Abstract

Recent years have witnessed widespread applications of the fish-eye lens with a wide field-of-view. However, its inherent distortion poses a big challenge to the intelligent recognition of dense analogs (IRDA) by convolutional neural networks (CNN). The major bottleneck of existing CNN models lies in their limited modeling capacity for distorted objects in fish-eye images, leading to the misclassification of hard examples. To further improve the accuracy of IRDA, we propose a novel key point calibrating and clustering (KPCC) algorithm based on the hemispherical projection model. Our method can effectively correct the hard example misclassification predicted by the CNN, significantly enhancing the performance of the IRDA. The experiments show that, as a light-weight computation calibrating and stable adaptive clustering method, the KPCC increases the precision and recall rate of IRDA on the intelligent retail dataset by 8.55% and 8.07%, respectively; compared with the classic Focalloss, QFocalloss, and OHEM (online hard example mining), it can mine hard examples more sufficiently, especially in the scene of distorted dense analog detection.

© 2024 Optica Publishing Group

Distorted dense analogs intelligent recognition in fisheye lenses by partially featured points calibrating and clustering

Min Zeng, Zhi Chen, and Fang Li
Appl. Opt. 61(7) D85-D91 (2022)

Dense stereo fish-eye images using a modified hemispherical ASW algorithm

Yakun Zhang, Haibin Li, Wenming Zhang, and Cunjun Xiao
J. Opt. Soc. Am. A 38(4) 476-487 (2021)

High precision two-step calibration method for the fish-eye camera

Bo Tu, Lu Liu, Yihui Liu, Ye Jin, and Junxiong Tang
Appl. Opt. 52(7) C37-C42 (2013)

Bootstrap geometric ground calibration method for wide angle star sensors

Samuel Teague and Javaan Chahl
J. Opt. Soc. Am. A 41(4) 654-663 (2024)

Three-dimensional simulation method of fish-eye lens distortion for a vehicle backup rear-view camera

Daehee Kim and Joonki Paik
J. Opt. Soc. Am. A 32(7) 1337-1343 (2015)