Optoelectronics Letters, Volume. 20, Issue 4, 243(2024)

Multi-scale detector optimized for small target

Yongchang ZHU1, Sen YANG1, Jigang TONG1、*, and Zenghui WANG2,3
Author Affiliations
  • 1School of Electrical Engineering and Automation, Tianjin University of Technology, Tianjin 300384, China
  • 2Center of Artificial Intelligence and Data Science, University of South Africa, Florida 1709, South Africa
  • 3Department of Electrical Engineering, University of South Africa, Florida 1709, South Africa
  • show less

    The effectiveness of deep learning networks in detecting small objects is limited, thereby posing challenges in addressing practical object detection tasks. In this research, we propose a small object detection model that operates at multiple scales. The model incorporates a multi-level bidirectional pyramid structure, which integrates deep and shallow networks to simultaneously preserve intricate local details and augment global features. Moreover, a dedicated multi-scale detection head is integrated into the model, specifically designed to capture crucial information pertaining to small objects. Through comprehensive experimentation, we have achieved promising results, wherein our proposed model exhibits a mean average precision (mAP) that surpasses that of the well-established you only look once version7 (YOLOv7) model by 1.1%. These findings validate the improved performance of our model in both conventional and small object detection scenarios.

    Tools

    Get Citation

    Copy Citation Text

    ZHU Yongchang, YANG Sen, TONG Jigang, WANG Zenghui. Multi-scale detector optimized for small target[J]. Optoelectronics Letters, 2024, 20(4): 243

    Download Citation

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

    Received: Jul. 9, 2023

    Accepted: Dec. 18, 2023

    Published Online: Aug. 9, 2024

    The Author Email: Jigang TONG (tjgtjut@163.com)

    DOI:10.1007/s11801-024-3126-1

    Topics