Infrared and Laser Engineering, Volume. 50, Issue 11, 20210206(2021)
Target recognition based on multi-view infrared images
Figures & Tables(7)
Fig. 1. Flowchart of infrared image target recognition based on multi-view
Fig. 3. Performance comparison of different methods on noisy samples
Fig. 4. Performance comparison of different methods on occluded samples
Table 1. Similarity matrix of multi-view infrared images
View tableView in ArticleTable 1. Similarity matrix of multi-view infrared images
${I_1}$ ${I_2}$ $ \cdots $ ${I_N}$ ${I_1}$ ${c_{11}}$ ${c_{12}}$ $ \cdots $ ${c_{1N}}$ ${I_2}$ ${c_{21}}$ ${c_{22}}$ $ \cdots $ ${c_{2N}}$ $ \vdots $ $ \vdots $ $ \vdots $ $ \ddots $ $ \vdots $ ${I_N}$ ${c_{N1}}$ ${c_{N2}}$ $ \cdots $ ${c_{NN}}$
Table 2. Recognition results of the proposed method on the original samples of four targets
View tableView in ArticleTable 2. Recognition results of the proposed method on the original samples of four targets
Class Bus Car Truck Van Recognition rate Bus 1576 5 6 13 98.50% Car 9 2674 7 10 99.04% Truck 4 1 592 3 98.67% Van 2 3 6 889 98.78% Average recognition rate 98.81%
Table 3. Performance comparison of different methods on orginal samples
View tableView in ArticleTable 3. Performance comparison of different methods on orginal samples
Methods Average recognition rate Proposed 98.81% SRC 97.68% SVM 97.04% HOG 97.23% Deep features 98.02%
Tools
Get Citation
Copy Citation Text
Lu Zhao, Sen Xiong. Target recognition based on multi-view infrared images[J]. Infrared and Laser Engineering, 2021, 50(11): 20210206
Paper Information
Category: Image processing
Received: Mar. 30, 2021
Accepted: --
Published Online: Dec. 7, 2021
The Author Email:
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20