Small Object Detection of High-Resolution Images Based on Feature Fusion and Learnable Anchor

被引：0
|
作者：
Li C. [1 ]
Huang X.-Y. [1 ]
Wang K. [1 ]
机构：
[1] School of Computer, Hubei University of Technology, Hubei, Wuhan
来源：
Tien Tzu Hsueh Pao/Acta Electronica Sinica | 2022年 / 50卷 / 07期
关键词：
feature fusion; high resolution images; learnable anchor; small object detection;
D O I：
10.12263/DZXB.20200917
中图分类号：
学科分类号：
摘要：
Small object detection of high-resolution images presents significant challenges. To solve the problem that downsampling and cropping of high-resolution images result in missed detections and false detections due to the loss of fine details and contextual information, an algorithm based on feature fusion and learnable anchor is proposed for small object detection of high-resolution images. Contextual and detailed features are extracted from downsampled images and cropped patches respectively, which are then fused layer-wise. The fused features are further combined with smoothed features to strengthen both fine details and contextual information. To mitigate the feature inconsistency, learnable anchor is applied to make the fused features accommodative to the location and shape of anchors. The proposed method is tested from the perspective of global inference and local inference compared to state-of-the-art detectors. The experimental results show the accuracy and effectiveness of the proposed method. © 2022 Chinese Institute of Electronics. All rights reserved.
引用
收藏
页码：1684 / 1695
页数：11
相关论文
共 32 条
  • [11] LIU S, QI L, QIN H F, Et al., Path aggregation network for instance segmentation, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8759-8768, (2018)
  • [12] CHEN W Y, JIANG Z Y, WANG Z Y, Et al., Collaborative global-local networks for memory-efficient segmentation of ultra-high resolution images, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8916-8925, (2019)
  • [13] SUN K, XIAO B, LIU D, Et al., Deep high-resolution representation learning for human pose estimation, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR), pp. 5686-5696, (2019)
  • [14] CHEN K, PANG J M, WANG J Q, Et al., Hybrid task cascade for instance segmentation, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4969-4978, (2019)
  • [15] REN S Q, HE K M, GIRSHICK R, Et al., Faster R-CNN: Towards real-time object detection with region proposal networks, IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 6, pp. 1137-1149, (2017)
  • [16] OKSUZ K, CAM B C, KALKAN S, Et al., Imbalance problems in object detection: A review, IEEE Transactions on Pattern Analysis and Machine Intelligence, 43, 10, pp. 3388-3415, (2021)
  • [17] CAI Z W, VASCONCELOS N., Cascade R-CNN: Delving into high quality object detection, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 6154-6162, (2018)
  • [18] ZHANG H K, CHANG H, MA B P, Et al., Dynamic RCNN: Towards High Quality Object Detection via Dynamic Training, Computer Vision-ECCV 2020, pp. 260-275, (2020)
  • [19] WANG J Q, ZHANG W W, CAO Y H, Et al., Side-aware boundary localization for more precise object detection, European Conference on Computer Vision, pp. 403-419, (2020)
  • [20] WANG J Q, CHEN K, YANG S, Et al., Region proposal by guided anchoring, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR), pp. 2960-2969, (2019)
1234