Results 161 to 170 of about 13,782 (194)
Some of the next articles are maybe not open access.
Modified Keyframe Selection Algorithm and Map Visualization Based on ORB-SLAM2
2020 4th International Conference on Robotics and Automation Sciences (ICRAS), 2020Recently, Simultaneous Localization and Mapping (SLAM) has becoming an important technology for mobile robot. Real time performance and localization accuracy are two main indicators for SLAM. Traditional SLAM algorithms (i.e. ORB-SLAM2) adopt interframe motion time based method, which depends on keyframes similarity detection to select keyframes.
Pengfa Xie +6 more
openaire +2 more sources
Research on the Improvement of ORB-SLAM2 Algorithm Based on Deep Learning
2023 5th International Conference on Artificial Intelligence and Computer Applications (ICAICA), 2023Vision-based Simultaneous Localization and Map Building (VSLAM) refers to the camera as the only external sensor that creates a map of the environment while positioning itself.
Shimeng Cao
openaire +2 more sources
LFD-SLAM: improved point line combination feature algorithm based on ORB-SLAM2
Fourth International Conference on Testing Technology and Automation Engineering (TTAE 2024)With the progression of computer and automation technologies, alongside advancements in the shipbuilding industry, the automation level in ship manufacturing has been steadily increasing.
Jiaqi Mao, Guang Yang
openaire +2 more sources
Research on Modification of the Initial Pose Estimation Algorithm for ORB-SLAM2
2024 International Conference on Information Technology, Comunication Ecosystem and Management (ITCEM)ORB-SLAM2 has been widely used in computer vision applications. To overcome the limitations in the initial pose estimation step in complex scenes, this paper proposes an adaptive threshold strategy to modify the constant velocity motion model.
Xin Yang, Hongxia Cui
openaire +2 more sources
Path-Tracking Control Based on Deep ORB-SLAM2
2020 International Automatic Control Conference (CACS), 2020This paper proposes a mobile robot navigation control design based on deep vSLAM approach. The deep vSLAM system integrates ORB-SLAM2 with a deep neural network (DNN) to enhance the localization performance of an embedded navigation system. An RGB-D camera is utilized to realize the deep vSLAM system. In the proposed deep vSLAM algorithm, the DNN works
Kai-Tai Song, Song-Qing Ou
openaire +1 more source
Annual Conference of the IEEE Industrial Electronics Society, 2022
Mini-drones have a wide range of applications, including weather monitoring, parcel delivery, search and rescue, and entertainment. As their functionality, safety, and performance heavily relies on ubiquitously reliable positioning and navigation, their ...
Amin Basiri, V. Mariani, L. Glielmo
semanticscholar +1 more source
Mini-drones have a wide range of applications, including weather monitoring, parcel delivery, search and rescue, and entertainment. As their functionality, safety, and performance heavily relies on ubiquitously reliable positioning and navigation, their ...
Amin Basiri, V. Mariani, L. Glielmo
semanticscholar +1 more source
ORB-SLAM2 Based Teach-and-Repeat System
2021The teach-and-repeat task is autonomous navigation along the trajectory taught in advance. A robot is manually driven along the desired trajectory during a teaching phase, and it stores information about it. In this paper, there is proposed a simple teach-and-repeat system based on visual simultaneous localization and mapping system ORB-SLAM2.
Tomáš Pivoňka, Libor Přeučil
openaire +1 more source
2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC), 2018
ORB-SLAM2 is an excellent keyframe-based SLAM with six degrees of freedom(6DOF), it can only triangulate 6DOF image frames for localization and mapping, and has no ability to process 3DOF(degrees of freedom) image frames which are not satisfied with the requirement of triangulation.
Fanyu Zeng, Wenchao Zeng, Yan Gan
openaire +1 more source
ORB-SLAM2 is an excellent keyframe-based SLAM with six degrees of freedom(6DOF), it can only triangulate 6DOF image frames for localization and mapping, and has no ability to process 3DOF(degrees of freedom) image frames which are not satisfied with the requirement of triangulation.
Fanyu Zeng, Wenchao Zeng, Yan Gan
openaire +1 more source
Research on omnidirectional ORB-SLAM2 for mobile robots
2018 IEEE CSAA Guidance, Navigation and Control Conference (CGNCC), 2018This paper proposes a method of using omnidirectional images as visual input to ORB-SLAM2 system. With it, the system can track ORB feature points in the whole 360°. Hence, compared to traditional monocular camera SLAM systems, the result will be much more robust since more ORB feature points can be extracted.
Yule Wang, Xubo Yang
openaire +1 more source
Research on Localization and Mapping Algorithm of Industrial Inspection Robot Based on ORB-SLAM2
2023 International Conference on Electronics and Devices, Computational Science (ICEDCS), 2023Visual SLAM technology is crucial for the localization and mapping of industrial inspection robots, improving their accuracy and robustness in practical applications.
Zixun Chen
semanticscholar +1 more source