ExposureEngine: Oriented Logo Detection and Sponsor Visibility Analytics in Sports Broadcasts

2025-10-06

AI Summary

Traditional sponsor visibility analysis relies on manual annotation or axis-aligned bounding boxes (HBBs), which fail to accurately localize rotated or skewed logos in sports broadcasts due to camera motion and perspective distortion, leading to unreliable visibility estimation. To address this, we propose the first end-to-end oriented logo detection and analytics system tailored for sports broadcasting. Our method employs an oriented bounding box (OBB)-based object detection framework, augmented with a viewpoint-aware module to rectify perspective distortion and a language-driven agent layer enabling natural-language queries and interpretable report generation. Evaluated on a dataset from Sweden’s top-tier football league, our model achieves an mAP@0.5 of 0.859, with precision of 0.96 and recall of 0.87—significantly improving localization accuracy for rotated logos. The system enables fully automated, auditable quantification of key sponsorship metrics, including exposure duration and screen coverage area.

Technology Category

• Computer Vision: Language and Vision
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Search and Optimization: Evaluation and Analysis

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Web traffic and log analysis

Abstract

Quantifying sponsor visibility in sports broadcasts is a critical marketing task traditionally hindered by manual, subjective, and unscalable analysis methods. While automated systems offer an alternative, their reliance on axis-aligned Horizontal Bounding Box (HBB) leads to inaccurate exposuremetrics when logos appear rotated or skewed due to dynamic camera angles and perspective distortions. This paper introduces ExposureEngine, an end-to-end system designed for accurate, rotation-aware sponsor visibility analytics in sports broadcasts, demonstrated in a soccer case study. Our approach predicts Oriented Bounding Box (OBB) to provide a geometrically precise fit to each logo regardless of the orientation on-screen. To train and evaluate our detector, we developed a new dataset comprising 1,103 frames from Swedish elite soccer, featuring 670 unique sponsor logos annotated with OBBs. Our model achieves a mean Average Precision (mAP@0.5) of 0.859, with a precision of 0.96 and recall of 0.87, demonstrating robust performance in localizing logos under diverse broadcast conditions. The system integrates these detections into an analytical pipeline that calculates precise visibility metrics, such as exposure duration and on-screen coverage. Furthermore, we incorporate a language-driven agentic layer, enabling users to generate reports, summaries, and media content through natural language queries. The complete system, including the dataset and the analytics dashboard, provides a comprehensive solution for auditable and interpretable sponsor measurement in sports media. An overview of the ExposureEngine is available online: https://youtu.be/tRw6OBISuW4 .

Problem

• Detecting rotated sponsor logos in sports broadcasts accurately
• Quantifying sponsor visibility with precise exposure metrics automatically
• Overcoming limitations of manual analysis and axis-aligned bounding boxes

Innovation

• Uses oriented bounding boxes for logo detection
• Integrates language-driven agent for querying
• Provides comprehensive visibility metrics analytics