A5100577002- Robotics and Sensor-Based Localization
- Advanced Neural Network Applications
- Advanced Image and Video Retrieval Techniques
- Video Surveillance and Tracking Methods
Yanshan University
2023-2025
Service robots operating in unstructured environments must effectively recognize and segment unknown objects to enhance their functionality. Traditional supervised learningbased segmentation techniques require extensive annotated datasets, which are impractical for the diversity of encountered real-world scenarios. Unseen Object Instance Segmentation (UOIS) methods aim address this by training models on synthetic data generalize novel objects, but they often suffer from simulation-to-reality...
Object detection and distance measurement are core technologies for indoor robots. RGB-D cameras enable robots to accurately calculate the between objects. However, irregular surfaces of small objects, including curved protrusions, can significantly affect accuracy. To improve estimation distance, an effective method obtaining accurate object sampling region is necessary. In this paper, we propose a unified architecture obtain depth values objects in scene achieve high-precision measurement....