Brain-Inspired Remote Sensing Interpretation: A Comprehensive Survey

Jiao, Licheng; Huang, Zhongjian; Liu, Xu; Yang, Yuting; Ma, Mengru; Zhao, Jiaxuan; You, Chao; Hou, Biao; Yang, Shuyuan; Liu, Fang; Ma, Wenping; Chen, Puhua; Feng, Zhixi; Tang, Xu; Guo, Yuwei; Zhang, Xiangrong; Quan, Dou; Wang, Shuang; Li, Weibin; Bai, Jing; Li, Yangyang; Shang, Ronghua; Feng, Jie

doi:10.1109/jstars.2023.3247455

Cited by 23 publications

(8 citation statements)

References 317 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are restrictions on the kinds of scenes that can be reconstructed using these methods, as they are designed to only use a single input view at test time [ 82 ]. Results from single-view 3D reconstruction are typically incomplete and inaccurate, particularly in cases where there are obstructions or obscured regions [ 114 ].…”

Section: Object Reconstructionmentioning

confidence: 99%

Deep Learning for 3D Reconstruction, Augmentation, and Registration: A Review Paper

Vinodkumar,

Karabulut,

Avots

et al. 2024

Entropy

View full text Add to dashboard Cite

The research groups in computer vision, graphics, and machine learning have dedicated a substantial amount of attention to the areas of 3D object reconstruction, augmentation, and registration. Deep learning is the predominant method used in artificial intelligence for addressing computer vision challenges. However, deep learning on three-dimensional data presents distinct obstacles and is now in its nascent phase. There have been significant advancements in deep learning specifically for three-dimensional data, offering a range of ways to address these issues. This study offers a comprehensive examination of the latest advancements in deep learning methodologies. We examine many benchmark models for the tasks of 3D object registration, augmentation, and reconstruction. We thoroughly analyse their architectures, advantages, and constraints. In summary, this report provides a comprehensive overview of recent advancements in three-dimensional deep learning and highlights unresolved research areas that will need to be addressed in the future.

show abstract

Section: Object Reconstructionmentioning

confidence: 99%

Deep Learning for 3D Reconstruction, Augmentation, and Registration: A Review Paper

Vinodkumar,

Karabulut,

Avots

et al. 2024

Entropy

View full text Add to dashboard Cite

show abstract

“…A survey conducted on brain-inspired algorithms employed on remote sensing data interpretation revealed that through interaction with the environment, reinforcement learning in remote sensing chooses consecutive actions by maximizing cumulative feature rewards. Reinforcement learning can achieve relatively high accuracy without utilizing any labelled training dataset, especially when there are only a few labelled pixels available [27]. The classification of polarimetric synthetic aperture radar images was proposed using an improved deep Q-network algorithm for few-shot remote sensing data.…”

Section: B Reinforcement Learningmentioning

confidence: 99%

A Metareinforcement-Learning-Based Hyperspectral Image Classification With a Small Sample Set

Amoako,

Cao,

Yang

et al. 2024

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

View full text Add to dashboard Cite

The fine spectral information contained in hyperspectral images (HSI) is combined with rich spatial features to provide feature qualities that serve as distinguishing variables for efficient classification performance. The task's objective is to correctly identify and categorize several object categories in the HSI, such as the ground, flora, water, and buildings, based on their spectral characteristics beneficial for a variety of applications, including mapping minerals, analyzing vegetation, and mapping urban land-use. The difficulty of learning new taskspecific knowledge from a limited data sample that encourages less training has not been overcome by deep learning models. The capacity of current models to generalize to new tasks on small data sets is still lacking. By learning features that are transferable to facilitate adaptation to novel tasks on small samples, meta-reinforcement learning shows promise in overcoming such difficulties. We proposed a meta-reinforcement learning (Meta-RL) model that decouples task inference to improve metatraining, and accelerate meta-learning with small HSI labeled samples for efficient classification. The model employs a Capsule network for effective cooperation between spectra-spatial bands. To minimize the temporal difference error, the Apex-X Deep Q network parameter update is used to meta-train our model. The proposed model obtains an overall accuracy between 95.85% and 96.78% with computational time between 3207.9s and 7487.9s for training and validation as well as between 21.57s and 32.98s for testing. The experimental results prove the competitiveness of the proposed model to existing traditional deep learning, meta-learning, and reinforcement learning methods in both classification accuracy and computational cost.

show abstract

“…Remote sensing foundation models [30] have received widespread attention in the last three years. Researchers have made many breakthroughs, achieving effective learning on various modalities and tasks.…”

Section: Foundation Models In Remote Sensingmentioning

confidence: 99%

Target Recognition of Synthetic Aperture Radar Images by Updated Classifiers

Liu

2021

Scientific Programming

View full text Add to dashboard Cite

For the problem of reliable decision in synthetic aperture radar (SAR) target recognition, a method based on updated classifiers is proposed. The convolutional neural network (CNN) and support vector machine (SVM) are used as basic classifiers to classify samples with unknown target labels. The two decisions are fused and the reliability of the fused decision is evaluated. The classified test samples with high reliabilities are added to the original training samples to update the classifiers. The updated classifiers have stronger classification abilities and the fused result of the two classifiers can obtain a more reliable decision. The proposed method is tested and verified based on the moving and stationary target acquisition and recognition (MSTAR) dataset. The experimental results verify the effectiveness and robustness of the proposed method.

show abstract

Brain-Inspired Remote Sensing Interpretation: A Comprehensive Survey

Cited by 23 publications

References 317 publications

Deep Learning for 3D Reconstruction, Augmentation, and Registration: A Review Paper

Deep Learning for 3D Reconstruction, Augmentation, and Registration: A Review Paper

A Metareinforcement-Learning-Based Hyperspectral Image Classification With a Small Sample Set

Target Recognition of Synthetic Aperture Radar Images by Updated Classifiers

Contact Info

Product

Resources

About