Military Vehicle Object Detection Based on Hierarchical Feature Representation and Refined Localization

Ouyang, Yan; Hu, Ruizhe; Xu, Honghui; Shao, Faming

doi:10.1109/access.2022.3207153

Cited by 11 publications

(4 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As an alternative to the conventional, ineffective detection methods employed in the military, the military vehicle object detection method (MVODM) was proposed in [ 23 ]. Hierarchical feature representation and RL localization techniques form the foundation of this approach.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Reinforcement learning (RL) is a subset of ML algorithms that investigates how agents should behave in a particular situation to achieve a certain goal or obtain the maximum rewards [ 19 ]. Effective traditional UAV detection approaches include radar systems [ 20 , 21 ], visual surveillance [ 22 , 23 ], radio frequency (RF) signals [ 24 , 25 , 26 ], and acoustic sensors [ 27 ]. According to [ 28 ], radio waves are used by radar systems to identify objects in the airspace.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

UAV Detection Using Reinforcement Learning

AlKhonaini,

Sheltami,

Mahmoud

et al. 2024

Sensors

View full text Add to dashboard Cite

Unmanned Aerial Vehicles (UAVs) have gained significant popularity in both military and civilian applications due to their cost-effectiveness and flexibility. However, the increased utilization of UAVs raises concerns about the risk of illegal data gathering and potential criminal use. As a result, the accurate detection and identification of intruding UAVs has emerged as a critical research concern. Many algorithms have shown their effectiveness in detecting different objects through different approaches, including radio frequency (RF), computer vision (visual), and sound-based detection. This article proposes a novel approach for detecting and identifying intruding UAVs based on their RF signals by using a hierarchical reinforcement learning technique. We train a UAV agent hierarchically with multiple policies using the REINFORCE algorithm with entropy regularization term to improve the overall accuracy. The research focuses on utilizing extracted features from RF signals to detect intruding UAVs, which contributes to the field of reinforcement learning by investigating a less-explored UAV detection approach. Through extensive evaluation, our findings show the remarkable results of the proposed approach in achieving accurate RF-based detection and identification, with an outstanding detection accuracy of 99.7%. Additionally, our approach demonstrates improved cumulative return performance and reduced loss. The obtained results highlight the effectiveness of the proposed solution in enhancing UAV security and surveillance while advancing the field of UAV detection.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

UAV Detection Using Reinforcement Learning

AlKhonaini,

Sheltami,

Mahmoud

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Ouyang, Wang, Hu, Xu, and Shao proposed a method for vehicle detection in the military on the basis of hierarchical feature representation and reinforcement learning refinement localization [15]. They constructed a new dataset of military vehicle images sourced from the internet for the object detection task.…”

Section: Literature Surveymentioning

confidence: 99%

Analysis of Deep Neural Networks for Military Target Classification using Synthetic Aperture Radar Images

Jacob,

Wall,

Sharif

2023

2023 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT)

View full text Add to dashboard Cite

Target detection and classification in the military is an area that is very significant in modern battlefields. Using Synthetic Aperture Radar images for classifying targets adds to its significance, as these images are high-resolution images of the surface of the earth created using microwave radiation and they can be used anytime, anywhere, and in any weather conditions. A target classification system using deep learning to classify military vehicles from Synthetic Aperture Radar images is proposed in this study. The system uses a baseline Convolutional Neural Network to classify the images of military vehicles from the MSTAR dataset, achieving a baseline accuracy of 90%. Further transfer learning was applied to the system by using 5 different pre-trained networks, namely the InceptionV3, VGG16, VGG19, ResNet50, and MobileNet. These models were analysed and evaluated using 3 different evaluation metrics, the Confusion matrix, Classification report, and Mean Average Precision to discover the most accurate and efficient model for this task. The models VGG16 and MobileNet displayed the best performance on the dataset achieving accuracies of 98% and 97%, respectively. The ResNet50 model displayed the worst performance among the models, achieving an accuracy of 82%. While the other models, InceptionV3 and VGG19, achieved accuracies of 92% and 96% respectively.

show abstract

“…Images melded together often align more closely with human visual perception, thereby finding applications in related sectors such as image segmentation [3], biometric recognition [4], object detection [5], and object tracking [6]. Concurrently, the fusion of images can also provide increased data support for domains like video surveillance [7], military [8], and medical [9].…”

Section: Introductionmentioning

confidence: 99%

OMOFuse: An Optimized Dual-Attention Mechanism Model for Infrared and Visible Image Fusion

Yuan,

2023

Mathematics

View full text Add to dashboard Cite

Infrared and visible image fusion aims to fuse the thermal information of infrared images and the texture information of visible images into images that are more in compliance with people’s visual perception characteristics. However, in the existing related work, the fused images have incomplete contextual information and poor fusion results. This paper presents a new image fusion algorithm—OMOFuse. At first, both the channel and spatial attention mechanisms are optimized by a DCA (dual-channel attention) mechanism and an ESA (enhanced spatial attention) mechanism. Then, an ODAM (optimized dual-attention mechanism) module is constructed to further improve the integration effect. Moreover, a MO module is used to improve the network’s feature extraction capability for contextual information. Finally, there is the loss function ℒ from the three parts of SSL (structural similarity loss), PL (perceptual loss), and GL (gap loss). Extensive experiments on three major datasets are performed to demonstrate that OMOFuse outperforms the existing image fusion methods in terms of quantitative determination, qualitative detection, and superior generalization capabilities. Further evidence of the effectiveness of our algorithm in this study are provided.

show abstract

Military Vehicle Object Detection Based on Hierarchical Feature Representation and Refined Localization

Cited by 11 publications

References 37 publications

UAV Detection Using Reinforcement Learning

UAV Detection Using Reinforcement Learning

Analysis of Deep Neural Networks for Military Target Classification using Synthetic Aperture Radar Images

OMOFuse: An Optimized Dual-Attention Mechanism Model for Infrared and Visible Image Fusion

Contact Info

Product

Resources

About