• Home
  • Search
  • CNN-Based Salient Target Detection Method of UAV Video Reconnaissance Image
  • Cite Icon1
  • https://doi.org/10.14569/ijacsa.2024.0150909Copy DOI Icon

CNN-Based Salient Target Detection Method of UAV Video Reconnaissance Image

  • Abstract
  • Literature Map
  • Citations
  • Similar Papers
Abstract

In order to address the challenges of image complexity, capturing subtle information, fluctuating lighting, and dynamic background interference in drone video reconnaissance, this paper proposes a salient object detection method based on convolutional neural network (CNN). This method first preprocesses the drone video reconnaissance images to remove haze and improve image quality. Subsequently, the Faster R-CNN framework was utilized for detection, where in the Region Proposal Network (RPN) stage, the K-means clustering algorithm was used to generate optimized preset anchor boxes for specific datasets to enhance the accuracy of target candidate regions. The Fast R-CNN classification loss function is used to distinguish salient target regions in reconnaissance images, while the regression loss function precisely adjusts the target bounding boxes to ensure accurate detection of salient targets. In response to the potential failure of Faster R-CNN in extreme situations, this paper innovatively introduces a saliency screening strategy based on similarity analysis to finely screen superpixels, preliminarily locate target positions, and further optimize saliency object detection results. In addition, the use of saturation component enhancement and brightness component dual frequency coefficient enhancement techniques in the HSI color space significantly improves the visual effect of salient target images, enhancing image clarity while preserving the natural and soft colors, effectively improving the visual quality of detection results. The experimental results show that this method exhibits significant advantages of high accuracy and low false detection rate in salient object detection of unmanned aerial vehicle (UAV) video reconnaissance images. Especially in complex scenes, it can still stably and accurately identify targets, significantly improving detection performance.

Similar Papers
  • Supplementary Content
  • Citations5

REMOVED: Detecting anomalies within Unmanned Aerial Vehicle (UAV) video based on contextual saliency

  • Sep 10, 2020
  • Applied Soft Computing
  • Mostafa Al-Gabalawy
  • PDF
  • Research Article
  • Citations9

Temporal and non-temporal contextual saliency analysis for generalized wide-area search within unmanned aerial vehicle (UAV) video

  • Sep 06, 2021
  • The Visual Computer
  • Simon G E Gökstorp +1
  • Conference Article
  • Citations54

Insulator Detection in Aerial Images Based on Faster Regions with Convolutional Neural Network

  • Jun 01, 2018
  • Xinyu Liu +5
  • Conference Article
  • Citations30

Object Tracking in Unmanned Aerial Vehicle (UAV) Videos Using a Combined Approach

  • Mar 18, 2005
  • Shuqun Zhang
  • PDF
  • Research Article
  • Citations25

Monitoring Human Visual Behavior during the Observation of Unmanned Aerial Vehicles (UAVs) Videos

  • Oct 19, 2018
  • Drones
  • Vassilios Krassanakis +2
  • Conference Article

Joint and transfer learning of CNN and similarity metric for comparing UAV video image patches

  • Aug 01, 2016
  • Yuting Chen +2
  • Research Article
  • Citations63

Deep learning and handcrafted features for one-class anomaly detection in UAV video

  • Sep 15, 2020
  • Multimedia Tools and Applications
  • Amira Chriki +3
  • Research Article
  • Citations23

An automatic assessment of road condition from aerial imagery using modified VGG architecture in faster-RCNN framework

  • Jun 21, 2021
  • Journal of Intelligent & Fuzzy Systems
  • A Malini +2
  • Addendum

RETRACTED ARTICLE: Temporal and non-temporal contextual saliency analysis for generalized wide-area (GWA) search within UAV video

  • Jan 03, 2021
  • The Visual Computer
  • Mostafa Al-Gabalawy
  • Book Chapter
  • Citations2

Scalable Object Detection Using Deep but Lightweight CNN with Features Fusion

  • Jan 01, 2017
  • Qiaosong Chen +6
  • Research Article
  • Citations5

SuperMOT: Decoupling Motion and Fusing Temporal Pyramid Features for UAV Multiobject Tracking

  • Jan 01, 2025
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Libo Ren +4
  • Research Article
  • Citations293

Real-Time Traffic Flow Parameter Estimation From UAV Video Based on Ensemble Classifier and Optical Flow

  • Jan 01, 2019
  • IEEE Transactions on Intelligent Transportation Systems
  • Ruimin Ke +4
  • Research Article
  • Citations15

Image recognition in UAV videos using convolutional neural networks

  • Apr 01, 2020
  • IET Software
  • Yadira Quiñonez +3
  • Research Article
  • Citations33

Conditional GAN based individual and global motion fusion for multiple object tracking in UAV videos

  • Dec 30, 2019
  • Pattern Recognition Letters
  • Hongyang Yu +5
  • PDF
  • Research Article
  • Citations31

One-Shot Multiple Object Tracking in UAV Videos Using Task-Specific Fine-Grained Features

  • Aug 09, 2022
  • Remote Sensing
  • Han Wu +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.