LiuDongdong

爱好由来落笔难,一诗千改心始安。

IMU Trajectory

Advantages of IMU : (1) energy-efficient, capable of running 24h a day without draining a battery; (2) works any where even inside a bag or a pocket(get device acc); Disadvantage: small sensor errors or biases explode quickly in the double integration process. In Augmented Reality applications(eg., apple ARKit, Google ARCore, Microsoft HoloLens), IMU augments Slam by resolving scale ambiguities and providing motion cues in the absence of visual features. UAVs,

Multi-Sense

level: IEEE Robotics and automation letters date: ‘2019,10’ keyword: Deep learning in robotics and automation,action segmentation,ergonomic safety. Paper: Ergonomic Risk predition we present a first of its kind end-to-end deep learning system for ergonomic risk assessment during indoor object manipulation using camera videos. Our learning system is based on action segmentation*, where an action class (with a corresponding risk label) is predicted for every video frame. The REBA model assigns

BlueTooth Paper

Billah, Md Fazlay Rabbi Masum, et al. “BLE Can See: A Reinforcement Learning Approach for RF-based Indoor Occupancy Detection.” Proceedings of the 20th International Conference on Information Processing in Sensor Networks (co-located with CPS-IoT Week 2021). 2021. CCF_B Paper: BLE Can See Summary propose BLECS, a Bluetooth-dependent indoor occupancy detection system which can adapt itself in th edynamic environment. The system uses a reinforcement learning approach to predict the occupancy

Hand Analyse Record

level: CVPR CCF_A author: Tomas Simon Carnegie Mellon University date: 2017 keyword: hand pose Paper: OpenPose HandKeypoint Summary present an approach that uses a multi-camera system to train fine-grained detectors for keypoints. Research Objective Application Area: hand based HCI and robotics Purpose: to extract hand point coordinate from single RGB images. Proble Statement self-occlusion due to articulation, view-point, grasped object. previous work: many approaches to image-based face and body keypoint

RFID ActionRecognition

level: ACM数据库 Embedded Networked Sensor Systems CCF_B author: Yinggang Yu ,Dong Wang, Run Zhao, Qian Zhang ShangHaiJiaoTongUniversity date: 2019 .11 keyword: RFID,wireless sensing ,ongoing gesture recognition,adversarial learning Paper: RFID ongoing Gesture Summary 通过一个阅读器多个标签进行实验,使用CNN来分别提取相位和RSSI
0%