE movement. Secondly, we integrated cameras and Lidar sensors to enable rapid and precise pose adjustments during docking. The introduction of a boundary line detection system, along with an optimized, lightweight YOLO algorithm, ensures swift and accurate identification of boundaries, obstacles, and docking sites. Finally, we formulated a unique control algorithm for effective obstacle avoidance and docking in varied apron conditions, guaranteeing meticulous management of vehicle pose and speed. Our experimental findings reveal an 89% detection accuracy for the virtual channel boundary line, a 95% accuracy for guiding markers, and an F1-Score of 0.845 for the YOLO object detection algorithm. The GSE achieved an average docking error of less than 3 cm and an angular deviation under 5 degrees, corroborating the efficacy and advanced nature of our proposed approach in Unpiloted GSE detection and aircraft docking.

Unification of Road Scene Segmentation Strategies Using Multistream Data and Latent Space Attention

Road scene understanding, as a field of research, has attracted increasing attention in recent years. The development of road scene understanding capabilities that are applicable to real-world road scenarios has seen numerous complications. This has largely been due to the cost and complexity of achieving human-level scene understanding, at which successful segmentation of road scene elements can be achieved with a mean intersection over union score close to 1.0. There is a need for more of a unified approach to road scene segmentation for use in self-driving systems. Previous works have demonstrated how deep learning methods can be combined to improve the segmentation and perception performance of road scene understanding systems. This paper proposes a novel segmentation system that uses fully connected networks, attention mechanisms, and multiple-input data stream fusion to improve segmentation performance. Results show comparable performance compared to previous works, with a mean intersection over union of 87.4% on the Cityscapes dataset.

Occlusion-Free Road Segmentation Leveraging Semantics for Autonomous Vehicles

The deep convolutional neural network has led the trend of vision-based road detection, however, obtaining a full road area despite the occlusion from monocular vision remains challenging due to the dynamic scenes in autonomous driving. Inferring the occluded road area requires a comprehensive understanding of the geometry and the semantics of the visible scene. To this end, we create a small but effective dataset based on the KITTI dataset named KITTI-OFRS (KITTI-occlusion-free road segmentation) dataset and propose a lightweight and efficient, fully convolutional neural network called OFRSNet (occlusion-free road segmentation network) that learns to predict occluded portions of the road in the semantic domain by looking around foreground objects and visible road layout. In particular, the global context module is used to build up the down-sampling and joint context up-sampling block in our network, which promotes the performance of the network. Moreover, a spatially-weighted cross-entropy loss is designed to significantly increases the accuracy of this task. Extensive experiments on different datasets verify the effectiveness of the proposed approach, and comparisons with current excellent methods show that the proposed method outperforms the baseline models by obtaining a better trade-off between accuracy and runtime, which makes our approach is able to be applied to autonomous vehicles in real-time.