FAST DETECTION OF TARGET BASED ON SSD DATASET TRAINING ALGORITHM

Authors

  • Z. Q. HOU
  • C. H. CHEN
  • W. S. YU
  • X. F. LIAO
  • J. Y. WANG

DOI:

https://doi.org/10.52292/j.laar.2018.217

Keywords:

deep learning, SSD model, data set training, target, edge detection

Abstract

Edge detection is one of the most basic contents of image processing and analysis. The edge of the image contains the position and contour of the image, which is one of the basic features of the image. The accuracy of the traditional algorithm is not high because of the strong jitter of the target and the larger interference. The key to target edge detection lies in the extraction of effective features, and this can be properly realized with a feature extraction based on the depth-learning algorithm. In this paper, a method of sample synthesis is proposed, which is used for network training and can be used to detect small-scale moving targets in a limited sample space. A large number of experimental tests show that the algorithm can detect small moving target edges, showing high accuracy, real-time performance and strong robustness.

Downloads

Published

2018-07-31

Issue

Vol. 48 No. 3 (2018): Latin American Applied Research

Section

Control and Information Processing

License

Once a paper is accepted for publication, the author is assumed to have transferred its copyright to the Publisher. The Publisher will not, however, put any limitation on the personal freedom of the author to use material from the paper in other publications. From September 2019 it is required that authors explicitly sign a copyright release form before their paper gets published. The Author Copyright Release form can be found here