FM-智慧商場之多攝影機電腦視覺技術概論(IoT系列課程)
Teacher: 莊仁輝
2022/06/10~2024/12/31
Registration deadline:2024/12/31

Summary

隨選隨學!Let's have fun with this MOOC:智慧商場之多攝影機電腦視覺技術概論(IoT系列課程)!

(本課程隨選隨學,僅提供課程影片,無授課教師與助教參與,也不開放測驗、討論區、與證書等功能。)


本課程將對於可結合物聯網應用於智慧商場之先進多人定位系統之電腦視覺技術進行介紹與探討。相關技術可以定位之方式分成:(1)以重建三維人體(水平截面/垂直線段取樣)進行定位,(2)以人體模型(矩形立牌陣列)的佔有機率(面積)來定位,(3)整合前兩種方法的混合方法。本課程將介紹以上各類技術之發展趨勢,包括人物相互遮蔽條件下之定位正確性、不同影像處理方法之穩定性與執行速度各方面提升系統效能之選項。此外,本課程亦將介紹至少兩種可結合物聯網應用之多攝影機系統之校正方法,以及不同校正方法於正確性與實施方便性之比較。學習本課程之學員,可以獲得多人定位系統所需之電腦視覺與影像處理相關背景知識以及最新的技術發展趨勢,而對後續於相關領域之學習或產品研發(如商場人流與熱點分析、人群行為安全監控、購物動線最佳化等)亦將有莫大的幫助。

本課程於 2016 年製作,部分技術可能已有更新,請各位學員隨時留意最新技術。

Course Object

獲得多人定位系統所需之電腦視覺與影像處理相關背景知識以及最新的技術發展趨勢。對後續於相關領域之學習或產品研發(如商場人流與熱點分析、人群行為安全監控、購物動線最佳化等)亦將有莫大的幫助。

Course Teacher Intro

莊仁輝 老師  國立陽明交通大學 資訊工程學系 教授

莊仁輝老師,目前為國立陽明交通大學資訊工程學系教授兼教務長,研究專長為訊號與影像處理、電腦視覺 VLSI設計,莊教授帶領的團隊持續研發先進的電腦視覺技術,已獲得數十件國內外專利與業界與研發單位共同建構出產學研體系,提升台灣在智慧型環境(尤其是視覺安全監控方面)之研發技術。該團隊於2013年獲得第三屆經濟部國家產業創新獎之年度科專楷模獎。

Course Schedule

Unit 1:人物定位的基本構思和介紹基於垂直消失點的人物定位方法

Unit 2:使用足跡分析加速基於垂直消失點的人物定位方法

Unit 3:介紹基於人物模型人物定位方法並一般化此方法

Unit 4:加速基於人物模型人物定位方法

Unit 5:攝影機校正

Unit 6:人物定位和攝影機校正實作流程

Course Grade

本課程不開放測驗與證書。

Grade Required


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

Course Ability

具備基礎計算機網路概論之相關知識

Course Suggest

  • 參考書目:

[1] L M. Fuentes and S. A. Velastin, “People tracking in surveillance applications,” in Proc. the 2nd IEEE Int. workshop on PETS, 2001.

[2] http://online.wsj.com/news/articles/SB10001424052702303332904579230401030827722

[3] S. M. Khan and M. Shah, “Tracking multiple occluding people by localizing on multiple scene planes,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 31, no. 3, pp. 505–519, 2009.

[4] K.-H. Lo and J.-H. Chuang, “Vanishing point-based line sampling for efficient axis-based people localization,” in Proc. IEEE Int. Conf. on Image Processing, 2011.

[5] K.-H. Lo and J.-H. Chuang, "Vanishing point-based line sampling for real-time people localization," IEEE Transactions on Circuits and Systems for Video Technology, vol.23, no.7, pp.1209–1223, 2013.

[6] K.-H. Lo and J.-H. Chuang, “View-invariant measure of line correspondence and its application in people localization,” in Proc. IEEE Int. Conf. on Image Processing, 2012.

[7] K.-H. Lo C.-J. Wang, J.-H. Chuang, and H.-T. Chen, “Acceleration of vanishing point-based line sampling scheme for people localization and height estimation via 3D line sampling,” in Proc. IEEE Int. Conf. on Pattern Recognition, 2012.

[8] F. Fleuret, J. Berclaz, R. Lengagne, and P. Fua, “Multicamera people tracking with a probabilistic occupancy map,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 30, no. 2, pp. 267–282, 2008.

[9] Y.-S. Lin, K.-H. Lo, H.-T. Chen, and J.-H. Chuang, “VP-transform: a novel vanishing point-based image transform for enhancement of people localization,” in Proc. IEEE Int. Conf. on Multimedia and Expo, 2013.

[10] Y.-S. Lin, K.-H. Lo, H.-T. Chen, and J.-H. Chuang, “Vanishing point-based image transforms for enhancement of probabilistic occupancy map-based people localization,” IEEE Transactions on Image Processing, vol. 23, no. 12, pp. 5586–5598, 2014.

[11] Y.-S. Lin, H.-T. Chen, J.-N. Hwang, C.-J. Hsiao, and J.-H. Chuang, “1-D integral image for enhancing efficiency and effectiveness of probabilistic occupancy map-based people localization approach,” in Proc. Int. Conf. on Digital Image Processing, 2016.

[12] Y.-S. Lin, H.-T. Chen, and J.-H. Chuang, "An efficient probabilistic occupancy map-based people localization approach," in Proc. IEEE Int. Conf. on Visual Communications and Image Processing, 2015.

[13] Yen-Chou Tai, Yong-Sheng Chen, and Jen-Hui Chuang, “Efficient calibration of multi-plane homography using laser levels,” in Proc. IEEE Int. Conf. on Image Processing, 2015.