One estimation method of road slope and vehicle distance

Article Robotics

VIRAL-Fusion: A Visual-Inertial-Ranging-Lidar Sensor Fusion Approach

Thien-Minh Nguyen et al.

Summary: In recent years, significant progresses have been made in onboard self-localization (OSL) methods based on cameras or lidar. However, these methods still face inherent challenges such as estimation drift and robustness in low-texture environment. This study proposes a comprehensive optimization-based estimator that integrates data from multiple sensors to achieve long-term consistent and flexible localization for unmanned aerial vehicles (UAVs). The proposed method is evaluated in various scenarios and demonstrates effective resolution of drift issue with minimal installation requirements.

IEEE TRANSACTIONS ON ROBOTICS (2022)

添加到收藏夹

Article Engineering, Civil

Towards Real-Time Monocular Depth Estimation for Robotics: A Survey[-5pt]

Xingshuai Dong et al.

Summary: This paper presents a comprehensive survey of monocular depth estimation (MDE), covering methods, performance evaluation metrics, datasets, and applications. It also summarizes open-source implementations of representative methods and discusses future research directions. The survey aims to assist readers in navigating this research field.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging

S. Mahdi H. Miangoleh et al.

Summary: The research has found a trade-off between consistent scene structure and high-frequency details in depth estimation, and proposes a depth merging network to combine low- and high-resolution estimations to take advantage of this duality. By merging estimations at different resolutions with changing context, multi-megapixel depth maps with a high level of detail can be generated using a pre-trained model.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic