Open Access

ARTICLE

Robust Detection for Fisheye Camera Based on Contrastive Learning

Junzhe Zhang¹, Lei Tang^1,*, Xin Zhou²

1 School of Information Engineering, Chang’an University, Xi’an, 710064, China
2 College of Automation, Northwestern Polytechnical University, Xi’an, 710129, China

* Corresponding Author: Lei Tang. Email:

Computers, Materials & Continua 2025, 83(2), 2643-2658. https://doi.org/10.32604/cmc.2025.061690

Received 30 November 2024; Accepted 19 February 2025; Issue published 16 April 2025

Abstract

Fisheye cameras offer a significantly larger field of view compared to conventional cameras, making them valuable tools in the field of computer vision. However, their unique optical characteristics often lead to image distortions, which pose challenges for object detection tasks. To address this issue, we propose Yolo-CaSKA (Yolo with Contrastive Learning and Selective Kernel Attention), a novel training method that enhances object detection on fisheye camera images. The standard image and the corresponding distorted fisheye image pairs are used as positive samples, and the rest of the image pairs are used as negative samples, which are guided by contrastive learning to help the distorted images find the feature vectors of the corresponding normal images, to improve the detection accuracy. Additionally, we incorporate the Selective Kernel (SK) attention module to focus on regions prone to false detections, such as image edges and blind spots. Finally, the on the augmented KITTI dataset is improved by over the original Yolov8, while the on the WoodScape dataset is improved by compared to OmniDet. The results demonstrate the performance of our proposed model for object detection on fisheye images.

---

Keywords

---