Electronic Science and Technology ›› 2022, Vol. 35 ›› Issue (7): 40-45.doi: 10.16180/j.cnki.issn1007-7820.2022.07.007

Previous Articles     Next Articles

Improved YOLOv3 Model Based on New Feature Extraction and Fusion Module

ZHAO Xuan,ZHOU Fan,YU Hancheng   

  1. College of Electronic and Information Engineering,Nanjing University of Aeronautics and Astronautics, Nanjing 211106,China
  • Received:2021-01-21 Online:2022-07-15 Published:2022-08-16
  • Supported by:
    Open Research Fund of Key Laboratory of Ministry of Education(UASP2001)


There is a certain optimization space for the feature extraction branch and multi-scale detection branch of YOLOv3 model. To solve this problem, this study proposes two structural improvement methods to improve the detection accuracy of the model on the target detection data set. For the three scales (13×13, 26×26, 52×52) of the YOLOv3 model, a priori anchor frames of different lengths and widths are used, and the label frames of the three scales are the same, and the feature fusion method between the design scales is used to improve the accuracy of the model. In view of the problem of convolutional layer spatial view sharing, the original convolutional layer can be replaced with deformable convolution to improve the accuracy of the model. The test result on the industrial tool library proves that the accuracy of the test set of the improved model is increased by 3.6 MAP when compared with the original YOLOv3.

Key words: object detection, deep learning, multiscale fusion, industrial tool detection, residual module, YOLOv3, IOU loss

CLC Number: 

  • TP274