A Multimodal Data Collaborative Intelligent Detection and 3D Positioning Method for Ships at Sea

By employing a multimodal data collaborative intelligent detection method for maritime vessels, combining visible light images, thermal imaging, and lidar data, all-weather, highly robust, and high-precision maritime target detection and 3D positioning are achieved. This overcomes the limitations of single-modal perception and the inadequacy of multimodal fusion in existing technologies, and meets the real-time and computing resource requirements of intelligent navigation systems.

CN121259288BActive Publication Date: 2026-06-30HARBIN INST OF TECH AT WEIHAI +1
1 Cites 0 Cited by

Patent Information

Application Number
CN202511396099.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-09-28
Publication Date
2026-06-30
Estimated Expiration
2045-09-28

AI Technical Summary

Technical Problem

Existing maritime target detection systems mostly rely on single-modal perception methods, which are difficult to cope with diverse scenarios under complex sea conditions, leading to missed or false detections of targets. Furthermore, existing multimodal fusion methods lack effective cross-modal consistency modeling, making it difficult to fully explore the complementary characteristics of each modality. In addition, deep learning models are difficult to meet the needs of intelligent navigation systems in terms of real-time performance and computational resource consumption.

Method used

A multimodal data collaborative intelligent detection method for ships at sea is adopted. Through multi-sensor synchronous acquisition, refined preprocessing, dynamic weighted fusion and multi-tracking mechanism collaborative strategy, combined with visible light images, thermal imaging and lidar data, the accurate three-dimensional positioning and motion state prediction of ship targets can be achieved.

Benefits of technology

It achieves all-weather, highly robust, and high-precision maritime target detection and 3D positioning, effectively addressing the challenges of target identification in complex sea conditions, improving the accuracy and real-time performance of detection, and meeting the engineering deployment requirements of intelligent navigation systems.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

This application discloses a multimodal data collaborative intelligent detection and 3D localization method for maritime vessels, comprising: fine preprocessing of collected multi-source heterogeneous data and preliminary target detection; dynamic weighted fusion of the preprocessed multi-source heterogeneous data, combined with depth data from lidar, to achieve accurate coordinate recovery of the vessel target in 3D space; and prediction and updating of the motion state of the identified target based on a multi-tracking mechanism collaborative strategy. By fully utilizing the rich texture information of visible light images, the anti-interference capability of thermal imaging, and the precise spatial depth data of lidar through multimodal data perception and preliminary processing, heterogeneous data deep fusion and 3D localization, and advanced multi-target continuous tracking and state estimation, this method integrates a multi-tracking mechanism collaborative strategy to predict and update the motion state of the identified target, effectively addressing the problem of tracking interruption caused by nonlinear motion or temporary occlusion of maritime targets.
Need to check novelty before this filing date? Find Prior Art