An enhanced SSD with feature cross-reinforcement for small-object detection

被引:0
|
作者
Lixiong Gong
Xiao Huang
Yinkang Chao
Jialin Chen
Binwen Lei
机构
[1] Hubei University of Technology,School of Mechanical Engineering
来源
Applied Intelligence | 2023年 / 53卷
关键词
Object detection; SSD; Attention mechanism; Feature cross reinforcement; Adaptive threshold;
D O I
暂无
中图分类号
学科分类号
摘要
Due to the limited feature information possessed by small objects in images, it is difficult for a single-shot multibox detector (SSD) to quickly notice the important regions of these small image objects. We propose an enhanced SSD based on feature cross-reinforcement (FCR-SSD). For shallow sampling, an improved group shuffling-efficient channel attention (GS-ECA) mechanism is used to make the model focus on the object areas rather than the background. Then, an FCR module allows the multiscale information from the shallow layer to be passed to the subsequent layer and fused to generate an enhanced feature map, which improves the utilization of the context information associated with small objects. We develop an adaptive algorithm for calculating positive and negative candidate box selection thresholds to select positive and negative samples, determine the intersection over union (IOU) thresholds of candidate boxes and ground-truth boxes, and adaptively determine the threshold for each ground-truth box. The proposed FCR-SSD algorithm achieves 79.6% mean average precision (mAP) for the PASCAL VOC 2007 dataset and 30.1% mAP for the MS COCO dataset at 34.2 frames per second (FPS) when run on an RTX 3080Ti GPU. The experimental results show that the FCR-SSD model yields high accuracy and a good detection speed in small-target detection tasks.
引用
收藏
页码:19449 / 19465
页数:16
相关论文
共 50 条
  • [1] An enhanced SSD with feature cross-reinforcement for small-object detection
    Gong, Lixiong
    Huang, Xiao
    Chao, Yinkang
    Chen, Jialin
    Lei, Binwen
    APPLIED INTELLIGENCE, 2023, 53 (16) : 19449 - 19465
  • [2] Correction to: An enhanced SSD with feature cross-reinforcement for small-object detection
    Lixiong Gong
    Xiao Huang
    Yinkang Chao
    Jialin Chen
    Binwen Lei
    Applied Intelligence, 2023, 53 : 21483 - 21484
  • [3] An enhanced SSD with feature cross-reinforcement for small-object detection (Mar, 10.1007/s10489-023-04544-1, 2023)
    Gong, Lixiong
    Huang, Xiao
    Chao, Yinkang
    Chen, Jialin
    Lei, Binwen
    APPLIED INTELLIGENCE, 2023, 53 (18) : 21483 - 21484
  • [4] Mask-guided SSD for small-object detection
    Chang Sun
    Yibo Ai
    Sheng Wang
    Weidong Zhang
    Applied Intelligence, 2021, 51 : 3311 - 3322
  • [5] Mask-guided SSD for small-object detection
    Sun, Chang
    Ai, Yibo
    Wang, Sheng
    Zhang, Weidong
    APPLIED INTELLIGENCE, 2021, 51 (06) : 3311 - 3322
  • [6] Small Object Detection Algorithm Based on Feature Pyramid-Enhanced Fusion SSD
    Li, Haotian
    Lin, Kezheng
    Bai, Jingxuan
    Li, Ao
    Yu, Jiali
    COMPLEXITY, 2019, 2019
  • [7] SFE-SSD: Shallow Feature Enhancement SSD for Small Object Detection
    Hongchen TAN
    Jun ZHOU
    Shengjing TIAN
    Xiuping LIU
    JournalofMathematicalResearchwithApplications, 2019, 39 (06) : 733 - 744
  • [8] An enhanced SSD with feature fusion and visual reasoning for object detection
    Leng, Jiaxu
    Liu, Ying
    NEURAL COMPUTING & APPLICATIONS, 2019, 31 (10): : 6549 - 6558
  • [9] An enhanced SSD with feature fusion and visual reasoning for object detection
    Jiaxu Leng
    Ying Liu
    Neural Computing and Applications, 2019, 31 : 6549 - 6558
  • [10] A multi-scale semantically enriched feature pyramid network with enhanced focal loss for small-object detection
    Kiobya, Twahir
    Zhou, Junfeng
    Maiseli, Baraka
    KNOWLEDGE-BASED SYSTEMS, 2025, 310