Graph of Concepts for Semantic Annotation of Remotely Sensed Images based on Direct Neighbors in RAG

Amiri, Khitem; Farah, Mohamed

doi:10.1080/07038992.2019.1569507

Cited by 7 publications

(5 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Super pixel algorithms such as Simple Linear Iterative Clustering (SLIC) are often used to segment images, but they do not consider the semantic information of the image context. Amiri [6] proposed a remote sensing image semantic annotation method based on a region adjacency graph (RAG). It uses SLIC to segment the image and construct a RAG graph, examining the context, spatial, and spectral information of the image region.…”

Section: Methods Based On Spatial Geometry and Texture Informationmentioning

confidence: 99%

“…When necessary, the user can make a guidance mask in step (4) containing guidance information and feed the guidance mask and the input image into the DGN in step (5). The DGN activates the guidance module as much as possible to embed the guidance information into the internal features, and give the second annotation image in step (6), which fully refers to the guidance information. To further improve the performance of the annotation, we back to step (7).…”

Section: Methodsmentioning

confidence: 99%

“…To increase the efficiency of re-annotation, some methods based on spatial geometry and texture information [4], [6], [7], [14] allow for correction of mislabeling by adjusting their own parameters to adapt to perturbations such as contrast and scale changes [10].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Deep Neural Network for Image Segmentation

2023

jeis

View full text Add to dashboard Cite

Many tasks demand high-quality remote sensing image annotation products that are difficult to achieve through existing automated methods. Obtaining high-quality pixel annotations is time-consuming and laborious. This study proposes architecture with controllable correction ability that can automatically generate image annotations and allow annotators to adaptively correct previous annotations by making simple guidance information after discovering errors. This method can be applied to any convolution-based network. A training method and metric were proposed to measure the efficiency of reannotation. We conducted experiments on the Vaihingen dataset using different base architectures and backbones. Our study shows that our training method can effectively direct the guidance module to utilize the guidance information and improve the reannotation efficiency up to 2.53 times. In addition, more advanced architectures may give better results.

show abstract

Section: Methods Based On Spatial Geometry and Texture Informationmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Deep Neural Network for Image Segmentation

2023

jeis

View full text Add to dashboard Cite

show abstract

“…Based on domain ontology, Mohamed Farah et al [67] presented a graph-based method for RS image semantic annotation, which tried to simultaneously process all available information of the image and develop an annotation procedure to generate graphs for representing objects and their spatial relations in the studied scene. Besides, in order to give a formalized and reasonable representation of the relationships between different regions and related labels in the RS image, Khitem Amiri et al [68] proposed a semantic annotation approach based on region adjacency graphs to produce a concept graph, which could represent the objects in the scene by using spatial and spectrum attributes. However, due to the limitation of conceptualized knowledge, these methods relied on prior knowledge, and their performances are not ideal.…”

Section: A Semantic Graph-based Remote Sensing Image Annotationmentioning

confidence: 99%

Remote Sensing Image Interpretation With Semantic Graph-Based Methods: A Survey

Sun

Dustdar

Ranjan

et al. 2022

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

View full text Add to dashboard Cite

With the significant improvements in Earth observation (EO) technologies, remote sensing (RS) data exhibit the typical characteristics of Big Data. Propelled by the powerful feature extraction capabilities of intelligent algorithms, remote sensing image interpretation has drawn remarkable attention and achieved progress. However, the semantic relationship and domain knowledge hidden in massive RS images have not been fully exploited. To the best of our knowledge, a comprehensive review of recent achievements regarding semantic graph-based methods for comprehension and interpretation of remote sensing images is still lacking. Specifically, this article discusses the main challenges of remote sensing image interpretation and presents a systematic survey of typical semantic graph-based methodologies for RS knowledge representation and understanding, including the Ontology Model, Geo-Information Tupu, and Semantic Knowledge Graph. Furthermore, we categorize and summarize how the existing technologies address different challenges in RS image interpretation based on semantic graph-based methods, which indicates that the semantic information about potential relationships and prior knowledge of variant RS targets are central to the solution. In addition, a case study of RS geological interpretation based on the semantic knowledge graph is demonstrated to show the promising capability of intelligent RS image interpretation. Finally, the future directions are discussed for further research.

show abstract

“…In [3], histogram of local binary patterns that models the relationship of each pixel in a given image with its neighbors (which are located on a circle around that pixel) by a binary code is presented. Graph-based image representations, where the nodes model region properties and the edges represent the spatial relationships among the regions, are introduced in [4]- [6]. Descriptors of bag of spectral values are introduced in [7] to model the spectral information content of high dimensional RS images.…”

Section: Introductionmentioning

confidence: 99%

Toward Remote Sensing Image Retrieval Under a Deep Image Captioning Perspective

Hoxha

Melgani

Demir

2020

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

View full text Add to dashboard Cite

The performance of remote sensing image retrieval (RSIR) systems depends on the capability of the extracted features in characterizing the semantic content of images. Existing RSIR systems describe images by visual descriptors that model the primitives (such as different land-cover classes) present in the images. However, the visual descriptors may not be sufficient to describe the high-level complex content of RS images (e.g., attributes and relationships among different land-cover classes). To address this issue, in this paper we present a RSIR system that aims at generating and exploiting textual descriptions to accurately describe the relationships between the objects and their attributes present in RS images with captions (i.e., sentences). To this end, the proposed retrieval system consists of three main steps. The first step aims to encode the image visual features and then translate the encoded features into a textual description that summarizes the content of the image with captions. This is achieved based on the combination of a convolutional neural network with a recurrent neural network. The second step aims to convert the generated textual descriptions into semantically meaningful feature vectors. This is achieved by using the recent word embedding techniques. Finally, the last step estimates the similarity between the vectors of the textual descriptions of the query image and those of the archive images, and then retrieve the most similar images to the query image. Experimental results obtained on two different datasets show that the description of the image content with captions in the framework of RSIR leads to an accurate retrieval performance.

show abstract

Graph of Concepts for Semantic Annotation of Remotely Sensed Images based on Direct Neighbors in RAG

Cited by 7 publications

References 45 publications

A Deep Neural Network for Image Segmentation

A Deep Neural Network for Image Segmentation

Remote Sensing Image Interpretation With Semantic Graph-Based Methods: A Survey

Toward Remote Sensing Image Retrieval Under a Deep Image Captioning Perspective

Contact Info

Product

Resources

About