paper-with-me

홈 › Papers

A Unified Detection Pipeline for Robust Object Detection in Fisheye-Based Traffic Surveillance

2025-10-22 · Neema Jakisa Owor, Joshua Kofi Asamoah, Tanner Wambui Muturi, Anneliese Jakisa Owor, Blessing Agyei Kyem, Andrews Danyo, Yaw Adu-Gyamfi, Armstrong Aboah arxiv

Fisheye cameras offer an efficient solution for wide-area traffic surveillance by capturing large fields of view from a single vantage point. However, the strong radial distortion and nonuniform resolution inherent in fisheye imagery introduce substantial challenges for standard object detectors, particularly near image boundaries where object appearance is severely degraded. In this work, we present a detection framework designed to operate robustly under these conditions. Our approach employs a simple yet effective pre and post processing pipeline that enhances detection consistency across the image, especially in regions affected by severe distortion. We train several state-of-the-art detection models on the fisheye traffic imagery and combine their outputs through an ensemble strategy to improve overall detection accuracy. Our method achieves an F1 score of0.6366 on the 2025 AI City Challenge Track 4, placing 8thoverall out of 62 teams. These results demonstrate the effectiveness of our framework in addressing issues inherent to fisheye imagery.

📄 PDF Abstract BibTeX arXiv:2510.20016

Code (0)

등록된 구현이 없습니다.

Tasks

Robust Object Detection

Similar Papers 제목 키워드 기반

Datasets for Face and Object Detection in Fisheye Images

2019-06-27 · Jianglin Fu, Ivan V. Bajic, Rodney G. Vaughan

We present two new fisheye image datasets for training face and object detection models: VOC-360 and Wider-360. The fisheye images are created by post-processing regular images collected from two well-known datasets, VOC…

Face DetectionObjectobject-detectionObject Detection+1

3D Object Detection from a Single Fisheye Image Without a Single Fisheye Training Image

2020-03-08 · Elad Plaut, Erez Ben Yaacov, Bat El Shlomo

Existing monocular 3D object detection methods have been demonstrated on rectilinear perspective images and fail in images with alternative projections such as those acquired by fisheye cameras. Previous works on object …

2D Object Detection3D Object DetectionMonocular 3D Object DetectionObject+2

FisheyeSuperPoint: Keypoint Detection and Description Network for Fisheye Images

2021-02-27 · Anna Konrad, Ciarán Eising, Ganesh Sistu, John McDonald 외

Keypoint detection and description is a commonly used building block in computer vision systems particularly for robotics and autonomous driving. However, the majority of techniques to date have focused on standard camer…

Autonomous DrivingHomography EstimationKeypoint Detection

Edge-case Synthesis for Fisheye Object Detection: A Data-centric Perspective

2025-07-22 · Seunghyeon Kim, Kyeongryeol Go arxiv

Fisheye cameras introduce significant distortion and pose unique challenges to object detection models trained on conventional datasets. In this work, we propose a data-centric pipeline that systematically improves detec…

Object Detection

Geometry-Aware Fisheye-LiDAR Fusion for Robust 3D Object Detection in Low-Overlap Setups

2026-06-07 · Xiangzhong Liu, Xihao Wang, Hao Shen arxiv

As autonomous systems expand from capital-intensive robotaxis to cost-sensitive logistics, sensor configurations are increasingly optimized for coverage-per-cost. A prevalent sparse-view setup utilizes dual-fisheye camer…

Robust 3D Object Detection