<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Kan-Hua Lee</title><description>Notes on machine learning, computer vision, and physics.</description><link>https://kanhua.github.io/</link><item><title>My experiment on porting Python to Mojo: supercharging a Physics Simulation</title><link>https://kanhua.github.io/posts/mojo-hard-sphere-collision/</link><guid isPermaLink="true">https://kanhua.github.io/posts/mojo-hard-sphere-collision/</guid><description>Mojo promises Python&apos;s ease of use with C-like performance. But what does it take to port a real Python project? I converted a hard-sphere collision simulation…</description><pubDate>Sun, 17 Aug 2025 08:00:00 GMT</pubDate></item><item><title>My selected highlights of CVPR 2024</title><link>https://kanhua.github.io/posts/cvpr-2024/</link><guid isPermaLink="true">https://kanhua.github.io/posts/cvpr-2024/</guid><description>I got a chance to attend CVPR 2024 (remotely). I posted my version of highlights on my Medium.</description><pubDate>Sun, 23 Jun 2024 14:00:00 GMT</pubDate></item><item><title>Ray Tracing Simulation: A Tutorial</title><link>https://kanhua.github.io/posts/ray-tracing/</link><guid isPermaLink="true">https://kanhua.github.io/posts/ray-tracing/</guid><description>Modeling light as rays is widely used in computer graphics and lens design. I encountered this problem when I tried to do some optical design but had no access…</description><pubDate>Mon, 09 Mar 2020 12:00:00 GMT</pubDate></item><item><title>3D object detection with Lyft self-driving car data</title><link>https://kanhua.github.io/posts/frustum-pointnet-lyft-3d/</link><guid isPermaLink="true">https://kanhua.github.io/posts/frustum-pointnet-lyft-3d/</guid><description>This is my attempt of a past Kaggle competition Lyft 3D Object Detection for Autonomous Vehicles, using the concept of frustum-pointnet to solve this past…</description><pubDate>Sun, 08 Mar 2020 12:01:00 GMT</pubDate></item><item><title>Traffic light classification without (re-)training a DNN model</title><link>https://kanhua.github.io/posts/traffic-light-detection/</link><guid isPermaLink="true">https://kanhua.github.io/posts/traffic-light-detection/</guid><description>I did this project partly for Udacity&apos;s Self-Driving car degree and was lazy to train and retraing a DNN model. It ends up that this solution is not so lazy,…</description><pubDate>Fri, 01 Nov 2019 14:00:00 GMT</pubDate></item><item><title>Lane line detection</title><link>https://kanhua.github.io/posts/lane-line-detection/</link><guid isPermaLink="true">https://kanhua.github.io/posts/lane-line-detection/</guid><description>This is a project with Udacity&apos;s Self-Driving Car Nanodegree. The aim is to identify the lane lines on the road and get their curvatures, using an algorithmic…</description><pubDate>Fri, 13 Jul 2018 11:54:00 GMT</pubDate></item><item><title>Implementing path planning of a self-driving car</title><link>https://kanhua.github.io/posts/carnd-path-planning/</link><guid isPermaLink="true">https://kanhua.github.io/posts/carnd-path-planning/</guid><description>The aim of this project is to implement a car that drives automatically in a simulation world. The car should be able to switch the lane smoothly when…</description><pubDate>Mon, 01 Jan 2018 14:00:00 GMT</pubDate></item><item><title>Behavioural cloning of self-driving car</title><link>https://kanhua.github.io/posts/behavioural-cloning/</link><guid isPermaLink="true">https://kanhua.github.io/posts/behavioural-cloning/</guid><description>This is a project with Udacity&apos;s Self-Driving Car Nanodegree. The aim is to use deep learning approach[1] to clone the behaviour of a car in the simulator made…</description><pubDate>Tue, 11 Apr 2017 12:00:00 GMT</pubDate></item></channel></rss>