Multimodal Sensing Platform and Dataset
We are designing and deploying a multi-modal multi-node sensor data collection platform that can be utilized for various data collection tasks with reproducibility and easy deployment.
Ph.D. Candidate
Ph.D. Candidate at UCLA
Ziqi Wang received his M.S degree at UCLA ECE Department in 2020, and his B.Eng. degree in Electrical Engineering from Fudan University, China in 2018. He is currently pursuing his Ph.D. Degree in the Signal and Systems area at UCLA. Working as a graduate student researcher at Networked and Embedded Systems Laboratory (NESL), he is under the supervision of Prof. Mani B. Srivastava.
His research interests generally lie in the area of Mobile Sensing, Mobile Computing, Signal Processing and Internet of Things, for example, detection and recognition of human activities with wireless sensing modalities. He is also interested in developing secure learning-enabled systems leading to fascinating applications, e.g., human-computer interaction and smart home management. Recently, he is devoted to design architectures for multimodal data collection and analysis, e.g, fusing the information from multiple sensors like camera, LiDAR, and UWB Radar to help robot systems build situational awareness.
Ziqi is recognized as the Outstanding Graduates of Fudan University in 2018, as well as Best Student Poster/Demo Honorable Mention at the ECE Annual Research Review of UCLA.
We are designing and deploying a multi-modal multi-node sensor data collection platform that can be utilized for various data collection tasks with reproducibility and easy deployment.
Video scene analysis can detect and classify people and objects in the scene. Wireless vibrometry employs wireless signals to sense subtle vibrations from the objects and infer their internal states. The combination of these two constitutes a more comprehensive understanding of the scene.
We present UWHear, a system that simultaneously recovers and separates sounds from multiple sources. UWHear employs Impulse Radio Ultra-Wideband (IR-UWB) technology to directly seperate reconstruct audio from sound source vibrations.