Multi-Attention-Based Semantic Segmentation Network for Land Cover Remote Sensing Images

Jia, Jintong; Song, Jiarui; Kong, Qingqiang; Yang, Huan; Teng, Yuanwen; Song, Xuan

doi:10.3390/electronics12061347

Cited by 6 publications

(9 citation statements)

References 43 publications

(48 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Attention mechanisms have proven to be effective in computer vision, allowing models to focus on relevant parts of the input by assigning different weights to different regions [ 46 ]. Several works have demonstrated that incorporating attention can enhance the performance of semantic segmentation models, including DeepLabv3+ [ 47 , 48 , 49 ]. In our work, we have chosen to use the SimAM (Simple Attention Module) [ 10 ].…”

Section: Proposed Methodsmentioning

confidence: 99%

mid-DeepLabv3+: A Novel Approach for Image Semantic Segmentation Applied to African Food Dietary Assessments

Baban A Erep,

Chaari

2023

Sensors

View full text Add to dashboard Cite

Recent decades have witnessed the development of vision-based dietary assessment (VBDA) systems. These systems generally consist of three main stages: food image analysis, portion estimation, and nutrient derivation. The effectiveness of the initial step is highly dependent on the use of accurate segmentation and image recognition models and the availability of high-quality training datasets. Food image segmentation still faces various challenges, and most existing research focuses mainly on Asian and Western food images. For this reason, this study is based on food images from sub-Saharan Africa, which pose their own problems, such as inter-class similarity and dishes with mixed-class food. This work focuses on the first stage of VBDAs, where we introduce two notable contributions. Firstly, we propose mid-DeepLabv3+, an enhanced food image segmentation model based on DeepLabv3+ with a ResNet50 backbone. Our approach involves adding a middle layer in the decoder path and SimAM after each extracted backbone feature layer. Secondly, we present CamerFood10, the first food image dataset specifically designed for sub-Saharan African food segmentation. It includes 10 classes of the most consumed food items in Cameroon. On our dataset, mid-DeepLabv3+ outperforms benchmark convolutional neural network models for semantic image segmentation, with an mIoU (mean Intersection over Union) of 65.20%, representing a +10.74% improvement over DeepLabv3+ with the same backbone.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

mid-DeepLabv3+: A Novel Approach for Image Semantic Segmentation Applied to African Food Dietary Assessments

Baban A Erep,

Chaari

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…3) CNN-based attentional networks: MACU-Net introduced in [20], MAU-Net in [18], and Multi-scale network with HL module provided by [19], AttU-Net U-Net with addtitive attention [37], CAU-Net [64].…”

Section: Experimental Hypothesesmentioning

confidence: 99%

New Fusion Approach of Spatial and Channel Attention for Semantic Segmentation of Very High Spatial Resolution Remote Sensing Images

Atiampo,

Diédié

2024

OJAppS

View full text Add to dashboard Cite

The semantic segmentation of very high spatial resolution remote sensing images is difficult due to the complexity of interpreting the interactions between the objects in the scene. Indeed, effective segmentation requires considering spatial local context and long-term dependencies. To address this problem, the proposed approach is inspired by the MAC-UNet network which is an extension of U-Net, densely connected combined with channel attention. The advantages of this solution are as follows: 1) The new model introduces a new attention called propagate attention to build an attention-based encoder. 2) The fusion of multi-scale information is achieved by a weighted linear combination of the attentions whose coefficients are learned during the training phase. 3) Introducing in the decoder, the Spatial-Channel-Global-Local block which is an attention layer that uniquely combines channel attention and spatial attention locally and globally. The performances of the model are evaluated on 2 datasets WHDLD and DLRSD and show results of mean intersection over union (mIoU) index in progress between 1.54% and 10.47% for DLRSD and between 1.04% and 4.37% for WHDLD compared with the most efficient algorithms with attention mechanisms like MAU-Net and transformers like TMNet.

show abstract

“…The precision of remote sensing images can be evaluated using the confusion matrix, which enables and assessment to be conducted by analyzing all pixels across different categories and presenting a concise overview of the degree of misclassification between the classified categories and the actual categories [57]. The calculation of several performance metrics such as overall accuracy, the Kappa coefficient, the producer's accuracy, the user's accuracy, the misclassification error, and the missed classification error can be conducted in the aquaculture area [17].…”

Section: Accuracy Assessmentmentioning

confidence: 99%

Review of the Accuracy of Satellite Remote Sensing Techniques in Identifying Coastal Aquaculture Facilities

Chen,

Lv,

Zhang

et al. 2024

Fishes

View full text Add to dashboard Cite

The predominant form of aquaculture is the facility fishery, which is also subject to significant impacts from marine disasters. Conducting research on the extraction of facility fishery areas based on remote sensing technology is crucial to efficiently comprehending the configuration of coastal culture patterns and to establishing scientifically sound plans for managing and administering these areas. The extensive dispersion of facility fishery areas in coastal regions poses a challenge to the conduction of comprehensive field surveys. The utilization of satellite remote sensing images for information extraction has emerged as a significant area of research in the fields of coastal fishery and ecological environment. This study provides a systematic description of the current research status of coastal fishery area extraction methods using remote sensing technology from 2000 to 2022 reported in the literature. The methods discussed include the visual interpretation method, image element-based classification, object-based classification, supervised classification, unsupervised classification, and neural network classification. The extraction accuracy of each method in the coastal facility fishery area is evaluated, and the advantages and disadvantages of these methods, as well as their limitations and existing problems, are analyzed in detail, to construct a reference framework for the investigation of the high-precision extraction of facility fishery areas from satellite remote sensing images.

show abstract

Multi-Attention-Based Semantic Segmentation Network for Land Cover Remote Sensing Images

Cited by 6 publications

References 43 publications

mid-DeepLabv3+: A Novel Approach for Image Semantic Segmentation Applied to African Food Dietary Assessments

mid-DeepLabv3+: A Novel Approach for Image Semantic Segmentation Applied to African Food Dietary Assessments

New Fusion Approach of Spatial and Channel Attention for Semantic Segmentation of Very High Spatial Resolution Remote Sensing Images

Review of the Accuracy of Satellite Remote Sensing Techniques in Identifying Coastal Aquaculture Facilities

Contact Info

Product

Resources

About