WendellZ524 / Resume

Home Page:resume-ashy-mu.vercel.app

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Personal Information

Education

The University of Melbourne

  • Degree: Master of Information Technology
  • Period: 2021 - 2022

University California, Riverside

  • Degree: Bachelor of Electronic & Computer Engineering
  • Period: 2019 - 2020

Wuhan University of Technology

  • Degree: Bachelor of Electronic & Computer Engineering
  • Period: 2019 - 2020

Work Experience

Bosch (Chengdu) Information Technology Services Co., Ltd. Shanghai Branch

  • Position: Research Scientist
  • Period: 2022 - Present

Responsibilities:

Ground Truth System

  • Development Perception model for Grount Truth System: Based on PersFormer and BEVFusion, use Lidar point as 3D PE to guide the height of BEV feature map. Apply min-cost flow for matching to contrast DETR-like loss.
  • Data selection: use Perceptre-hash, Timestamps, and IMU information to select divergence data for human annotation.
  • Annotation quality check: use CLIP-IQA to select blurred, bad samples from the dataset. Using Grounded-SAM and other rule-based functions to check lane line labeling quality.

Setup & maintain IT Lab and department local AI training cluster

  • Build up a local registry for docker images.
  • Fulfill ITL network requirements & DevOps by using Ansible and playbook.
  • Build a monitor based on Grafana & Prometheus.
  • Build high-concurrent DFS for computer vision case by Ceph.

Center for Environmental Research and Technology, UC Riverside

  • Position: Research Assitant
  • Period:2019-2021

Responsibilities:

  • Unity Client Development: Build a digital twin for Toyota Infotech based on Unity Engine. Adapt LGSVL to the original project, and build the communication among SUMO's traffic flow, real-world vehicles, and Unity Engine.
  • Tech Art: Optimize graphic performance for PBR rendering to ensure the Oculus Rift2 can run at least 45Hz on RTX2080.

Other Projects

Feature-based IR for indoor localization (2020):

  • Use VGG's muti-scale contrast an image vector as key for image data, and use cosine distance to search related images in the database, use OANet to calculate the query image's orientation & position.

Source-free semi-supervised domain adaptation for Image Segmentation (2022):

  • Adapt a trained on GAT5's DeepLabV3 model to the Citysapes dataset via labels from semantic-kitty.

About

resume-ashy-mu.vercel.app


Languages

Language:CSS 67.5%Language:JavaScript 16.7%Language:HTML 15.8%