EdwardLeeLPZ

PowerBEV

POWERBEV, a novel and elegant vision-based end-to-end framework that only consists of 2D convolutional layers to perform perception and forecasting of multiple objects in BEVs.

EdwardLeeLPZ

Personal Repository of Peizheng Li

PhD_Research_Plan

EdwardLeeLPZ.github.io

Context-Experiments

Several experiments that analyze the influence of context on the detection effect and separate contextual information from features

Domain-Adaptation

A domain adaptation project based on context and global prototype developed on Detectron2

Human-Activity-Recognition

A project based on smart phone sensors that uses deep residual neural networks to recognize human activities

Diabetic-Retinopathy-Detection

A project that uses deep convolutional neural networks to automatically diagnose diabetic retinopathy.