A Large-Scale Dataset and a New Method for RemoteSensing Traffic Object Segmentation

2026-07-04

AI Summary

This work addresses the limitations of existing remote sensing traffic object segmentation datasets, which lack sufficient category and scene diversity to support accurate regional transportation capacity assessment in real-world complex environments. To bridge this gap, we introduce NWPU-Traffic, a large-scale, multi-city, cross-national dataset featuring high-resolution instance-level annotations across four traffic object categories and 49 cities. Furthermore, we propose a robust segmentation method that integrates a spatial-channel feature interaction mechanism with an adaptive decoder to effectively handle challenges posed by scale variation and complex backgrounds. Extensive experiments demonstrate that our approach significantly outperforms current baselines. Both the dataset and code are publicly released to facilitate future research.

Abstract

Remote sensing imagery plays a crucial role in evaluating regional transportation capacity. However, existing segmentation datasets often lack diversity in object categories and scenes, limiting the ability of models to comprehensively evaluate trans portation capacity in real-world scenes. To alleviate this gap, we construct a large-scale and diverse dataset for transportation object segmentation, named as NWPU-Traffic. This dataset encompass four traffic object categories (car, airplane, ship, and train) and a wide range of scenes from 49 cities across 7 countries, with instance-level annotations to ensure precise segmentation of individual objects, which bridges critical shortcomings in resolution and scene diversity in existing datasets. Leveraging this dataset, we establish a benchmark with several popular segmentation networks. Furthermore, we propose a novel segmentation method that leverages spatial-channel preserving feature interaction and an adaptive feature decoder, enabling robust segmentation across varying scales and complex environments. Extensive experiments and ablation studies validate the effectiveness of our approach. The dataset and code are publicly available at https://github.com/CVer-Yang/NWPU-Traffic.

Problem

• remote sensing
• traffic object segmentation
• dataset diversity
• scene variability
• transportation capacity evaluation

Innovation

• remote sensing
• traffic object segmentation
• large-scale dataset
• feature interaction
• adaptive decoder