Enhancing Rotated Object Detection via Anisotropic Gaussian Bounding Box and Bhattacharyya Distance

2025-10-18

AI Summary

This paper addresses inaccurate orientation modeling and large localization errors in rotated object detection. To this end, we propose a rotation-invariant detection method based on anisotropic Gaussian bounding boxes and the Bhattacharyya distance. Specifically, we model rotated bounding boxes using anisotropic Gaussian distributions to explicitly encode object aspect ratios and orientation characteristics. Furthermore, we design a Bhattacharyya-distance-based loss function that jointly optimizes rotation angle and geometric shape, thereby enhancing orientation sensitivity and geometric consistency. The method is seamlessly integrated into mainstream detection frameworks and supports end-to-end training. Extensive experiments on remote sensing and aerial imagery benchmarks—including DOTA and HRSC2016—demonstrate significant improvements in mean Average Precision (mAP) over existing state-of-the-art methods, validating the proposed approach’s accuracy, robustness, and generalization capability under complex real-world scenarios.

Technology Category

• Computer Vision: Object Detection & Categorization
• Intelligent Robots: Localization, Mapping, and Navigation
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Detecting rotated objects accurately and efficiently is a significant challenge in computer vision, particularly in applications such as aerial imagery, remote sensing, and autonomous driving. Although traditional object detection frameworks are effective for axis-aligned objects, they often underperform in scenarios involving rotated objects due to their limitations in capturing orientation variations. This paper introduces an improved loss function aimed at enhancing detection accuracy and robustness by leveraging the Gaussian bounding box representation and Bhattacharyya distance. In addition, we advocate for the use of an anisotropic Gaussian representation to address the issues associated with isotropic variance in square-like objects. Our proposed method addresses these challenges by incorporating a rotation-invariant loss function that effectively captures the geometric properties of rotated objects. We integrate this proposed loss function into state-of-the-art deep learning-based rotated object detection detectors, and extensive experiments demonstrated significant improvements in mean Average Precision metrics compared to existing methods. The results highlight the potential of our approach to establish new benchmark in rotated object detection, with implications for a wide range of applications requiring precise and reliable object localization irrespective of orientation.

Problem

• Improving rotated object detection accuracy in computer vision applications
• Addressing limitations of traditional detectors with orientation variations
• Enhancing detection robustness using Gaussian representation and Bhattacharyya distance

Innovation

• Anisotropic Gaussian representation for rotated objects
• Bhattacharyya distance-based rotation-invariant loss function
• Integration into deep learning detectors for improved accuracy