Abstract

Dense analogs intelligent recognition (DAIR) has many potential applications in various fields as a new cross-disciplinary frontier of artificial intelligence and optical technology. However, with extensive application of fisheye lenses, inherent distortions in fisheye images have brought new challenges to DAIR. To solve this problem, we propose and experimentally demonstrate a partially featured points calibrating method that needs only correction of central points of the bounding boxes output by a convolutional neural network (CNN). The key to our method is a central-coordinate calibrating and clustering algorithm (CCCCA) based on a hemispheric double longitude projection model. Experimental results show that the CCCCA reduces the classification error rate by 6.05%, enhancing the classification accuracy of distorted DAIR up to 99.31%. Such classification accuracy is about 2.74% higher than that achieved by the mainstream online hard example mining algorithm, effectively modifying recognition errors induced by the CNN.

© 2022 Optica Publishing Group

Key point calibrating and clustering for hard example mining of dense analogs in the fish-eye lens

Min Zeng, Zhi Chen, and Shengjian Wu
J. Opt. Soc. Am. A 41(2) 229-240 (2024)

Method for calibrating the fisheye distortion center

Fuyu Huang, Yongzhong Wang, Xueju Shen, Chao Lin, and Yudan Chen
Appl. Opt. 51(34) 8169-8176 (2012)

ASI aurora search: an attempt of intelligent image processing for circular fisheye lens

Xi Yang, Xinbo Gao, Bin Song, Nannan Wang, and Dong Yang
Opt. Express 26(7) 7985-8000 (2018)

Fisheye lens calibration using virtual grid

Aymen Arfaoui and Simon Thibault
Appl. Opt. 52(12) 2577-2583 (2013)

Real-time pose estimation for an underwater object combined with deep learning and prior information

Xianwei Ge, Shukai Chi, Wei Jia, and Ke Jiang
Appl. Opt. 61(24) 7108-7118 (2022)