EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MineSDS: A Unified Framework for Small Object Detection and Drivable Area Segmentation for Open-Pit Mining Scenario

Yong Liu, Cheng Li, Jiade Huang, Ming Gao

Sensors · 2023

DOI: 10.3390/s23135977 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Yong Liu und 3 weiteren Autor:innen. Beteiligte Einrichtung: Zhuzhou CRRC Times Electric Co., Ltd., Zhuzhou 412001, China. Hauptthemen laut MEDLINE: Algorithms, Learning. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 38 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, State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To tackle the challenges posed by dense small objects and fuzzy boundaries on unstructured roads in the mining scenario, we proposed an end-to-end small object detection and drivable area segmentation framework for open-pit mining. We employed a convolutional network backbone as a feature extractor for both two tasks, as multi-task learning yielded promising results in autonomous driving perception. To address small object detection, we introduced a lightweight attention module that allowed our network to focus more on the spatial and channel dimensions of small objects without impeding inference time. We also used a convolutional block attention module in the drivable area segmentation subnetwork, which assigned more weight to road boundaries to improve feature mapping capabilities. Furthermore, to improve our network perception accuracy of both tasks, we used weighted summation when designing the loss function. We validated the effectiveness of our approach by testing it on pre-collected mining data which were called Minescape. Our detection results on the Minescape dataset showed 87.8% mAP index, which was 9.3% higher than state-of-the-art algorithms. Our segmentation results surpassed the comparison algorithm by 1 percent in MIoU index. Our experimental results demonstrated that our approach achieves competitive performance.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsLearningData CollectionSpineMining

Stichwörter der Autor:innen

autonomous drivingdrivable area segmentationopen-pit minesmall object detection

Autor:innen und Institutionen

  • Zhuzhou CRRC Times Electric Co., Ltd., Zhuzhou 412001, China.
  • State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body, College of Mechanical and Vehicle Engineering, Hunan University, Changsha 410082, China.

Förderung

  • National Key R&D Program of China
  • National Natural Science Foundation of China
  • State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body

Zitieren

APA

Liu, Y., Li, C., Huang, J., & Gao, M. (2023). MineSDS: A Unified Framework for Small Object Detection and Drivable Area Segmentation for Open-Pit Mining Scenario. Sensors. https://doi.org/10.3390/s23135977

Vancouver

Liu Y, Li C, Huang J, Gao M. MineSDS: A Unified Framework for Small Object Detection and Drivable Area Segmentation for Open-Pit Mining Scenario. Sensors. 2023. doi:10.3390/s23135977

BibTeX
@article{Liu2023,
  author = {Liu, Yong and Li, Cheng and Huang, Jiade and Gao, Ming},
  title = {MineSDS: A Unified Framework for Small Object Detection and Drivable Area Segmentation for Open-Pit Mining Scenario},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23135977}
}
Kostenlos starten →