Results 281 to 290 of about 162,676 (316)

Cross Fusion of Point Cloud and Learned Image for Loop Closure Detection

IEEE Robotics and Automation Letters
Loop closure detection (LCD) plays a crucial role in simultaneous localization and mapping (SLAM) systems to eliminate accumulated odometry drifts as the map is built, and using multi-modal information can improve the accuracy and robustness of this ...
Haosong Yue, Danyang Cao, Zhong Liu, Tian Wang, Weihai Chen   +4 more
semanticscholar   +1 more source

Enhancing Cooperative Visual SLAM with a Self-Supervised Deep Learning Model for Efficient Keypoint-Based Inter-map Loop Closure Detection

2024 IEEE 20th International Conference on Automation Science and Engineering (CASE)
This paper introduces a self-supervised deep learning keypoint model SiLK specifically designed for loop closure detection in Cooperative Visual SLAM (Simultaneous Localization and Mapping).
Zakaria Chekakta, Abdelhafid Zenati, Nabil Aouf   +2 more
semanticscholar   +1 more source

Online Loop-Closure Detection via Dynamic Sparse Representation

2016
Visual loop closure detection is an important problem in visual robot navigation. Successful solutions to visual loop closure detection are based on image matching between the current view and the map images. In order to obtain a solution that is scalable to large environments involving thousands or millions of images, the efficiency of a loop closure ...
Moein Shakeri, Hong Zhang
openaire   +1 more source

Collaborative SLAM with Convolutional Neural Network-based Descriptor for Inter-Map Loop Closure Detection

International Conference on Automation, Robotics and Applications
This paper introduces a novel Collaborative Si-multaneous Localization and Mapping (CSLAM) framework, enhanced with a Histogram of Oriented Gradients (HOG) de-scriptor, to improve Inter-Map Loop Closure Detection.
Zuyuan Zhu, Zakaria Chekakta, Nabil Aouf
semanticscholar   +1 more source

GraSS: Graph Neural Networks for Loop Closure Detection with Semantic and Spatial Assistance

International Symposium on Circuits and Systems
Loop Closure Detection (LCD) is an essential part of minimizing drift due to the accumulation of previously pose errors in Simultaneous Localization and Mapping (SLAM). The existing loop detection methods are limited by the changes of external conditions
Shihang Lu, Zhuolin Peng, Zhuoling Xiao, Bo Yan, Shuisheng Lin, Sheng Yu, Di He   +6 more
semanticscholar   +1 more source

MRM-LOOP:A Dynamic Visual Loop Closure Detection Algorithm Based on Motion Region Matching

IEEE International Conference on Software Quality, Reliability and Security Companion
Aiming at the problem of false negatives and false positives in loop closure detection for visual SLAM algorithms in dynamic environments, a dynamic visual SLAM loop closure detection algorithm based on motion region matching named MRM-LOOP is proposed ...
Zhiming Zhang, Jun Zhang, Yuansheng Liu
semanticscholar   +1 more source

Indoor loop closure detection based on geometric features

Tenth International Symposium on Precision Mechanical Measurements, 2021
Jiang Wensong, Zhiyuan Zhu, Luo Zai, Yang Li   +3 more
openaire   +1 more source

Dynamic Weighting-Based Deep Learning for SLAM Loop Closure Detection

2024 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML)
In LiDAR SLAM systems, loop closure detection is a crucial component to ensure localization accuracy and map consistency. OverlapNet, a loop closure detection algorithm based on image overlap rate, has demonstrated strong performance.
Bin Yang, Chuan Qiu, Wei Yang, Mingwu Ren   +3 more
semanticscholar   +1 more source

Loop Closure Detection With Bidirectional Manifold Representation Consensus

IEEE Transactions on Intelligent Transportation Systems, 2023
Kaining Zhang, Zizhuo Li, Jiayi Ma
openaire   +1 more source

Visual Loop-Closure Detection via Prominent Feature Tracking

Journal of Intelligent & Robotic Systems, 2022
Ioannis Tsampikos Papapetros, Vasiliki Balaska, Antonios Gasteratos   +2 more
openaire   +1 more source