Multispectral target detection based on the space–spectrum structure constraint with the multi-scale hierarchical model

2018 ◽  
Vol 68 ◽  
pp. 58-67 ◽  
Author(s):  
Zhuang Zhao ◽  
Yuwei Zhang ◽  
Lianfa Bai ◽  
Yi Zhang ◽  
Jing Han
Keyword(s):  
Target Detection ◽  
Hierarchical Model ◽  
Multi Scale ◽  
Structure Constraint ◽  
Spectrum Structure ◽  
Space Spectrum

Infrared small-target detection based on multi-directional multi-scale high-boost response

2019 ◽  
Vol 26 (6) ◽  
pp. 568-582 ◽  
Author(s):  
Lingbing Peng ◽  
Tianfang Zhang ◽  
Suqi Huang ◽  
Tian Pu ◽  
Yuhan Liu ◽  
...  
Keyword(s):  
Target Detection ◽  
Small Target ◽  
Small Target Detection ◽  
Multi Scale ◽  
Infrared Small Target

A Multi-scale, Hierarchical Model to Map Riparian Zones

2016 ◽  
Vol 32 (8) ◽  
pp. 1709-1720 ◽  
Author(s):  
J. A. Salo ◽  
D. M. Theobald
Keyword(s):  
Hierarchical Model ◽  
Riparian Zones ◽  
Multi Scale

scholarly journals Fast-armored target detection based on multi-scale representation and guided anchor

2020 ◽  
Vol 16 (4) ◽  
pp. 922-932
Author(s):  
Fan-jie Meng ◽  
Xin-qing Wang ◽  
Fa-ming Shao ◽  
Dong Wang ◽  
Xiao-dong Hu
Keyword(s):  
Target Detection ◽  
Multi Scale

Infrared Dim and Small Target Detection Algorithm Based on Multi-scale Anisotropic Diffusion Equation

2015 ◽  
Vol 44 (9) ◽  
pp. 910002 ◽  
Author(s):  
周慧鑫 ZHOU Hui-xin ◽  
赵营 ZHAO Ying ◽  
秦翰林 QIN Han-lin ◽  
殷世民 YIN Shi-min ◽  
刘刚 LIU Gang ◽  
...  
Keyword(s):  
Diffusion Equation ◽  
Target Detection ◽  
Anisotropic Diffusion ◽  
Detection Algorithm ◽  
Small Target ◽  
Small Target Detection ◽  
Multi Scale ◽  
Anisotropic Diffusion Equation

scholarly journals Improved YOLO-V3 with DenseNet for Multi-Scale Remote Sensing Target Detection

Sensors ◽  
2020 ◽  
Vol 20 (15) ◽  
pp. 4276 ◽  
Author(s):  
Danqing Xu ◽  
Yiquan Wu
Keyword(s):  
Remote Sensing ◽  
Object Detection ◽  
Target Detection ◽  
Poor Performance ◽  
Aerial Images ◽  
Single Shot ◽  
Multi Scale ◽  
Dense Distribution ◽  
Different Dimensions ◽  
Small Targets

Remote sensing targets have different dimensions, and they have the characteristics of dense distribution and a complex background. This makes remote sensing target detection difficult. With the aim at detecting remote sensing targets at different scales, a new You Only Look Once (YOLO)-V3-based model was proposed. YOLO-V3 is a new version of YOLO. Aiming at the defect of poor performance of YOLO-V3 in detecting remote sensing targets, we adopted DenseNet (Densely Connected Network) to enhance feature extraction capability. Moreover, the detection scales were increased to four based on the original YOLO-V3. The experiment on RSOD (Remote Sensing Object Detection) dataset and UCS-AOD (Dataset of Object Detection in Aerial Images) dataset showed that our approach performed better than Faster-RCNN, SSD (Single Shot Multibox Detector), YOLO-V3, and YOLO-V3 tiny in terms of accuracy. Compared with original YOLO-V3, the mAP (mean Average Precision) of our approach increased from 77.10% to 88.73% in the RSOD dataset. In particular, the mAP of detecting targets like aircrafts, which are mainly made up of small targets increased by 12.12%. In addition, the detection speed was not significantly reduced. Generally speaking, our approach achieved higher accuracy and gave considerations to real-time performance simultaneously for remote sensing target detection.

Sign in / Sign up

Export Citation Format

Share Document