{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "**你的目標**是使用光流技術來判斷影片中哪些部分包含向上、向下、向左或向右的移動。\n", "\n", "首先按照課堂中所述的方法提取影片的幀:\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# Code here" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "現在,按照講座中所描述的計算密集光流幀,並將密集光流轉換為極座標:\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# Code here" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "為每個光流幀建立方向的直方圖。直方圖顯示有多少向量落入特定的區間,並應該將幀中不同方向的移動分開。\n", "\n", "> 你可能也需要將所有大小低於某個閾值的向量設為零。這樣可以去除影片中一些小的額外移動,例如眼睛和頭部。\n", "\n", "繪製一些幀的直方圖。\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# Code here" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "看著直方圖,應該可以很直接地判斷移動的方向。你需要選擇那些對應於上/下/左/右方向的區間,並且超過某個閾值的區間。\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "# Code here" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "恭喜!如果你已完成以上所有步驟,你已完成此實驗!\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n---\n\n**免責聲明**: \n本文件已使用人工智能翻譯服務 [Co-op Translator](https://github.com/Azure/co-op-translator) 進行翻譯。儘管我們致力於提供準確的翻譯,但請注意,自動翻譯可能包含錯誤或不準確之處。原始語言的文件應被視為權威來源。對於重要信息,建議使用專業人工翻譯。我們對因使用此翻譯而引起的任何誤解或錯誤解釋不承擔責任。\n" ] } ], "metadata": { "language_info": { "name": "python" }, "orig_nbformat": 4, "coopTranslator": { "original_hash": "153d9e417e079bf62f8f693002d0deaf", "translation_date": "2025-08-31T09:49:51+00:00", "source_file": "lessons/4-ComputerVision/06-IntroCV/lab/MovementDetection.ipynb", "language_code": "hk" } }, "nbformat": 4, "nbformat_minor": 2 }