Abstract

We propose a polarimetric imaging processing method based on feature fusion and apply it to the task of target detection. Four images with distinct polarization orientations were used as one parallel input, and they were fused into a single feature map with richer feature information. We designed a learning feature fusion method using convolutional neural networks (CNNs). The fusion strategy was derived from training. Meanwhile, we generated a dataset involving one original image, four polarization orientation images, ground truth masks, and bounding boxes. The effectiveness of our method was compared to that of conventional deep learning methods. Experimental results revealed that our method gets a 0.80 mean average precision (mAP) and a 0.09 miss rate (MR), which are both better than the conventional deep learning method.

© 2021 Optical Society of America

Target classification of multislit streak tube imaging lidar based on deep learning

Wenhao Li, Shangwei Guo, Yu Zhai, Fei Liu, Zhengchao Lai, and Shaokun Han
Appl. Opt. 60(28) 8809-8817 (2021)

Deep learning polarimetric three-dimensional integral imaging object recognition in adverse environmental conditions

Kashif Usmani, Gokul Krishnan, Timothy O’Connor, and Bahram Javidi
Opt. Express 29(8) 12215-12228 (2021)

Mid-fusion of road scene polarization images on pretrained RGB neural networks

Khalid Omer and Meredith Kupinski
J. Opt. Soc. Am. A 38(4) 515-525 (2021)

Polarimetric imaging detection using a convolutional neural network with three-dimensional and two-dimensional convolutional layers

Rui Sun, Xiaobing Sun, Feinan Chen, Qiang Song, and Hao Pan
Appl. Opt. 59(1) 151-155 (2020)

Learning-based denoising for polarimetric images

Xiaobo Li, Haiyu Li, Yang Lin, Jianhua Guo, Jingyu Yang, Huanjing Yue, Kun Li, Chuan Li, Zhenzhou Cheng, Haofeng Hu, and Tiegen Liu
Opt. Express 28(11) 16309-16321 (2020)