A5011613315- Indoor and Outdoor Localization Technologies
- RFID technology advancements
- Robotics and Sensor-Based Localization
- Context-Aware Activity Recognition Systems
- IPv6, Mobility, Handover, Networks, Security
- Smart Grid Energy Management
- Advanced Adaptive Filtering Techniques
- Augmented Reality Applications
- Bluetooth and Wireless Communication Technologies
- Energy Efficient Wireless Sensor Networks
- Advanced Wireless Network Optimization
- Wireless Networks and Protocols
- Advanced Image and Video Retrieval Techniques
- QR Code Applications and Technologies
- Vehicle License Plate Recognition
- Advanced Antenna and Metasurface Technologies
- Speech and Audio Processing
- IoT and Edge/Fog Computing
Tsinghua University
2024-2025
Tianjin University
2019-2024
Wireless human sensing plays a crucially important role in the human-computer interaction context, which activities and even emotions can be recognized understood by computers. A batch of academic efforts have been proposed to use wireless techniques such as WiFi, RFID, Bluetooth, Radar, Zigbee address problem. Each kind technology has its own characteristics advantages thus is suitable for specific application scenarios. For example, WiFi-based solutions achieve non-intrusive sensing,...
Individual activity recognition is crucial for Human-Computer Interaction (HCI) applications, especially in multi-person scenarios. Current approaches, based on wearable sensors or wireless signals (e.g., WiFi and RFID), however, are often focused single person scenario only, due to the limitation of existing sensing technologies. In order address issue, we design a DEeper Exercise Monitoring system, called DEEM, which introduce computer vision techniques facilitate RFID devices provide...
The evolution of Wi-Fi to next-generation 802.11bf demonstrates the potential device-free sensing applications, where we can remotely infer behaviors users without bringing into physical contact with them. Among these tracking is critical provide location based services. Recent systems be cataloged model-based and data-based approaches: (1) approach build mathematical model. However, this method sensitive environmental noise, spends more execution time; (2) train a neural network. requires...
This paper studies the practically important problem of missing tag detection for multi-category RFID systems, where tags are normally categorized into different categories according to types or brands associated items. Existing protocols make a common unrealistic assumption that all belong single category. Although performing an existing protocol separately on each category seems workable, it will take quite long execution time when tens involved. proposes Simultaneous Missing Tag Detection...
Mobile robot-assisted book inventory such as identification and order detection has become increasingly popular in smart library, replacing the manual which is time-consuming error-prone. The existing systems are either computer vision (CV)-based or RFID-based, however several limitations inevitable. CV-based may not be able to identify books effectively due low accuracy of detecting texts on spine. RFID tags attached can used a uniquely. However, high tag density scenarios coupling effects...
Localization of target tagged objects on the shelf is great significance in RFID-enabled warehousing scenarios. Compared with RFID localization systems that use fixed reader antennas or mobile RFID-robot, portable reader-based methods are much more cost-effective. Hence, this paper focuses reader-portable localization. However, existing suffer from following limitations: (i) antenna required to pass by tags. Thus, tags corner can never be located; (ii) many reference need deployed advance,...
In the scenarios of warehousing or industrial manufacturing, objects usually should be placed vertically, box containing bottles wine cannot inverted, and books vertically on shelves. RFID has many attractive advantages, no requirement line-of-sight battery-free for long-term monitoring. Hence, an RFID-based solution was proposed to detect whether tagged are oblique. However, existing two major limitations: (i) it requires that both reader static; (ii) can only deal with case upside down but...