Editorial for Special Issue “Remote Sensing for Target Object Detection and Identification”

Vivone, Gemine; Addesso, P.; Ziemann, Amanda

doi:10.3390/rs12010196

Cited by 3 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The high-altitude remote sensing images [1][2][3][4] obtained by satellites and aircrafts are widely used in military, navigation, disaster relief, etc. So, remote sensing target detection [5][6][7] is becoming an important research hotspot. The interferences of the light changes, environment, and other complex backgrounds in remote sensing images make remote sensing targets hard to be detected.…”

Section: Introductionmentioning

confidence: 99%

MRFF-YOLO: A Multi-Receptive Fields Fusion Network for Remote Sensing Target Detection

Xu¹,

Wu²

2020

Remote Sensing

View full text Add to dashboard Cite

High-altitude remote sensing target detection has problems related to its low precision and low detection rate. In order to enhance the performance of detecting remote sensing targets, a new YOLO (You Only Look Once)-V3-based algorithm was proposed. In our improved YOLO-V3, we introduced the concept of multi-receptive fields to enhance the performance of feature extraction. Therefore, the proposed model was termed Multi-Receptive Fields Fusion YOLO (MRFF-YOLO). In addition, to address the flaws of YOLO-V3 in detecting small targets, we increased the detection layers from three to four. Moreover, in order to avoid gradient fading, the structure of improved DenseNet was chosen in the detection layers. We compared our approach (MRFF-YOLO) with YOLO-V3 and other state-of-the-art target detection algorithms on an Remote Sensing Object Detection (RSOD) dataset and a dataset of Object Detection in Aerial Images (UCS-AOD). With a series of improvements, the mAP (mean average precision) of MRFF-YOLO increased from 77.10% to 88.33% in the RSOD dataset and increased from 75.67% to 90.76% in the UCS-AOD dataset. The leaking detection rates are also greatly reduced, especially for small targets. The experimental results showed that our approach achieved better performance than traditional YOLO-V3 and other state-of-the-art models for remote sensing target detection.

show abstract

Section: Introductionmentioning

confidence: 99%

MRFF-YOLO: A Multi-Receptive Fields Fusion Network for Remote Sensing Target Detection

Xu¹,

Wu²

2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

Infrared Image Processing System Based on AI and Convolutional Neural Network

Yang,

Fan,

Zhou

2023

2023 International Conference on Computers, Information Processing and Advanced Education (CIPAE)

View full text Add to dashboard Cite

A method to improve accuracy of definition and promptness of forecasting of spacecraft motion parameters

Пічугін

Кожушко

Bortsova

2022

soi

View full text Add to dashboard Cite

The subject of the presented paper is the methods used to define spacecraft motion parameters. The goal of the paper is to develop approaches to improve accuracy of definition and promptness of forecasting of motion parameters. The tasks are 1) to determine the aspects influencing the result accuracy at defining initial conditions of the spacecraft motion, 2) to reveal the drawbacks of traditional methods and 3) to suggest some possible ways that can be used to improve accuracy and promptness at defining the spacecraft motion parameters. During the research it is revealed that the result accuracy at defining the initial conditions of the spacecraft motion is influenced by three aspects – a random component caused by presence of random errors in trajectory measurements, a dynamic component due to dynamic errors of the used model of the spacecraft motion and the error defined by the size of convergence region of the minimization method that is used to solve the multi-point boundary problem. To receive the least inaccuracy at defining the spacecraft motion parameters it is necessary to process some optimal quantity of measuring information which should ensure sufficient compensation of random errors and at the same time prevent the dynamic error from influencing considerably. At it it should be taken into account that the amount of the measured information should not be less than it is necessary to ensure convergence of the algorithm used to define those motion parameters. The main results are as follows. For solving the task of increasing accuracy of spacecraft motion parameters definition the paper suggests a new method based on minimization with definition of initial approximation region. The suggested method implements a non-local approach to minimization of the goal function, which ensures better as compared to traditional methods convergence. To increase the promptness of spacecraft motion forecasting it is suggested to use the mathematical apparatus of differential transformations. It allows decreasing the computational expenditures 3 to 4 times as compared to the regular ballistic and navigational algorithms while the given accuracy is preserved. On the basis of the performed research the following conclusions can be made. To increase the accuracy of the spacecraft motion parameters definition it is necessary to optimize the required number of measurement orbit passes, for that it is appropriate to use the Nelder-Mead search method. At implementing the advanced coordinate methods of the spacecraft control, to increase the promptness of the spacecraft motion forecasting, it is necessary to considerably decrease the computational expenditures for the motion parameters definition. To achieve that it is reasonable to use the mathematical apparatus of the differential transformations.

show abstract

Editorial for Special Issue “Remote Sensing for Target Object Detection and Identification”

Cited by 3 publications

References 14 publications

MRFF-YOLO: A Multi-Receptive Fields Fusion Network for Remote Sensing Target Detection

MRFF-YOLO: A Multi-Receptive Fields Fusion Network for Remote Sensing Target Detection

Infrared Image Processing System Based on AI and Convolutional Neural Network

A method to improve accuracy of definition and promptness of forecasting of spacecraft motion parameters

Contact Info

Product

Resources

About