Approximate Supervised Object Distance Estimation on Unmanned Surface Vehicles

2025-01-09

AI Summary

To address the high cost, limited visibility, and complex calibration associated with conventional distance estimation for unmanned surface vehicles (USVs)—which rely on expensive sensors such as LiDAR, radar, or stereo cameras—this paper proposes a low-cost, supervised dual-task distance estimation method based on object detection. We innovatively extend mainstream single-stage detectors (e.g., YOLO and RetinaNet) by introducing a dedicated distance regression branch, enabling joint optimization of object localization and metric distance prediction from monocular imagery alone, without auxiliary hardware. Leveraging a custom-built maritime object image dataset captured under realistic sea conditions, our approach achieves real-time distance estimation for vessels, buoys, and other maritime obstacles, attaining an average relative error of less than 15%. The method has been successfully integrated into an operational marine auxiliary early-warning system, significantly enhancing the safety and deployability of USVs in near-shore operations.

Technology Category

• Intelligent Robots: State Estimation
• Computer Vision: Object Detection & Categorization
• Search and Optimization: Distributed Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Unmanned surface vehicles (USVs) and boats are increasingly important in maritime operations, yet their deployment is limited due to costly sensors and complexity. LiDAR, radar, and depth cameras are either costly, yield sparse point clouds or are noisy, and require extensive calibration. Here, we introduce a novel approach for approximate distance estimation in USVs using supervised object detection. We collected a dataset comprising images with manually annotated bounding boxes and corresponding distance measurements. Leveraging this data, we propose a specialized branch of an object detection model, not only to detect objects but also to predict their distances from the USV. This method offers a cost-efficient and intuitive alternative to conventional distance measurement techniques, aligning more closely with human estimation capabilities. We demonstrate its application in a marine assistance system that alerts operators to nearby objects such as boats, buoys, or other waterborne hazards.

Problem

• Unmanned Surface Vehicles
• Distance Estimation
• Cost-effective Solutions

Innovation

• Supervised Object Detection
• Distance Estimation
• Unmanned Surface Vessels (USVs) Perception