Acta Optica Sinica, Volume. 38, Issue 12, 1215008(2018)

Scene-Coupled Intelligent Multi-Task Detection Algorithm for Air-to-Ground Remote Sensing Image

Xing Liu*, Jian Chen, Dongfang Yang*, and Hao He
Author Affiliations
  • Missile Engineering College, Rocket Force University of Engineering, Xi'an, Shaanxi 710025, China
  • show less
    Figures & Tables(13)
    Air-to-ground variable resolution scene. (a) High-altitude vision; (b) middle-altitude vision; (c) low-altitude vision
    Models. (a) SSD model; (b) FSSD model
    Scene-coupled multi-task object detection model
    Information activation module. (a) Synchronous activation; (b) asynchronous activation
    Scene-assisted multi-task datasets. (a) Scene- object datasets; (b) remote sensing scene datasets
    Visualization results of scene coupling multi-task model (VGG16) validation set
    Sequential scene change resolution target search. (a) Far view rasterization scene perception schematic; (b) high-altitude scene-aware guided object detection
    • Table 1. Two feature map channel fusion methods (synchronous activation, VGG16)

      View table

      Table 1. Two feature map channel fusion methods (synchronous activation, VGG16)

      Base modelChannel addition mAP /%Channel concatenation mAP /%
      SSD82.1386.63
      FSSD86.7890.45
    • Table 2. Comparison of IA module on different framework models

      View table

      Table 2. Comparison of IA module on different framework models

      Base modelObject detection mAP /%Scene classification mAP /%
      SSD-IA86.6398.21
      SSD-none83.1298.31
      FSSD-IA90.4598.69
      FSSD-none88.4498.56
    • Table 3. Effect of synchronous and asynchronous activations on accuracy of object detection

      View table

      Table 3. Effect of synchronous and asynchronous activations on accuracy of object detection

      Base modelSynchronous activation mAP /%Asynchronous activation mAP /%
      SSD86.6384.31
      FSSD90.4588.36
    • Table 4. Scene-coupled multi-task model detection results based on different feature extractions

      View table

      Table 4. Scene-coupled multi-task model detection results based on different feature extractions

      Feature extractionObject detection taskScene classification taskFrame rate
      AP /%precision /%
      CarTruckAirplaneBoatTownAirportWaters
      VGG1691.9777.5198.4293.9198.3298.7599.0130
      ResNet5093.1284.2399.1794.6799.3199.1299.5214
      MobileNetsv284.7679.3488.4586.5698.2297.4398.3246
      Darknetv283.1377.2185.3182.1497.5198.2198.7740
    • Table 5. Comparison of proposed algorithm with traditional object detection models %

      View table

      Table 5. Comparison of proposed algorithm with traditional object detection models %

      AlgorithmAPmAP
      CarTruckAirplaneBoat
      SSD-VGG1684.2467.2298.3189.7784.89
      FSSD-VGG1688.8769.4597.6292.2887.05
      Proposed-VGG1691.9777.5198.4293.9190.45
    • Table 6. Classification results in remote sensing scenes under different feature extraction networks

      View table

      Table 6. Classification results in remote sensing scenes under different feature extraction networks

      Feature extractionPrecision /%
      TownAirportWaters
      VGG1698.4499.7599.11
      ResNet5098.5198.9899.43
      MobileNetsv297.3297.9398.92
      Darknetv297.7397.6698.57
    Tools

    Get Citation

    Copy Citation Text

    Xing Liu, Jian Chen, Dongfang Yang, Hao He. Scene-Coupled Intelligent Multi-Task Detection Algorithm for Air-to-Ground Remote Sensing Image[J]. Acta Optica Sinica, 2018, 38(12): 1215008

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Machine Vision

    Received: Jun. 28, 2018

    Accepted: Aug. 7, 2018

    Published Online: May. 10, 2019

    The Author Email:

    DOI:10.3788/AOS201838.1215008

    Topics