Maritime Computer Vision Workshop @ CVPR 2026

Challenges / Vision-to-Chart Data Association

Vision-to-Chart Data Association

Quick links: Dataset download Submit (coming soon) Leaderboards (coming soon) Ask for help

Quick Start

1. Download the dataset from the dataset page .
2. Train your model on the provided dataset. Find starter code here (coming soon).
3. Upload your model exported to ONNX to be evaluated by us on the test split, see upload page (coming soon).

Overview

This challenge is about augmenting navigation data for maritime vehicles (boats). Given an image captured by boat-mounted camera, and chart markers of nearby navigational aids (buoys), the task is to identify visible buoys and match them with their corresponding chart markers. The goal is to maximize detected buoys as well as correct matches while minimizing localization error of detected buoys and wrong detections. The challenge is based on the paper "Real-Time Fusion of Visual and Chart Data for Enhanced Maritime Vision".

Task

The task is to develop a deep learning model capable of detecting buoys in a monocular image, and matching them to associated chart positions. Models will be evaluated on both detection and matching accuracy as well as localization error.

Dataset

The dataset consists of 6115 entries, with each entry containing a single RGB-based image, a variable amount of quieries, and a variable amount of labels. Each query denotes chart data of a nearby buoy, and has the format: (query id, distance to ship [meters], bearing from ship centerline [degrees], longitude, latidude). Each label denotes a nearby buoy visible in the image, and has the format (query id, BB center x, BB center y, BB width, BB height), where BB location specification follows the YOLO format and denotes the corresponding queries position in the image. Note that this dataset contains entries where no buoy is visible.

Evaluation metrics

The submitted models are evaluated on a test set that is not publicly available.
The following metrics are employed to assess model capabilities:

• Detection: Precision and Recall of detected buoys
• Matching: Average IoU of detected buoys BB
• Overall: Mean of detection and matching performance

Participate

To participate in the challenge follow these steps:

1. Download the dataset from the dataset page.
2. Train a deep learning model on the dataset.
3. Export your trained model to ONNX and submit it via the upload page (coming soon). We will subsequently evaluate it on the test split

Get Started

To help you get started and provide a brief introduction to the topic, we have developed a fusion transformer based on DETR which you can find here (TBD).

Model Submission

In order to submit your model you must first export it to ONNX format. A Python script is provided for this (coming soon)

The submitted ONNX files must meet the following requirements:

• Model Parameters not exceeding 50 million
• Exported for image size of 1024x1024
• Output tensor Format: TBD

The submitted models are tested on rescaled images of size 1024x1024. The output tensor of the model adheres to the YOLO Format, where x,y are the absolute center coordinates, w,h are the absolute bounding box dimensions and objectness, class are used to compute the confidence score. This tensor is extended by the distance value. We expect this value to be already rescaled to meters (not normalized).

To verify the validity of your ONNX export, you can use the testscript_onnx.py (coming soon).

Terms and Conditions

• Submissions must be made before the challenge deadline listed on the dates page.
• Submissions are limited to one per day. Failed submissions do not count towards this limit.
• The winner is determined by the highest score on the 'overall' metric.

If you have any questions, please join the MaCVi Support forum.