A method for generating images of spilled materials on highways from an aerial perspective

By separating road and vehicle areas using a segmentation model and combining it with a diffusion model to generate spill images that are in harmony with the environment, the problems of low efficiency, high cost, and insufficient diversity in the generation of spill data from aerial perspectives are solved, and high-quality automatic data generation and model training support are achieved.

CN121527653BActive Publication Date: 2026-06-30FUJIAN EXPRESSWAY TECH INNOVATION RES INST CO LTD
2 Cites 0 Cited by

Patent Information

Application Number
CN202511657934.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-11-13
Publication Date
2026-06-30
Estimated Expiration
2045-11-13

AI Technical Summary

Technical Problem

Existing technologies struggle to efficiently and accurately generate aerial images of debris scattered along highways, resulting in scarce and inefficient training data for detection models, high costs, and inefficient manual synthesis methods that are prone to visual inconsistencies.

Method used

The system uses pre-trained semantic segmentation and instance segmentation models to separate road and vehicle regions, generates random-shaped polygonal masks, and combines a diffusion model with textual prompts to generate spill images that are in harmony with the surrounding environment, and automatically generates annotation files.

Benefits of technology

It significantly improves the scene realism and adaptability of synthetic images, reduces labor costs, enriches the diversity of training data, ensures the quality of synthetic images, and helps improve the detection accuracy of models.

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

Abstract

This invention relates to the field of intelligent transportation technology, and in particular to a method for generating images of spilled materials on highways from an aerial perspective. The method involves the following steps: road region segmentation using a pre-trained semantic segmentation model to generate a binary mask for the road region; vehicle target elimination using a pre-trained instance segmentation model to generate a vehicle contour mask; spilled material mask generation by generating a randomly shaped polygonal mask within the effective road area; local image preprocessing to perform geometric correction and size standardization on the cropped area; conditional image generation using a diffusion model combined with spatial conditions and textual prompts to generate a spilled material image adapted to the background; and image fusion and annotation to fuse the spilled material image back into the original image and automatically generate a standard annotation file. This invention can generate visually consistent and realistic composite images of spilled materials, achieve automatic generation of annotation files, significantly reduce data preparation costs, and improve data generation efficiency and diversity.
Need to check novelty before this filing date? Find Prior Art