# Improved Person Detection on Omnidirectional Images with Non-maxima Suppression

arXiv: https://arxiv.org/abs/1805.08503 · HTML: https://mlsanity.com/paper/1805.08503/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2018.

## Built on by (most cited first, 6 of 6)

- [Large-Scale Person Detection and Localization using Overhead Fisheye Cameras](https://mlsanity.com/paper/2307.08252/) (2023)
- [OmniPD: One-Step Person Detection in Top-View Omnidirectional Indoor Scenes](https://mlsanity.com/paper/2204.06846/) (2022)
- [Applications of Deep Learning for Top-View Omnidirectional Imaging: A Survey](https://mlsanity.com/paper/2304.08193/) (2023)
- [Segmentation-Based Bounding Box Generation for Omnidirectional Pedestrian Detection](https://mlsanity.com/paper/2104.13764/) (2021)
- [Panoramic Distortion-Aware Tokenization for Person Detection and Localization in Overhead Fisheye Images](https://mlsanity.com/paper/2503.14228/) (2025)
- [PMOF: A Dataset and Benchmark for Passenger Monitoring Using Overhead Fisheye Cameras](https://mlsanity.com/paper/2606.13910/) (2026)

## Abstract (arXiv)

We propose a person detector on omnidirectional images, an accurate method to generate minimal enclosing rectangles of persons. The basic idea is to adapt the qualitative detection performance of a convolutional neural network based method, namely YOLOv2 to fish-eye images. The design of our approach picks up the idea of a state-of-the-art object detector and highly overlapping areas of images with their regions of interests. This overlap reduces the number of false negatives. Based on the raw bounding boxes of the detector we fine-tuned overlapping bounding boxes by three approaches: non-maximum suppression, soft non-maximum suppression and soft non-maximum suppression with Gaussian smoothing. The evaluation was done on the PIROPO database and an own annotated Flat dataset, supplemented with bounding boxes on omnidirectional images. We achieve an average precision of 64.4 % with YOLOv2 for the class person on PIROPO and 77.6 % on Flat. For this purpose we fine-tuned the soft non-maximum suppression with Gaussian smoothing.