Acta Optica Sinica, Volume. 38, Issue 7, 0710004(2018)
Design of Augmented Reality Head-up Display System Based on Image Semantic Segmentation
Figures & Tables(6)
Fig. 3. Training process of improved SSD network. (a) Relationship between iteration number and training loss; (b) relationship between iteration number and accuracy
Fig. 4. Results of semantic segmentation and virtual-real registration in different environments. (a) Original images; (b) method of Ref.[12]; (c) proposed method; (d) virtual-real registration images
Fig. 5. RMS error of virtual-real registration and comparison in different directions. (a) x; (b) y; (c) z
Table 1. Evaluation of network output results and comparison of average processing time
View tableTable 1. Evaluation of network output results and comparison of average processing time
Algorithm MPA /% MIoU /% t /(ms·frame-1)DeepLab-CRF[ 13 ]76.2 70.8 436 SegNet[ 12 ]70.1 66.4 515 Proposed 77.8 72.1 410
Tools
Get Citation
Copy Citation Text
Zhe An, Xiping Xu, Jinhua Yang, Yang Qiao, Yang Liu. Design of Augmented Reality Head-up Display System Based on Image Semantic Segmentation[J]. Acta Optica Sinica, 2018, 38(7): 0710004
Paper Information
Category: Image Processing
Received: Jan. 25, 2018
Accepted: --
Published Online: Sep. 5, 2018
The Author Email: An Zhe (2016200046@mails.cus)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20