Review of Image Classification Algorithms Based on Convolutional Neural Networks

Chen, Leiyu; Li, Shaobo; Bai, Qiang; Yang, Jing; Jiang, Sanlong; Miao, Yanming

doi:10.3390/rs13224712

Cited by 204 publications

(73 citation statements)

References 232 publications

(349 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Among them, fully convolutional network models are widely used in the field. By testing the performances of different semantic segmentation models on public datasets, it was found that the detection accuracy of the fully convolutional network models is much better than that of previous methods [15][16][17]. Hence, researchers have introduced FCN and FCN-based models into the field of flame segmentation.…”

Section: Introductionmentioning

confidence: 99%

Comparative Research on Forest Fire Image Segmentation Algorithms Based on Fully Convolutional Neural Networks

Wang

Peng

2022

Forests

View full text Add to dashboard Cite

In recent years, frequent forest fires have plagued countries all over the world, causing serious economic damage and human casualties. Faster and more accurate detection of forest fires and timely interventions have become a research priority. With the advancement in deep learning, fully convolutional network architectures have achieved excellent results in the field of image segmentation. More researchers adopt these models to segment flames for fire monitoring, but most of the works are aimed at fires in buildings and industrial scenarios. However, there are few studies on the application of various fully convolutional models to forest fire scenarios, and comparative experiments are inadequate. In view of the above problems, on the basis of constructing the dataset with remote-sensing images of forest fires captured by unmanned aerial vehicles (UAVs) and the targeted optimization of the data enhancement process, four classical semantic segmentation models and two backbone networks are selected for modeling and testing analysis. By comparing inference results and the evaluation indicators of models such as mPA and mIoU, we can find out the models that are more suitable for forest fire segmentation scenarios. The results show that the U-Net model with Resnet50 as a backbone network has the highest segmentation accuracy of forest fires with the best comprehensive performance, and is more suitable for scenarios with high-accuracy requirements; the DeepLabV3+ model with Resnet50 is slightly less accurate than U-Net, but it can still ensure a satisfying segmentation performance with a faster running speed, which is suitable for scenarios with high real-time requirements. In contrast, FCN and PSPNet have poorer segmentation performance and, hence, are not suitable for forest fire detection scenarios.

show abstract

Section: Introductionmentioning

confidence: 99%

Comparative Research on Forest Fire Image Segmentation Algorithms Based on Fully Convolutional Neural Networks

Wang

Peng

2022

Forests

View full text Add to dashboard Cite

show abstract

“…The image can be directly used as input for training. The model can automatically learn the pixel difference of the water seepage image to quickly and accurately complete the classi cation target [23][24][25].…”

Section: Introductionmentioning

confidence: 99%

Research on Water Seepage Detection Technology of Tunnel Asphalt Pavement Based on Deep Learning and Digital Image Processing

Zhao

et al. 2022

Preprint

View full text Add to dashboard Cite

In order to improve the traffic safety of the tunnel pavement and reduce the impact of water seepage on the pavement structure, a convolutional neural network (CNN) model is established based on image detection technology to realize the identification, classification and statistics of pavement seepage. First, compared with the MobileNet network model, the deep learning model EfficientNet network model was built, and the accuracy of the two models was analyzed for pavement seepage recognition. The F1 Score was introduced to evaluate the accuracy and comprehensive performance of the two models for different types of seepage characteristics. Then the three gray processing methods, six threshold segmentation methods, as well as three filtering methods were compared to extract water seepage characteristics of digital image. Finally, based on the processed image, a calculation method of water seepage area was proposed to identify the actual asphalt pavement water seepage. The result shows that the recognition accuracy of the EfficientNet network model in the training set and the validation set are 99.85% and 97.53%, respectively, and the prediction accuracy is 98.00%. The accuracy of pavement water seepage recognition and prediction is better than the MobileNet network model. Using the cvtColor function for gray processing, using THRESH_BINARY for threshold segmentation, and using a combination of median filtering and morphological opening operations for image noise reduction can effectively extract water seepage characteristics. The water seepage area calculated by the proposed method has a small difference with the actual water seepage area, and the effect is agreeable.

show abstract

“…Furthermore, the aggregation could lead to a loss of information, and thus it would be interesting to explore classification methods that deal with all the pixels inside an ITC and not with an aggregation of them. In recent years, much attention has been devoted to the use of deep learning methods [21][22][23][24][25][26] and, in particular, convolutional neural networks (CNN) [24,[27][28][29]. These types of classification networks allow the exploitation of both the spectral and spatial information, which may improve the classification results substantially [27].…”

Section: Introductionmentioning

confidence: 99%

Wood Decay Detection in Norway Spruce Forests Based on Airborne Hyperspectral and ALS Data

et al. 2022

View full text Add to dashboard Cite

Wood decay caused by pathogenic fungi in Norway spruce forests causes severe economic losses in the forestry sector, and currently no efficient methods exist to detect infected trees. The detection of wood decay could potentially lead to improvements in forest management and could help in reducing economic losses. In this study, airborne hyperspectral data were used to detect the presence of wood decay in the trees in two forest areas located in Etnedal (dataset I) and Gran (dataset II) municipalities, in southern Norway. The hyperspectral data used consisted of images acquired by two sensors operating in the VNIR and SWIR parts of the spectrum. Corresponding ground reference data were collected in Etnedal using a cut-to-length harvester while in Gran, field measurements were collected manually. Airborne laser scanning (ALS) data were used to detect the individual tree crowns (ITCs) in both sites. Different approaches to deal with pixels inside each ITC were considered: in particular, pixels were either aggregated to a unique value per ITC (i.e., mean, weighted mean, median, centermost pixel) or analyzed in an unaggregated way. Multiple classification methods were explored to predict rot presence: logistic regression, feed forward neural networks, and convolutional neural networks. The results showed that wood decay could be detected, even if with accuracy varying among the two datasets. The best results on the Etnedal dataset were obtained using a convolution neural network with the first five components of a principal component analysis as input (OA = 65.5%), while on the Gran dataset, the best result was obtained using LASSO with logistic regression and data aggregated using the weighted mean (OA = 61.4%). In general, the differences among aggregated and unaggregated data were small.

show abstract

Review of Image Classification Algorithms Based on Convolutional Neural Networks

Cited by 204 publications

References 232 publications

Comparative Research on Forest Fire Image Segmentation Algorithms Based on Fully Convolutional Neural Networks

Comparative Research on Forest Fire Image Segmentation Algorithms Based on Fully Convolutional Neural Networks

Research on Water Seepage Detection Technology of Tunnel Asphalt Pavement Based on Deep Learning and Digital Image Processing

Wood Decay Detection in Norway Spruce Forests Based on Airborne Hyperspectral and ALS Data

Contact Info

Product

Resources

About