邁向自動駕駛之AI物件偵測技術
Teacher: 張添烜
公務人員MOOC     

2019/03/29 ~ 2019/12/31
3 Hour/4 Week (Course is Working)

Summary

本課程介紹以深度學習為基礎的物件偵測作法,適用於自動駕駛或輔助駕駛設計。將會介紹各種經典的兩段式與一段式作法,並探討如何加速符合即時應用,與如何增加準確率的各種做法,最後將以實例說明實際應用場景所遇到的問題與效果。

This course will introduce object detection approach based on deep learning, which is suitable autonomous driving applications. The topics will cover two stage approaches, single stage approaches and discuss how to accelerate the execution of these deep learning models to meet real time constraints and improve their accuracy. Finally, a real case will be studied to show their strength and weakness.

Course Object

預期學生修完本門課,能深入了解以深度學習為基礎的物件偵測背後的原理與其限制,並對實際應用所面臨的即時運算與準確率問題,知道如何解決。

After taking this course, students will learn the principle and limitations of the object detection based on deep learning, and know their real time constraints and accuracy problems and their solutions.

Course Teacher Intro

download.php?id=417&area=teacherfiles

ChangTS.jpg
張添烜博士於2000年於交大電子獲得博士學位,於2000~2004任職於創意電子擔任副理,於2004年加入交大電子擔任教職至今。於2009年至比利時IMEC擔任訪問學者。張博士曾獲中國電機工程學會優秀年輕電機工程師獎,台灣IC設計學會傑出年輕學者獎。他的專長為VLSI 設計,深度學習與訊號處理。

Tian-Sheuan Chang received the B.S., M.S., and Ph.D. degrees in electronic engineering from National Chiao-Tung University (NCTU), Hsinchu, Taiwan, in 1993, 1995, and 1999, respectively.

        From 2000 to 2004, he was a Deputy Manager with Global Unichip Corporation, Hsinchu, Taiwan. In 2004, he joined the Department of Electronics Engineering, NCTU, where he is currently a Professor. In 2009, he was a visiting scholar in IMEC, Belgium. His current research interests include system-on-a-chip design, VLSI signal processing, and computer architecture.

  Dr. Chang has received the Excellent Young Electrical Engineer from Chinese Institute of Electrical Engineering in 2007, and the Outstanding Young Scholar from Taiwan IC Design Society in 2010. He has been actively involved in many international conferences as an organizing committee or technical program committee member.

Course Schedule

第1週:Two stage detection 兩段式物件偵測

第2週:Single stage object detection 一段式物件偵測

第3週:Fast object detection and small object detection 快速物件偵測與小物件偵測

第4週:Improvement and real case study 效果增進與實例探討

Course Content

週次

單元主題

第一週

Two stage detection

兩段式物件偵測

1-1 Object Detection

1-2 R-CNN

1-3 Fast R-CNN

1-4 Faster R-CNN

1-5 R-FCN

第二週

Single stage object detection

一段式物件偵測

1-6 Single Stage Object Detection

1-7 SSD: Single Shot MultiBox Detector

1-8 YOLO v2 v3

1-9 RetinaNet

第三週

Fast object detection and small object detection

快速物件偵測與小物件偵測

1-10-1 PVANet

1-10-2 Object Detection at 200FPS

1-11 Comparison

1-12 Mask R-CNN

1-13 Small Object Detection

第四週

Improvement and real case study

效果增進與實例探討

1-14-1 Improvement Over Mask R-CNN and RetinaNet-1

1-14-2 Improvement Over Mask R-CNN and RetinaNet-2

1-15 Uber Event

Course Mode

本課程分為 15 個單元,每週配合課程內容提供隨堂測驗,以幫助學習者快速確認是否瞭解上課內容,另安排各單元測驗用以考核學習成果,考核標準請參見「評分標準說明」。

Course Grade

  • 平時測驗:各單元測驗,共 15 單元,佔 100 %

Grade Required


Course grade pass:60Grade Memo:max grade 100 point

Course Ability

本課程建議具備基本深度學習概念即可,無須太多背景知識,適合所有對深度學習於物件偵測有興趣的學習者修習。