Research on automatic detection technology for missile warhead-body separation events based on infrared imaging

This paper introduces an innovative recognition network that combines the VGG19 model with Squeeze-and-Excitation (SE) blocks to tackle the binary classification of missile warhead-body separation events. By integrating SE blocks, which dynamically recalibrate channel-wise feature responses, the proposed model significantly enhances the VGG19 network's feature representation abilities. This improvement allows the classifier to effectively distinguish subtle differences in the data. In a simulated UAV-based infrared detection scenario, the experimental results illustrate the model's exceptional performance, achieving an average accuracy of 96.49%, a precision of 97.56%, a recall of 83.33%, and an F1 score of 89.89%. The above study has expanded the application scenarios of infrared image recognition and simultaneously verified the effectiveness of deep neural networks in processing datasets with subtle discriminability. Future research will focus on further optimizing the network architecture and investigating its efficacy in more intricate multi-class classification situations.

• Publication year

  2025

• Venue

  Conference on Computer Graphics, Artificial Intelligence, and Data Processing

• Publication date

  2025-04-10

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.1117/12.3061430
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Advanced automated target recognition (ATR) and multi-target tracker (MTT) with electro-optical (EO) sensors

  2020cited by this paper
• Imaging simulation of space based infrared panoramic scanning sensor

  2020cited by this paper
• A Study on IR Target Recognition Approach in Aerial Jamming Environment Based on Bayesian Probabilistic Model

  2019cited by this paper
• Squeeze-and-Excitation Networks

  2017cited by this paper
• Rocket launch detection and tracking using EO sensor

  2017cited by this paper
• Decoupled Weight Decay Regularization

  2017cited by this paper
• Rethinking the Inception Architecture for Computer Vision

  2015cited by this paper
• Very Deep Convolutional Networks for Large-Scale Image Recognition

  2014influential reference

• No citing papers are available for this paper.