An Object-Oriented CNN Model Based on Improved Superpixel Segmentation for High-Resolution Remote Sensing Image Classification

Li, Zhiqing; Li, Erzhu; Samat, Alim; Xu, Tianyu; Liu, Wei; Yi-hu, Zhu

doi:10.1109/jstars.2022.3181744

Cited by 18 publications

(11 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to traditional methods like average or max pooling, covariance pooling captures the interrelations between image features by computing their covariance matrix, which allows for a more comprehensive description of land objects and spatial structures. This paper proposes using an Improved Objectoriented CNN model (IOCNN) [63] to capture higher-order features. Building on first-order features, the model employs attention mechanisms and covariance pooling to extract second-order features.…”

Section: Fine-grained Scene Classification Modelmentioning

confidence: 99%

Land Cover Change Detection Based on Vector Polygons and Deep Learning With High-Resolution Remote Sensing Images

Zhang,

Liu,

Niu

et al. 2024

IEEE Trans. Geosci. Remote Sensing

Self Cite

View full text Add to dashboard Cite

Vector Polygons are valuable survey data, serving as crucial outputs of national geographical censuses and a fundamental data source for detecting changes in geographical conditions. Current remote-sensing image change detection methods rely on comparing images but overlook abundant historical vector results, struggle with model generalization, and lack adequate samples. Consequently, change detection remains a manual process primarily, unable to meet the requirements for automated and efficient monitoring of standardized geographical conditions. Hence, this paper proposes a change detection method for land cover vector polygons based on high-resolution remote sensing images and deep learning. Initially, the enhanced simple linear iterative clustering (SLIC) algorithm is applied to segment dual-temporal images from identical regions. Subsequently, an annotated dataset is generated using a multi-scale extraction, cropping-with-inpainting approach. Next, datasets derived from pre-and post-temporal images are used for training and testing, respectively, and the training set is purified by using twoclassifier cross-validation. Finally, an improved object-oriented convolutional neural network (CNN) model performs finegrained scene classification. The change rules and postprocessing method are then integrated to identify changed vector polygons. To validate the effectiveness and superiority of the proposed method, we conducted experiments on land cover change detection using datasets from two study areas. The results indicate that the proposed method achieves precision and recall rates of 91.89% and 94.44% on dataset-1, respectively. Similarly, in dataset-2, the precision and recall rates reach 87.59% and 91.41%, respectively. These findings demonstrate the method's efficacy in detecting changed vector polygons, reducing manual intervention, and enhancing detection efficiency.

show abstract

Section: Fine-grained Scene Classification Modelmentioning

confidence: 99%

Land Cover Change Detection Based on Vector Polygons and Deep Learning With High-Resolution Remote Sensing Images

Zhang,

Liu,

Niu

et al. 2024

IEEE Trans. Geosci. Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…In remote sensing image analysis, diffusion models have proven effective, especially in enhancing image representation and detail supplementation [60]- [62]. Furthermore, the DM also demonstrates its utility in cloud removal [63]- [65] and image segmentation [66] tasks. In the field of CD in RS images, these models effectively distinguish real changes from pseudo-changes due to noise through an iterative denoising process, thus improving the detection accuracy of details and edges.…”

Section: B Diffusion Modelmentioning

confidence: 99%

Siamese Meets Diffusion Network: SMDNet for Enhanced Change Detection in High-Resolution RS Imagery

Jia,

Lee,

Wang

et al. 2024

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

View full text Add to dashboard Cite

In recent years, the application of deep learning to change detection (CD) has significantly progressed in remote sensing images. CD tasks have mostly used architectures such as CNN and Transformer to locate image changes. However, these architectures have shortcomings in representing boundary details and are prone to false alarms and missed detections under complex lighting and weather conditions. For that, we propose a new network, Siamese Meets Diffusion Network (SMDNet), a CD model that combines discriminative and generative architecture. By leveraging the power of the Siam-U2Net Feature Differential Encoder (SU-FDE) and Denoising Diffusion Implicit Model (DDIM), it not only improves the accuracy of object edge detection but also enhances the data through iterative denoising and thinning reconstruction Detail detection accuracy. Improves the model's robustness under environmental changes. First, we propose an SU-FDE module that uses shared weight features to capture differences between time series images, refine edge detection, and combine it with the attention mechanism to identify vital coarse features, thereby improving model sensitivity and accuracy. Finally, the progressive sampling of DDIM is used to integrate further these key features, and the adaptability of the model in different environments is enhanced with the help of the denoising ability of the diffusion model and the accurate capture of the probability distribution of image data. The performance evaluation of SMDNet on LEVIR-CD, DSIFN-CD, and CDD datasets yields validated F1 scores of 89.17%, 88.48%, and 88.23%, respectively. This substantiates the advanced capabilities of our model in accurately identifying variations and intricate details.

show abstract

“…The two main subsystems of this system are (1) Portable Inspection and Maintenance Strategy (PIMS) [228,229] and (2) Portable Data Acquisition Strategy (PDAs) [230]. • Remote-sensing technologies: remote-sensing technologies can be divided into five main groups, including (1) mathematical morphology-based methods [231], (2) objectoriented methods Li et al [232], (3) edge detection-based methods [233], (4) road information-based methods [234] and ( 5) statistics-based methods [235].…”

Section: Temperaturementioning

confidence: 99%

Effects of Environmental and Operational Conditions on Structural Health Monitoring and Non-Destructive Testing: A Systematic Review

et al. 2023

View full text Add to dashboard Cite

The development of Structural Health Monitoring (SHM) and Non-Destructive Testing (NDT) techniques has rapidly evolved and matured over the past few decades. Advances in sensor technology have facilitated deploying SHM systems for large-scale structures and local NDT of structural members. Although both methods have been successfully applied to identify structural damage in various systems, Environmental and Operational Condition (EOC) variations can influence sensor measurements and mask damage signatures in the structural response. EOCs include environmental conditions, such as temperature, humidity, and wind, as well as operational conditions, such as mass loading, vibration, and boundary conditions. The effect of EOCs can significantly undermine the reliability and robustness of damage assessment technologies and limit their performance. Thus, successful SHM and NDT systems can compensate for changing EOCs. This paper provides a state-of-the-art review of the effects of EOCs on SHM and NDT systems. It presents recent developments in advanced sensing technology, signal processing, and analysis techniques that aim to eliminate the masking effect of EOC variations and increase the damage sensitivity and performance of SHM and NDT systems. The paper concludes with current research challenges, trends, and recommendations for future research directions.

show abstract

An Object-Oriented CNN Model Based on Improved Superpixel Segmentation for High-Resolution Remote Sensing Image Classification

Cited by 18 publications

References 72 publications

Land Cover Change Detection Based on Vector Polygons and Deep Learning With High-Resolution Remote Sensing Images

Land Cover Change Detection Based on Vector Polygons and Deep Learning With High-Resolution Remote Sensing Images

Siamese Meets Diffusion Network: SMDNet for Enhanced Change Detection in High-Resolution RS Imagery

Effects of Environmental and Operational Conditions on Structural Health Monitoring and Non-Destructive Testing: A Systematic Review

Contact Info

Product

Resources

About