Linked e-resources
Details
Table of Contents
Intro
Preface
Organization
Contents
Part I
Vision-Based Human-Robot Interaction and Applications
Knowledge-Enhanced Scene Context Embedding for Object-Oriented Navigation of Autonomous Robots
1 Introduction
2 Definition and Methodology
2.1 Task Definition
2.2 Knowledge Graph Based on Matterport3D (MattKG)
2.3 6-D Scene Context Embedding
2.4 End-to-End Learning
3 Experiments
4 Conclusion
References
An End-to-End Object Detector with Spatiotemporal Context Learning for Machine-Assisted Rehabilitation
1 Introduction
2 Related Work
3 Proposed Method
3.1 SEFP-RepVGG
3.2 Conv-DETR
4 Experimental Results and Discussion
4.1 Experimental Settings
4.2 Ablation Study
4.3 Comparison with State-of-the-Arts
4.4 Applications in Rehabilitation System
5 Conclusion
References
Skeleton-Based Hand Gesture Recognition by Using Multi-input Fusion Lightweight Network
1 Introduction
2 Related Works
2.1 Static and Motion Features
2.2 Skeleton-Based Gesture Recognition
3 Methodology
3.1 Modeling Static Feature by Center Joint Oriented Method
3.2 Extracting Global and Local Motion Features by Different Frames
3.3 Dimension Adjustment and Feature Fusion by CNN Embedding
4 Experiments
4.1 Dataset
4.2 Training Details
4.3 Ablation Studies
4.4 Comparison with Previous Methods
5 Conclusion
References
Multiple-Point Obstacle Avoidance Based on 3D Depth Camera Skeleton Modeling and Virtual Potential Field for the Redundant Manipulator
1 Introduction
2 Skeleton Algorithm Based on 3D Depth Camera
2.1 Building the Skeleton
2.2 Constructing Bounding Box
2.3 Finding Possible Collision Multiple-Points
3 Collision Avoidance for the Redundant Manipulator
3.1 Attractive Potential Field and Force
3.2 Repulsive Potential Field and Force
3.3 Modified Representation of Repulsive Force
3.4 Relation Between Forces and Joint Angles
4 Simulation
5 Conclusion
References
A Novel Grasping Approach with Dynamic Annotation Mechanism
1 Introduction
2 Related Work
3 Dataset
3.1 Overview
3.2 Basic and Decent Annotation
3.3 Annotation Transform
3.4 Evaluation
4 Grasping Detection Network
4.1 Network Structure
4.2 Loss Function
5 Experiments
5.1 Comparison Experiment of Datasets
5.2 Comparison Experiment of Methods
5.3 Robot Grasping Experiment
6 Conclusion
References
Tracking and Counting Method for Tomato Fruits Scouting Robot in Greenhouse
1 Introduction
2 Material and Method
2.1 Tomato Sample and Scouting Robot
2.2 Image Acquisition
2.3 Tomato Fruit Detection
2.4 Tracking and Counting of Tomato Fruit
2.5 Result Output
3 Result and Discussion
4 Conclusion and Future Work
References
Interaction, Control and Application Technologies of Welfare Robots
Preface
Organization
Contents
Part I
Vision-Based Human-Robot Interaction and Applications
Knowledge-Enhanced Scene Context Embedding for Object-Oriented Navigation of Autonomous Robots
1 Introduction
2 Definition and Methodology
2.1 Task Definition
2.2 Knowledge Graph Based on Matterport3D (MattKG)
2.3 6-D Scene Context Embedding
2.4 End-to-End Learning
3 Experiments
4 Conclusion
References
An End-to-End Object Detector with Spatiotemporal Context Learning for Machine-Assisted Rehabilitation
1 Introduction
2 Related Work
3 Proposed Method
3.1 SEFP-RepVGG
3.2 Conv-DETR
4 Experimental Results and Discussion
4.1 Experimental Settings
4.2 Ablation Study
4.3 Comparison with State-of-the-Arts
4.4 Applications in Rehabilitation System
5 Conclusion
References
Skeleton-Based Hand Gesture Recognition by Using Multi-input Fusion Lightweight Network
1 Introduction
2 Related Works
2.1 Static and Motion Features
2.2 Skeleton-Based Gesture Recognition
3 Methodology
3.1 Modeling Static Feature by Center Joint Oriented Method
3.2 Extracting Global and Local Motion Features by Different Frames
3.3 Dimension Adjustment and Feature Fusion by CNN Embedding
4 Experiments
4.1 Dataset
4.2 Training Details
4.3 Ablation Studies
4.4 Comparison with Previous Methods
5 Conclusion
References
Multiple-Point Obstacle Avoidance Based on 3D Depth Camera Skeleton Modeling and Virtual Potential Field for the Redundant Manipulator
1 Introduction
2 Skeleton Algorithm Based on 3D Depth Camera
2.1 Building the Skeleton
2.2 Constructing Bounding Box
2.3 Finding Possible Collision Multiple-Points
3 Collision Avoidance for the Redundant Manipulator
3.1 Attractive Potential Field and Force
3.2 Repulsive Potential Field and Force
3.3 Modified Representation of Repulsive Force
3.4 Relation Between Forces and Joint Angles
4 Simulation
5 Conclusion
References
A Novel Grasping Approach with Dynamic Annotation Mechanism
1 Introduction
2 Related Work
3 Dataset
3.1 Overview
3.2 Basic and Decent Annotation
3.3 Annotation Transform
3.4 Evaluation
4 Grasping Detection Network
4.1 Network Structure
4.2 Loss Function
5 Experiments
5.1 Comparison Experiment of Datasets
5.2 Comparison Experiment of Methods
5.3 Robot Grasping Experiment
6 Conclusion
References
Tracking and Counting Method for Tomato Fruits Scouting Robot in Greenhouse
1 Introduction
2 Material and Method
2.1 Tomato Sample and Scouting Robot
2.2 Image Acquisition
2.3 Tomato Fruit Detection
2.4 Tracking and Counting of Tomato Fruit
2.5 Result Output
3 Result and Discussion
4 Conclusion and Future Work
References
Interaction, Control and Application Technologies of Welfare Robots