Topic · unordered discovery
Computer Vision
Image and video understanding systems.
AI and ML
Projects
Featured Project
YOLO Right-of-Way Recognition
結合物件偵測與追蹤，把交通影片中的不禮讓行人情境轉成可檢查事件的大學畢業專題。
Outcome YOLOv8 detections and DeepSORT tracks are combined with scene rules to mark possible right-of-way violations across a video, not just a single frame.
View project profileCompleted deep-learning course project
LadaGAN–EfficientNetV2
從人臉生成、可追蹤 synthetic dataset 到判別器評估的完整深度學習實驗。
Outcome The experiment preserves 30 checkpoints, 150,000 synthetic faces, and the real/fake dataset construction used to train the discriminator.
View project profileWriting
讓「不禮讓行人」變成可追蹤的事件：YOLOv8 × DeepSORT
介紹一個以 YOLOv8、DeepSORT、OpenCV 與 PyQt5 組成的交通違規偵測工具，從影片輸入到標記結果。
Object DetectionComputer VisionOpenCV
LadaGAN 做得太逼真之後：一場生成器與判別器的拉鋸
東華大學資工系深度學習基石與實務第二個作業：從 LadaGAN 人臉生成、150K 合成資料，到 EfficientNetV2-B1 判別器的完整實驗記錄。
GANComputer VisionDeep Learning
Related Series
目前沒有以此 Topic 組織的 Series。