View in EDS

EENet: An edge-enhanced network for robust rockfall detection in complex mountainous environments.

Saved in:
Bibliographic Details
Title: EENet: An edge-enhanced network for robust rockfall detection in complex mountainous environments.
Authors: Liu, Hongbing1,2,3 (AUTHOR) lhb@my.swjtu.edu.cn, Zhang, Mingjin1,2,3 (AUTHOR) Zhang-Minjin@swjtu.edu.cn, Zhuang, Shenghan1,2,3 (AUTHOR) shenghanzhuang@my.swjtu.edu.cn, Chen, Kunping4 (AUTHOR) chenkunping@stu.cqu.edu.cn, Zhang, Jinxiang1,2,3 (AUTHOR) jinxiangzhang@swjtu.edu.cn
Source: Landslides. Apr2026, Vol. 23 Issue 4, p989-1004. 16p.
Subject Terms: *Rockslides, *Real-time computing, *Artificial neural networks, *Landscapes, *Image databases, *Machine learning
Abstract: Rockfalls in mountainous transportation corridors are highly unpredictable and pose significant risks, which require accurate and timely detection to ensure safety. However, such detection is often hindered by environmental factors like illumination changes, rain, and fog, which degrade the visibility of rockfall outlines. In addition, many high-accuracy detection models are computationally intensive and impractical for real-time monitoring. To address these challenges, we constructed and open-sourced a large-scale Mountain Rockfall Dataset (MRDataset), which comprises 3,921 annotated images. We also propose a lightweight Edge-Enhanced Network (EENet), which incorporates an Edge Spatial Stem (ESStem) to capture preliminary edge features and a Global Edge Fusion Network (GEFNet) to combine multi-scale information. The model uses dilated convolutions to preserve contextual continuity in boundaries and employs pruning and knowledge distillation to reduce size while maintaining detection accuracy. Experimental results demonstrate that EENet surpasses YOLO11, improving Precision by 5.2%, Recall by 1.5%, mAP50 by 3.3%, and mAP50:95 by 2.9%, while reducing the number of Parameters and FLOPs by 73.3% and 52.4%, respectively. Further tests show that EENet preserves edge integrity under complex conditions, substantially decreasing both missed and false detections. This study offers an accurate and efficient approach for rockfall monitoring, with promising potential for real-world applications. [ABSTRACT FROM AUTHOR]
Database: Energy & Power Source
FullText Text:
  Availability: 0
Header DbId: enr
DbLabel: Energy & Power Source
An: 192230626
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: EENet: An edge-enhanced network for robust rockfall detection in complex mountainous environments.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Liu%2C+Hongbing%22">Liu, Hongbing</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<i> lhb@my.swjtu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Zhang%2C+Mingjin%22">Zhang, Mingjin</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<i> Zhang-Minjin@swjtu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Zhuang%2C+Shenghan%22">Zhuang, Shenghan</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<i> shenghanzhuang@my.swjtu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Chen%2C+Kunping%22">Chen, Kunping</searchLink><relatesTo>4</relatesTo> (AUTHOR)<i> chenkunping@stu.cqu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Zhang%2C+Jinxiang%22">Zhang, Jinxiang</searchLink><relatesTo>1,2,3</relatesTo> (AUTHOR)<i> jinxiangzhang@swjtu.edu.cn</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Landslides%22">Landslides</searchLink>. Apr2026, Vol. 23 Issue 4, p989-1004. 16p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Rockslides%22">Rockslides</searchLink><br />*<searchLink fieldCode="DE" term="%22Real-time+computing%22">Real-time computing</searchLink><br />*<searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br />*<searchLink fieldCode="DE" term="%22Landscapes%22">Landscapes</searchLink><br />*<searchLink fieldCode="DE" term="%22Image+databases%22">Image databases</searchLink><br />*<searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Rockfalls in mountainous transportation corridors are highly unpredictable and pose significant risks, which require accurate and timely detection to ensure safety. However, such detection is often hindered by environmental factors like illumination changes, rain, and fog, which degrade the visibility of rockfall outlines. In addition, many high-accuracy detection models are computationally intensive and impractical for real-time monitoring. To address these challenges, we constructed and open-sourced a large-scale Mountain Rockfall Dataset (MRDataset), which comprises 3,921 annotated images. We also propose a lightweight Edge-Enhanced Network (EENet), which incorporates an Edge Spatial Stem (ESStem) to capture preliminary edge features and a Global Edge Fusion Network (GEFNet) to combine multi-scale information. The model uses dilated convolutions to preserve contextual continuity in boundaries and employs pruning and knowledge distillation to reduce size while maintaining detection accuracy. Experimental results demonstrate that EENet surpasses YOLO11, improving Precision by 5.2%, Recall by 1.5%, mAP50 by 3.3%, and mAP50:95 by 2.9%, while reducing the number of Parameters and FLOPs by 73.3% and 52.4%, respectively. Further tests show that EENet preserves edge integrity under complex conditions, substantially decreasing both missed and false detections. This study offers an accurate and efficient approach for rockfall monitoring, with promising potential for real-world applications. [ABSTRACT FROM AUTHOR]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=192230626
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s10346-025-02683-9
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 16
        StartPage: 989
    Subjects:
      – SubjectFull: Rockslides
        Type: general
      – SubjectFull: Real-time computing
        Type: general
      – SubjectFull: Artificial neural networks
        Type: general
      – SubjectFull: Landscapes
        Type: general
      – SubjectFull: Image databases
        Type: general
      – SubjectFull: Machine learning
        Type: general
    Titles:
      – TitleFull: EENet: An edge-enhanced network for robust rockfall detection in complex mountainous environments.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Liu, Hongbing
      – PersonEntity:
          Name:
            NameFull: Zhang, Mingjin
      – PersonEntity:
          Name:
            NameFull: Zhuang, Shenghan
      – PersonEntity:
          Name:
            NameFull: Chen, Kunping
      – PersonEntity:
          Name:
            NameFull: Zhang, Jinxiang
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 04
              Text: Apr2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 1612510X
          Numbering:
            – Type: volume
              Value: 23
            – Type: issue
              Value: 4
          Titles:
            – TitleFull: Landslides
              Type: main
ResultId 1