An Advanced Neural Network-Based Approach for Military Ground Vehicle Recognition in Sar Aerial Imagery

Neagoe, Victor-Emil; Carata, Serban-Vasile; Ciotec, Adrian-Dumitru

doi:10.19062/2247-3173.2016.18.1.5

Cited by 9 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When the resized image is feature extracted through ResNet50 [48], we can obtain the feature map of 1/4, 1/8, 1/16, and 1/32 down-sampled from the original image level by level. These feature maps are called 3,4,5]. As the backbone deepens, the size of the feature map gradually decreases, and the interference information is gradually removed.…”

Section: B Feature Extraction and Fusionmentioning

confidence: 99%

SAR Object Detection Encounters Deformed Complex Scenes and Aliased Scattered Power Distribution

Zhang

Feng

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Synthetic aperture radar (SAR) is widely used in terrain classification, object detection, and other fields. Compared with anchor-based detectors, anchor-free detectors remove the anchor mechanism and implement detection box encoding in a more elegant form. However, anchor-free detectors are limited by complex scenes caused by geometric transformations, such as overlaying, shadow, vertex displacement during SAR imaging. And the scattered power distribution of noise is similar to the edge of the object, making it difficult for the detector to locate the edge of the SAR object accurately. In order to alleviate these problems, we propose a high-speed and high-performance SAR image anchorfree detector. First, we propose a shallow feature refinement (SFR) module to effectively extract and retain the detailed information of objects, while coping with deformed complex scenes. Second, we analyze the optimization focus of the detector at different training iterations and propose iteration-aware loss to guide the detector, making the detector more accurately locate the edge of the object disturbed by the noise scattered power distribution. Third, number estimation helps to detect objects with more flexible criteria in box selection without manual labor. Compared with mainstream optical object detectors and SAR dedicated detectors, our method achieves the best speed-accuracy tradeoff on the SAR-ship dataset, with 96.4% average precision when the value of intersection over Manuscript

show abstract

Section: B Feature Extraction and Fusionmentioning

confidence: 99%

SAR Object Detection Encounters Deformed Complex Scenes and Aliased Scattered Power Distribution

Zhang

Feng

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…After continuous research and improvement by scholars, the current mainstream object detection methods have made significant progress in the detection of common targets. However, for military targets, due to their secrecy and environmental complexity, there are often greater difficulties for the detection of military targets [6]. In order to further improve the battlefield situational awareness, this paper addresses the detection of vehicle targets in military targets, aiming to improve the detection performance of military vehicle targets.…”

Section: Introductionmentioning

confidence: 99%

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

Ouyang

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Military vehicle object detection technology in complex environments is the basis for the implementation of reconnaissance and tracking tasks for weapons and equipment, and is of great significance for information and intelligent combat. In response to the poor performance of traditional detection algorithms in military vehicle detection, we propose a military vehicle detection method based on hierarchical feature representation and reinforcement learning refinement localization, referred to as MVODM. First, for the military vehicle detection task, we construct a reliable dataset MVD. Second, we design two strategies, hierarchical feature representation and reinforcement learning-based refinement localization, to improve the detector. The hierarchical feature representation strategy can help the detector select the feature representation layer suitable for the object scale, and the reinforcement learning-based refinement localization strategy can improve the accuracy of the object localization boxes. The combination of these two strategies can effectively improve the performance of the detector. Finally, the experimental results on the homemade dataset show that our proposed MVODM has excellent detection performance and can better accomplish the detection task of military vehicles.INDEX TERMS Military vehicle objects, object detection, reinforcement learning, hierarchical feature representation.

show abstract

YOLO-G: A Lightweight Network Model for Improving the Performance of Military Targets Detection

Kong

Wang

Zhao³

2022

IEEE Access

View full text Add to dashboard Cite

An Advanced Neural Network-Based Approach for Military Ground Vehicle Recognition in Sar Aerial Imagery

Cited by 9 publications

References 16 publications

SAR Object Detection Encounters Deformed Complex Scenes and Aliased Scattered Power Distribution

SAR Object Detection Encounters Deformed Complex Scenes and Aliased Scattered Power Distribution

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

YOLO-G: A Lightweight Network Model for Improving the Performance of Military Targets Detection

Contact Info

Product

Resources

About