Yu Guo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Yu Guo has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Mohammad S. Obaidat
King Abdullah II School of Information Technology, The University of Jordan, Amman, Jordan
11 shared publications Yang Yang
School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China
11 shared publications- Zhenqiang Mi
Beijing Advanced Innovation Center for Materials Genome Engineering, School of Intelligence Science and Technology, School of Computer and Communication Engineering, and the Shunde Innovation School, University of Science and Technology Beijing, Beijing, China
11 shared publications Zhenqiang Mi
University of Science and Technology Beijing, School of Computer and Communication Engineering, Beijing, China
7 shared publications- Xiaojuan Ban
University of Science and Technology Beijing, Beijing, China
5 shared publications - Yuanyan Xie
School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China
5 shared publications
Latest Publications
- Open Access
- 3 September 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 9 (3) , 1-26
HPIPainting: A Hand-Pen Interaction for VR Painting
Virtual Reality (VR) painting applications allow users to create visual imagery in 3D space. However, existing bare-hand VR painting and sketching systems frequently rely on generic hand gestures, which could lead to significant user misunderstandings. In this paper, we propose HPIPainting, a bare-hand VR painting system that implements a virtual pen interaction mechanism based on the Hand-Pen Interaction(HPI) paradigm. This paradigm leverages microgesture recognition to integrate natural pen-grasping gestures into a precise interaction model, enabling users to sketch in 3D space naturally and immersively. Specifically, we explored the design space for VR painting gestures and filtered out 9 microgestures through subjective evaluations to control various painting functions, such as start painting, edit, brush adjustment, geometric creation, and grid operations. Studies demonstrate that HPIPainting improves the immersion, usability, and expressive freedom of bare-hand VR Painting, it achieves controller-level drawing accuracy with a mean error of 1.21 mm, fast and reliable mode-switching within 222 ms, and significantly higher ratings for ease of use, hand fatigue, and naturalness compared to pinch- and controller-based input.
- 3 September 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 9 (3) , 1-26
Open AccessHPIPainting: A Hand-Pen Interaction for VR Painting
Virtual Reality (VR) painting applications allow users to create visual imagery in 3D space. However, existing bare-hand VR painting and sketching systems frequently rely on generic hand gestures, which could lead to significant user misunderstandings. In this paper, we propose HPIPainting, a bare-hand VR painting system that implements a virtual pen interaction mechanism based on the Hand-Pen Interaction(HPI) paradigm. This paradigm leverages microgesture recognition to integrate natural pen-grasping gestures into a precise interaction model, enabling users to sketch in 3D space naturally and immersively. Specifically, we explored the design space for VR painting gestures and filtered out 9 microgestures through subjective evaluations to control various painting functions, such as start painting, edit, brush adjustment, geometric creation, and grid operations. Studies demonstrate that HPIPainting improves the immersion, usability, and expressive freedom of bare-hand VR Painting, it achieves controller-level drawing accuracy with a mean error of 1.21 mm, fast and reliable mode-switching within 222 ms, and significantly higher ratings for ease of use, hand fatigue, and naturalness compared to pinch- and controller-based input.
- 4 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/CAA Journal of Automatica Sinica
- Vol. 12 (3) , 528-538
Multi-Scale Time Series Segmentation Network Based on Eddy Current Testing for Detecting Surface Metal Defects
In high-risk industrial environments like nuclear power plants, precise defect identification and localization are essential for maintaining production stability and safety. However, the complexity of such a harsh environment leads to significant variations in the shape and size of the defects. To address this challenge, we propose the multivariate time series segmentation network (MSSN), which adopts a multiscale convolutional network with multi-stage and depth-separable convolutions for efficient feature extraction through variable-length templates. To tackle the classification difficulty caused by structural signal variance, MSSN employs logarithmic normalization to adjust instance distributions. Furthermore, it integrates classification with smoothing loss functions to accurately identify defect segments amid similar structural and defect signal subsequences. Our algorithm evaluated on both the Mackey-Glass dataset and industrial dataset achieves over 95% localization and demonstrates the capture capability on the synthetic dataset. In a nuclear plant's heat transfer tube dataset, it captures 90% of defect instances with 75% middle localization F1 score.
- 4 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/CAA Journal of Automatica Sinica
- Vol. 12 (3) , 528-538
Multi-Scale Time Series Segmentation Network Based on Eddy Current Testing for Detecting Surface Metal Defects
In high-risk industrial environments like nuclear power plants, precise defect identification and localization are essential for maintaining production stability and safety. However, the complexity of such a harsh environment leads to significant variations in the shape and size of the defects. To address this challenge, we propose the multivariate time series segmentation network (MSSN), which adopts a multiscale convolutional network with multi-stage and depth-separable convolutions for efficient feature extraction through variable-length templates. To tackle the classification difficulty caused by structural signal variance, MSSN employs logarithmic normalization to adjust instance distributions. Furthermore, it integrates classification with smoothing loss functions to accurately identify defect segments amid similar structural and defect signal subsequences. Our algorithm evaluated on both the Mackey-Glass dataset and industrial dataset achieves over 95% localization and demonstrates the capture capability on the synthetic dataset. In a nuclear plant's heat transfer tube dataset, it captures 90% of defect instances with 75% middle localization F1 score.
- 24 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (8) , 7110-7117
An Object-Driven Navigation Strategy Based on Active Perception and Semantic Association
Efficiently navigating to a specific kind of objects in an unknown environment is an important and challenging research topic in Embodied AI. Existing methods, such as end-to-end learning ones and modular ones still struggle at this task as they have poor efficiency, interpretability and/or generalization. This paper proposes an object-driven navigation strategy for robots based on active perception and semantic association. Specifically, this strategy enables robots to explore the environment and complete object-driven navigation tasks by endowing them with the ability to explore areas, infer associations, remember scenes, continue navigation, and so on. On this basis, this paper designs a semantic association model based on a graph convolution network using rich information hidden in the environment, including geometric and semantic information, to dynamically predict the association between objects, providing more accurate and effective prior knowledge for object-driven navigation. Experimental results prove that the proposed strategy can help robots better perceive and understand the environment and it is superior to similar strategies in terms of success rate and navigation efficiency.
- 24 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (8) , 7110-7117
An Object-Driven Navigation Strategy Based on Active Perception and Semantic Association
Efficiently navigating to a specific kind of objects in an unknown environment is an important and challenging research topic in Embodied AI. Existing methods, such as end-to-end learning ones and modular ones still struggle at this task as they have poor efficiency, interpretability and/or generalization. This paper proposes an object-driven navigation strategy for robots based on active perception and semantic association. Specifically, this strategy enables robots to explore the environment and complete object-driven navigation tasks by endowing them with the ability to explore areas, infer associations, remember scenes, continue navigation, and so on. On this basis, this paper designs a semantic association model based on a graph convolution network using rich information hidden in the environment, including geometric and semantic information, to dynamically predict the association between objects, providing more accurate and effective prior knowledge for object-driven navigation. Experimental results prove that the proposed strategy can help robots better perceive and understand the environment and it is superior to similar strategies in terms of success rate and navigation efficiency.
- 30 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (2) , 840-847
Indoor Visual Re-Localization for Long-Term Autonomous Robots Based on Object-Level Features and Semantic Relationships
Visual re-localization has become one of the key technologies for long-term autonomous robots. Existing methods, mostly focusing on addressing day-night, weather, and seasonal changes, are not applicable in indoor scenarios. At the same time, the layouts of objects in indoor scenes are highly dynamic over time due to human interactions with the environment, which makes indoor re-localization challenging. This letter presents a novel indoor visual re-localization method for long-term autonomous robots. First, a scene graph model is proposed, incorporating object-level features and semantic relationships, which overcomes the influence of dynamic objects by understanding the interactions among objects. Then, a visual re-localization method is developed based on the proposed scene graph model. It adopts graph matching technologies to incorporate pairwise object interactions as important features for re-localization, and designs a feature reweighting strategy to further reduce the impact of outliers in dynamic scenes. The proposed re-localization method has been verified in both photorealistic simulation environments and real-world scenarios. The results show that our approach exhibits higher robustness to diverse object changes and performs comparably to the state-of-the-art methods when illumination changes occur.
- 30 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 8 (2) , 840-847
Indoor Visual Re-Localization for Long-Term Autonomous Robots Based on Object-Level Features and Semantic Relationships
Visual re-localization has become one of the key technologies for long-term autonomous robots. Existing methods, mostly focusing on addressing day-night, weather, and seasonal changes, are not applicable in indoor scenarios. At the same time, the layouts of objects in indoor scenes are highly dynamic over time due to human interactions with the environment, which makes indoor re-localization challenging. This letter presents a novel indoor visual re-localization method for long-term autonomous robots. First, a scene graph model is proposed, incorporating object-level features and semantic relationships, which overcomes the influence of dynamic objects by understanding the interactions among objects. Then, a visual re-localization method is developed based on the proposed scene graph model. It adopts graph matching technologies to incorporate pairwise object interactions as important features for re-localization, and designs a feature reweighting strategy to further reduce the impact of outliers in dynamic scenes. The proposed re-localization method has been verified in both photorealistic simulation environments and real-world scenarios. The results show that our approach exhibits higher robustness to diverse object changes and performs comparably to the state-of-the-art methods when illumination changes occur.
- 18 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 10 (1) , 473-485
Edge-Assisted Real-Time Instance Segmentation for Resource-Limited IoT Devices
Instance segmentation exploits the potential of Internet of Things (IoT) devices to perceive environmental semantic information and achieve complex interactions with the physical world. However, IoT devices usually have limited computing and storage resources and cannot afford the intensive computational costs of instance segmentation networks. This article proposes an edge-assisted instance segmentation method for resource-limited IoT devices; it selectively offloads some computation-intensive tasks from IoT devices to edge servers to accelerate the inference processes of instance segmentation networks. To reduce the communication cost caused by computation offloading, a data compression method is proposed to adaptively adjust the downsampling interval based on an attention mechanism. Considering the susceptibility of the computation offloading scheme to network conditions, an adaptive computation offloading strategy that can jointly optimize the offloading point and the data compression ratio is proposed so that the edge-assisted instance segmentation can meet the preset latency requirements while achieving maximal accuracy under volatile network conditions. Extensive experiments are conducted to verify the feasibility and efficiency of our method. The experimental results show that our method induces less latency than existing instance segmentation methods with a slight drop in accuracy.
- 18 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 10 (1) , 473-485
Edge-Assisted Real-Time Instance Segmentation for Resource-Limited IoT Devices
Instance segmentation exploits the potential of Internet of Things (IoT) devices to perceive environmental semantic information and achieve complex interactions with the physical world. However, IoT devices usually have limited computing and storage resources and cannot afford the intensive computational costs of instance segmentation networks. This article proposes an edge-assisted instance segmentation method for resource-limited IoT devices; it selectively offloads some computation-intensive tasks from IoT devices to edge servers to accelerate the inference processes of instance segmentation networks. To reduce the communication cost caused by computation offloading, a data compression method is proposed to adaptively adjust the downsampling interval based on an attention mechanism. Considering the susceptibility of the computation offloading scheme to network conditions, an adaptive computation offloading strategy that can jointly optimize the offloading point and the data compression ratio is proposed so that the edge-assisted instance segmentation can meet the preset latency requirements while achieving maximal accuracy under volatile network conditions. Extensive experiments are conducted to verify the feasibility and efficiency of our method. The experimental results show that our method induces less latency than existing instance segmentation methods with a slight drop in accuracy.
- Open Access
- 20 July 2022
- Published by MDPI AG in Electronics
- Vol. 11 (14) , 2266
Design and Implementation of an Intelligent Assistive Cane for Visually Impaired People Based on an Edge-Cloud Collaboration Scheme
Visually impaired people face many inconveniences in daily life, and there are problems such as high prices and single functions in the market of assistance tools for visually impaired people. In this work, we designed and implemented a low-cost intelligent assistance cane, particularly for visually impaired individuals, based on computer vision, sensors, and an edge-cloud collaboration scheme. Obstacle detection, fall detection, and traffic light detection functions have been designed and integrated for the convenience of moving for visually impaired people. We have also designed an image captioning function and object detection function with high-speed processing capability based on an edge-cloud collaboration scheme to improve the user experience. Experiments show that the performance metrics have an aerial obstacle detection accuracy of 92.5%, fall detection accuracy of 90%, and average image retrieval period of 1.124 s. It proves the characteristics of low power consumption, strong real-time performance, adaptability to multiple scenarios, and convenience, which can ensure the safety of visually impaired people when moving and can help them better perceive and understand the surrounding environment.
- 20 July 2022
- Published by MDPI AG in Electronics
- Vol. 11 (14) , 2266
Open AccessDesign and Implementation of an Intelligent Assistive Cane for Visually Impaired People Based on an Edge-Cloud Collaboration Scheme
Visually impaired people face many inconveniences in daily life, and there are problems such as high prices and single functions in the market of assistance tools for visually impaired people. In this work, we designed and implemented a low-cost intelligent assistance cane, particularly for visually impaired individuals, based on computer vision, sensors, and an edge-cloud collaboration scheme. Obstacle detection, fall detection, and traffic light detection functions have been designed and integrated for the convenience of moving for visually impaired people. We have also designed an image captioning function and object detection function with high-speed processing capability based on an edge-cloud collaboration scheme to improve the user experience. Experiments show that the performance metrics have an aerial obstacle detection accuracy of 92.5%, fall detection accuracy of 90%, and average image retrieval period of 1.124 s. It proves the characteristics of low power consumption, strong real-time performance, adaptability to multiple scenarios, and convenience, which can ensure the safety of visually impaired people when moving and can help them better perceive and understand the surrounding environment.
- Open Access
- 14 April 2022
- Published by MDPI AG in Information
- Vol. 13 (4) , 197
An Effective Student Grouping and Course Recommendation Strategy Based on Big Data in Education
Personalized education aims to provide cooperative and exploratory courses for students by using computer and network technology to construct a more effective cooperative learning mode, thus improving students’ cooperation ability and lifelong learning ability. Based on students’ interests, this paper proposes an effective student grouping strategy and group-oriented course recommendation method, comprehensively considering characteristics of students and courses both from a statistical dimension and a semantic dimension. First, this paper combines term frequency–inverse document frequency and Word2Vec to preferably extract student characteristics. Then, an improved K-means algorithm is used to divide students into different interest-based study groups. Finally, the group-oriented course recommendation method recommends appropriate and quality courses according to the similarity and expert score. Based on real data provided by junior high school students, a series of experiments are conducted to recommend proper social practical courses, which verified the feasibility and effectiveness of the proposed strategy.
- 14 April 2022
- Published by MDPI AG in Information
- Vol. 13 (4) , 197
Open AccessAn Effective Student Grouping and Course Recommendation Strategy Based on Big Data in Education
Personalized education aims to provide cooperative and exploratory courses for students by using computer and network technology to construct a more effective cooperative learning mode, thus improving students’ cooperation ability and lifelong learning ability. Based on students’ interests, this paper proposes an effective student grouping strategy and group-oriented course recommendation method, comprehensively considering characteristics of students and courses both from a statistical dimension and a semantic dimension. First, this paper combines term frequency–inverse document frequency and Word2Vec to preferably extract student characteristics. Then, an improved K-means algorithm is used to divide students into different interest-based study groups. Finally, the group-oriented course recommendation method recommends appropriate and quality courses according to the similarity and expert score. Based on real data provided by junior high school students, a series of experiments are conducted to recommend proper social practical courses, which verified the feasibility and effectiveness of the proposed strategy.
- Open Access
- 2 April 2022
- Published by MDPI AG in Electronics
- Vol. 11 (7) , 1136
An Efficient Object Navigation Strategy for Mobile Robots Based on Semantic Information
In recent years, the rapid development of computer vision makes it possible for mobile robots to be more intelligent. Among the related technologies, the visual SLAM system allows the mobile robot to locate itself, build the map, and provide a navigation strategy to execute follow-up tasks, such as searching for objects in unknown environment according to the observed information. However, most of the existing studies are meant to provide a predefined trajectory for the robot or allow the robot to explore blindly and randomly, which undoubtedly affects the efficiency of the object navigation process and goes against with the idea of “intelligent”. To solve the above problems, an efficient object navigation strategy is proposed in this paper. Firstly, a semantic association model is obtained by using the Mask R-CNN and skip-gram to conduct correlation analysis of common indoor objects. Then, with the help of the above model and ROS framework, an effective object navigation strategy is designed to enable the robot to find the given target efficiently. Finally, the classical ORB-SLAM2 system method is integrated to help the robot build a high usability environment map and find passable paths when moving. Simulation results validated that the proposed strategy can efficiently help the robot to navigate to the object without human intervention.
- 2 April 2022
- Published by MDPI AG in Electronics
- Vol. 11 (7) , 1136
Open AccessAn Efficient Object Navigation Strategy for Mobile Robots Based on Semantic Information
In recent years, the rapid development of computer vision makes it possible for mobile robots to be more intelligent. Among the related technologies, the visual SLAM system allows the mobile robot to locate itself, build the map, and provide a navigation strategy to execute follow-up tasks, such as searching for objects in unknown environment according to the observed information. However, most of the existing studies are meant to provide a predefined trajectory for the robot or allow the robot to explore blindly and randomly, which undoubtedly affects the efficiency of the object navigation process and goes against with the idea of “intelligent”. To solve the above problems, an efficient object navigation strategy is proposed in this paper. Firstly, a semantic association model is obtained by using the Mask R-CNN and skip-gram to conduct correlation analysis of common indoor objects. Then, with the help of the above model and ROS framework, an effective object navigation strategy is designed to enable the robot to find the given target efficiently. Finally, the classical ORB-SLAM2 system method is integrated to help the robot build a high usability environment map and find passable paths when moving. Simulation results validated that the proposed strategy can efficiently help the robot to navigate to the object without human intervention.
- Open Access
Stereo CenterNet based 3D Object Detection for Autonomous Driving
Recently, three-dimensional (3D) detection based on stereo images has progressed remarkably; however, most advanced methods adopt anchor-based two-dimensional (2D) detection or depth estimation to address this problem. Nevertheless, high computational cost inhibits these methods from achieving real-time performance. In this study, we propose a 3D object detection method, Stereo CenterNet (SC), using geometric information in stereo imagery. SC predicts the four semantic key points of the 3D bounding box of the object in space and utilizes 2D left and right boxes, 3D dimension, orientation, and key points to restore the bounding box of the object in the 3D space. Subsequently, we adopt an improved photometric alignment module to further optimize the position of the 3D bounding box. Experiments conducted on the KITTI dataset indicate that the proposed SC exhibits the best speed-accuracy trade-off among advanced methods without using extra data.
Open AccessStereo CenterNet based 3D Object Detection for Autonomous Driving
Recently, three-dimensional (3D) detection based on stereo images has progressed remarkably; however, most advanced methods adopt anchor-based two-dimensional (2D) detection or depth estimation to address this problem. Nevertheless, high computational cost inhibits these methods from achieving real-time performance. In this study, we propose a 3D object detection method, Stereo CenterNet (SC), using geometric information in stereo imagery. SC predicts the four semantic key points of the 3D bounding box of the object in space and utilizes 2D left and right boxes, 3D dimension, orientation, and key points to restore the bounding box of the object in the 3D space. Subsequently, we adopt an improved photometric alignment module to further optimize the position of the 3D bounding box. Experiments conducted on the KITTI dataset indicate that the proposed SC exhibits the best speed-accuracy trade-off among advanced methods without using extra data.
- 2 March 2021
- Published by Springer Nature in Neural Computing and Applications
- Vol. 33 (17) , 11447-11464
ATPS: an adaptive trajectory prediction system based on semantic information for dynamic objects
- 2 March 2021
- Published by Springer Nature in Neural Computing and Applications
- Vol. 33 (17) , 11447-11464
ATPS: an adaptive trajectory prediction system based on semantic information for dynamic objects