.jpg)
Jiaqi Zhang
I am a Master of Engineering student in UC Berkeley, majored in EECS. I once interned in Stanford as a researcher and Microsoft Research Asia as a software engineer. My interest lies in software development, especially the application of computer vision and machine learning, such like text recognition and AR/VR.
​
2019 IS&T International Symposium on Electronic Imaging (EI 2019).
Burlingame, California USA
Oral Report
UPCOMING EVENTS
2019 International Conference on Acoustics, Speech, and Signal Processing (ICASSP, 2019)
Brighton, UK
Poster Presentation
​Research and Project
A system for generating complex physically accurate sensor images for automotive applications
​
Vision Imaging Science and Technology Lab(VISTA Lab), Stanford University
Supervised by Prof. Brian A. Wandell
​
We designed an open source simulator that automates the creation of sensor irradiance and sensor images of typical automotive scenes in urban settings.
Pixel Level Data Augmentation for Semantic Image Segmentation
​
Intelligence Computation and Machine Learning Lab(ICMLL)
Supervised by Prof. Zengchang Qin
​
We proposed a pipeline of data augmentation method to balance the label distribution of dataset in order to improve segmentation performance.
Experimental results show that the proposed method can not only improve segmentation accuracy of those classes with low accuracy, but also obtain 1.3% to 2.1% increase in average segmentation accuracy.
Electroencephalogram(EEG) Classification and Brain Computer Interface Research Based on Motor Imagery
​
Supervised by Prof. Yang Li
​
Our method of processing EEG signals consist of HHT, EMD, CSP, and SVM algorithms. The classification accuracy of our method has raised up to 87%.
On-line experiment has succeeded and this project has been commercialized. The product based on this project aims to help rehabilitation of cerebral apoplexy.
Intelligent Robot Design
​
We designed the mechanical structure of line-tracking robot to catch objects, trace line, recognize objects and turn off the light. Several kinds of sensors are used to achieve are the functions.
-
Ultrasonic sensor is used to measure distances.
-
Infrared sensor is used to identify infrared light.
-
Gray-scale sensor is used to trace the correct path.
All of these sensors, motor and steering engine are controlled by single chip computer. We optimized our algorithms to let the robot much more intelligent. Depend on the very high accuracy of infrared identification and robustness of our robot, we win the Bronze Award in the robot competition in my college.