EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Multi-Scale Feature Fusion Based Lightweight Vehicle Target Detection Network on Aerial Optical Images

Chengrui Yu, Xiaonan Jiang, Fanlu Wu, Yao Fu, Junyan Pei, Yu Zhang, Xiangzhi Li, Tianjiao Fu

Remote Sensing · 29.09.2024 · 16 (19) · 3637

DOI: 10.3390/rs16193637 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 29.09.2024. Verfasst von Chengrui Yu und 7 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program of China, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Vehicle detection with optical remote sensing images has become widely applied in recent years. However, the following challenges have remained unsolved during remote sensing vehicle target detection. These challenges include the dense and arbitrary angles at which vehicles are distributed and which make it difficult to detect them; the extensive model parameter (Param) that blocks real-time detection; the large differences between larger vehicles in terms of their features, which lead to a reduced detection precision; and the way in which the distribution in vehicle datasets is unbalanced and thus not conducive to training. First, this paper constructs a small dataset of vehicles, MiVehicle. This dataset includes 3000 corresponding infrared and visible image pairs, offering a more balanced distribution. In the infrared part of the dataset, the proportions of different vehicle types are as follows: cars, 48%; buses, 19%; trucks, 15%; freight, cars 10%; and vans, 8%. Second, we choose the rotated box mechanism for detection with the model and we build a new vehicle detector, ML-Det, with a novel multi-scale feature fusion triple cross-criss FPN (TCFPN), which can effectively capture the vehicle features in three different positions with an mAP improvement of 1.97%. Moreover, we propose LKC–INVO, which allows involution to couple the structure of multiple large kernel convolutions, resulting in an mAP increase of 2.86%. We also introduce a novel C2F_ContextGuided module with global context perception, which enhances the perception ability of the model in the global scope and minimizes model Params. Eventually, we propose an assemble–disperse attention module to aggregate local features so as to improve the performance. Overall, ML-Det achieved a 3.22% improvement in accuracy while keeping Params almost unchanged. In the self-built small MiVehicle dataset, we achieved 70.44% on visible images and 79.12% on infrared images with 20.1 GFLOPS, 78.8 FPS, and 7.91 M. Additionally, we trained and tested our model on the following public datasets: UAS-AOD and DOTA. ML-Det was found to be ahead of many other advanced target detection algorithms.

Förderung

  • National Key R&D Program of China
  • National Natural Science Foundation of China

Zitieren

APA

Yu, C., Jiang, X., Wu, F., Fu, Y., Pei, J., Zhang, Y., Li, X., & Fu, T. (2024). A Multi-Scale Feature Fusion Based Lightweight Vehicle Target Detection Network on Aerial Optical Images. Remote Sensing, 16(19), 3637. https://doi.org/10.3390/rs16193637

Vancouver

Yu C, Jiang X, Wu F, Fu Y, Pei J, Zhang Y, et al. A Multi-Scale Feature Fusion Based Lightweight Vehicle Target Detection Network on Aerial Optical Images. Remote Sensing. 2024;16(19):3637. doi:10.3390/rs16193637

BibTeX
@article{Yu2024,
  author = {Yu, Chengrui and Jiang, Xiaonan and Wu, Fanlu and Fu, Yao and Pei, Junyan and Zhang, Yu and Li, Xiangzhi and Fu, Tianjiao},
  title = {A Multi-Scale Feature Fusion Based Lightweight Vehicle Target Detection Network on Aerial Optical Images},
  journal = {Remote Sensing},
  year = {2024},
  volume = {16},
  number = {19},
  pages = {3637},
  doi = {10.3390/rs16193637}
}
Kostenlos starten →