Results 91 to 100 of about 6,226 (231)

Deciphering pixel insights: A deep dive into deep learning strategies for enhanced indoor depth estimation

International Journal of Information Management Data Insights
Depth estimation is one of the crucial tasks for autonomous systems, which provides important information about the distance between the system and its surroundings.
Krisna Pinasthika, Fitri Utaminingrum, Chih‑Yang Lin, Chikamune Wada, Timothy K. Shih   +4 more
doaj   +1 more source

3D‐Printed Shark‐Inspired Soft–Hard Hybrid Underwater Robot With Buoyancy Control and Onboard Vision

Advanced Intelligent Systems, EarlyView.
A fully self‐contained shark‐inspired underwater robot is developed using 3D‐printed soft–hard hybrid structures, servo‐driven propulsion, and pump‐based buoyancy control. The platform achieves three‐dimensional locomotion and onboard vision‐based target tracking, offering a reproducible and accessible framework for biomimetic underwater robot research.
Shotaro Saito, Byeongwook Jo, Minghao Nie, Shoji Takeuchi   +3 more
wiley   +1 more source

Speckle Skin‐Based Multimodal Tactile Perception for Fine Robotic Manipulation

Advanced Intelligent Systems, EarlyView.
SpeckleTac, a miniature vision‐based tactile sensor, utilizes a speckle‐pattern skin and optical flow‐based scalable virtual marker tracking. Combined with advanced algorithms, it achieves high‐resolution 3D surface reconstruction, precise contact perception, and stable grasping capabilities.
Jiayuan Zhang, Chong Wang, Yingao Xu, Shihan Wang, Houping Wu, Yulian Peng, Hongbo Wang   +6 more
wiley   +1 more source

Survey on AI‐Enabled Computer Vision Technologies and Applications for Space Robotic Missions

Journal of Field Robotics, EarlyView.
ABSTRACT This survey provides a comprehensive overview of recent advancements and challenges in Artificial Intelligence (AI)‐enabled computer vision (CV) techniques for space robotic missions, spanning critical phases such as Entry, Descent, and Landing (EDL), orbital operations, and planetary surface exploration.
Maciej Quoos, Steven Kay, Julia Wajoras, Robert Field, Evridiki V. Ntagiou, Fakher Mohammad, Yang Gao   +6 more
wiley   +1 more source

Rotatable Lens‐Based 3D Reconstruction Method for Monocular Vision Systems

SmartBot, EarlyView.
Accurate 3D reconstruction in confined environments remains challenging because conventional vision‐based measurement systems are difficult to maintain compactness without sacrificing accuracy. Here, the authors develop a rotatable lens‐based monocular vision system, which is the first time using the refraction of the light induced by a rotating wedge ...
Puchen Zhu, Zhanpeng Huang, Wenkai Lai, Xiaoyin Zheng, Yiding Nie, Yang Liu, Jiajun An, Daifeng Wang, Dongliang Fan, Xiao Li, Jian S. Dai, Xin Ma   +11 more
wiley   +1 more source

CDFNet: Cross‐Modal Deep Fusion for Monocular 3D Semantic Scene Completion

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Semantic scene completion (SSC) aims to predict the semantic occupancy and geometry of 3D scenes. Recently, most studies focus on camera‐based approaches due to the rich visual cues of images and the cost‐effectiveness of cameras. However, these methods usually lack efficient fusion and fine‐grained processing of cross‐modal semantic ...
Xianjing Cheng, Lintai Wu, Jie Wen, Tianhao Peng, Yong Xu, Zairong Wei   +5 more
wiley   +1 more source

A Robust Visual Inertial Odometry SLAM Considering Robot Self Dynamics

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT In this paper, to deal with the dynamic SLAM problem, we investigate feature tracking and IMU preintegration in visual‐inertial odometry (VIO) and design a robust SLAM framework that explicitly considers robot self‐dynamics. We propose a self‐dynamics and IMU‐aided feature tracker to predict initial optical flow and an iterative refinement ...
Junyin Qiu, Hong Liu, Tianwei Zhang
wiley   +1 more source

RotGS: Rotation‐Guided 3D Gaussian Splatting for Turntable Sequences without Structure‐from‐Motion

Computer Graphics Forum, EarlyView.
Abstract The field of 3D reconstruction from multi‐view images has advanced rapidly thanks to 3D Gaussian Splatting (3DGS), which enables efficient and photorealistic scene representation. However, optimizing 3DGS requires high‐quality images from various viewpoints with accurate camera poses.
Kyumin Kim, Dohae Lee, Hanul Baek, In‐Kwon Lee   +3 more
wiley   +1 more source

See4D: Pose‐Free 4D Generation via Auto‐Regressive Video Inpainting

Computer Graphics Forum, EarlyView.
Abstract Immersive applications call for synthesizing spatiotemporal 4D content from casual videos without costly 3D supervision. Existing video‐to‐4D methods typically rely on manually annotated camera poses, which are labor‐intensive and brittle for in‐the‐wild footage.
Dongyue Lu, Ao Liang, Tianxin Huang, Xiao Fu, Yuyang Zhao, Baorui Ma, Liang Pan, Wei Yin, Lingdong Kong, Wei Tsang Ooi, Ziwei Liu   +10 more
wiley   +1 more source

Determining impact angle from the spatial distribution of shock metamorphism: A case study of the Gosses Bluff (Tnorala) impact structure, Australia

Meteoritics &Planetary Science, EarlyView.
Abstract The majority of planetary impacts occur at oblique angles. Impact structures on Earth are commonly eroded or buried, rendering the identification of the direction and angle of impact—using methods such as asymmetries in ejecta distribution, surface topographic expression, central uplift structure, and geophysical anomalies—challenging. In this
Eloise E. Matthews, Auriol S. P. Rae, Thomas Kenkmann, Nicholas E. Timms, Aaron J. Cavosie, Marian B. Holness   +5 more
wiley   +1 more source