Fully Convolutional Networks and Geographic Object-Based Image Analysis for the Classification of VHR Imagery

Mboga, Nicholus; Georganos, Stefanos; Grippa, Taïs; Lennert, Moritz; Vanhuysse, Sabine; Wolff, Éléonore

doi:10.3390/rs11050597

Cited by 53 publications

(45 citation statements)

References 43 publications

(58 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They also employed ancillary data and image texture rasters. In a recent work, Mboga et al [46] applied a fully convolutional neural network to OBIA-derived segmentation to produce landcover maps in an urban setting.…”

Section: Segmentation and Classificationmentioning

confidence: 99%

Identifying Vegetation in Arid Regions Using Object-Based Image Analysis with RGB-Only Aerial Imagery

2019

View full text Add to dashboard Cite

Vegetation state is usually assessed by calculating vegetation indices (VIs) derived from remote sensing systems where the near infrared (NIR) band is used to enhance the vegetation signal. However VIs are pixel-based and require both visible and NIR bands. Yet, most archived photographs were obtained with cameras that record only the three visible bands. Attempts to construct VIs with the visible bands alone have shown only limited success, especially in drylands. The current study identifies vegetation patches in the hyperarid Israeli desert using only the visible bands from aerial photographs by adapting an alternative geospatial object-based image analysis (GEOBIA) routine, together with recent improvements in preprocessing. The preprocessing step selects a balanced threshold value for image segmentation using unsupervised parameter optimization. Then the images undergo two processes: segmentation and classification. After tallying modeled vegetation patches that overlap true tree locations, both true positive and false positive rates are obtained from the classification and receiver operating characteristic (ROC) curves are plotted. The results show successful identification of vegetation patches in multiple zones from each study area, with area under the ROC curve values between 0.72 and 0.83.

show abstract

Section: Segmentation and Classificationmentioning

confidence: 99%

Identifying Vegetation in Arid Regions Using Object-Based Image Analysis with RGB-Only Aerial Imagery

2019

View full text Add to dashboard Cite

show abstract

“…For example, conditional random field (CRF) models are used as a postprocessing step to improve the classification by imposing a smoothness prior in low-level vision, so that neighboring pixels are more likely to be allocated the same class label [36]. An object-based classification method, which is adequate for describing boundaries of geo-objects by image segmentation, is combined with abstracted deep features to increase the classification accuracy [31,37]. In addition, a variety of methods are used in an attempt to add additional data to the FCN, such as digital surface models (DSM), vegetation indices (VI), and edge information [38][39][40][41].…”

Section: Fusion Of Multilevel Deep Featuresmentioning

confidence: 99%

Deep Feature Fusion with Integration of Residual Connection and Attention Model for Classification of VHR Remote Sensing Images

et al. 2019

View full text Add to dashboard Cite

The classification of very-high-resolution (VHR) remote sensing images is essential in many applications. However, high intraclass and low interclass variations in these kinds of images pose serious challenges. Fully convolutional network (FCN) models, which benefit from a powerful feature learning ability, have shown impressive performance and great potential. Nevertheless, only classification results with coarse resolution can be obtained from the original FCN method. Deep feature fusion is often employed to improve the resolution of outputs. Existing strategies for such fusion are not capable of properly utilizing the low-level features and considering the importance of features at different scales. This paper proposes a novel, end-to-end, fully convolutional network to integrate a multiconnection ResNet model and a class-specific attention model into a unified framework to overcome these problems. The former fuses multilevel deep features without introducing any redundant information from low-level features. The latter can learn the contributions from different features of each geo-object at each scale. Extensive experiments on two open datasets indicate that the proposed method can achieve class-specific scale-adaptive classification results and it outperforms other state-of-the-art methods. The results were submitted to the International Society for Photogrammetry and Remote Sensing (ISPRS) online contest for comparison with more than 50 other methods. The results indicate that the proposed method (ID: SWJ_2) ranks #1 in terms of overall accuracy, even though no additional digital surface model (DSM) data that were offered by ISPRS were used and no postprocessing was applied.

show abstract

“…Recently, deep neural networks (DNNs) are utilized for various kind of problems, which have shown immense performance in different applications, including image recognition [16,40,41]. Deep networks have changed the trend by replacing hand-engineered features to the learning strategy.…”

Section: B Deep Featuresmentioning

confidence: 99%

Deep CNN-based Features for Hand-Drawn Sketch Recognition via Transfer Learning Approach

Hayat¹,

She²,

Mateen³

et al. 2019

IJACSA

View full text Add to dashboard Cite

Image-based object recognition is a well-studied topic in the field of computer vision. Features extraction for hand-drawn sketch recognition and retrieval become increasingly popular among the computer vision researchers. Increasing use of touchscreens and portable devices raised the challenge for computer vision community to access the sketches more efficiently and effectively. In this article, a novel deep convolutional neural network-based (DCNN) framework for hand-drawn sketch recognition, which is composed of three wellknown pre-trained DCNN architectures in the context of transfer learning with global average pooling (GAP) strategy is proposed. First, an augmented-variants of natural images was generated and sum-up with TU-Berlin sketch images to all its corresponding 250 sketch object categories. Second, the features maps were extracted by three asymmetry DCNN architectures namely, Visual Geometric Group Network (VGGNet), Residual Networks (ResNet) and Inception-v3 from input images. Finally, the distinct features maps were concatenated and the features reductions were carried out under GAP layer. The resulting feature vector was fed into the softmax classifier for sketch classification results. The performance of proposed framework is comprehensively evaluated on augmented-variants TU-Berlin sketch dataset for sketch classification and retrieval task. Experimental outcomes reveal that the proposed framework brings substantial improvements over the state-of-the-art methods for sketch classification and retrieval.

show abstract

Fully Convolutional Networks and Geographic Object-Based Image Analysis for the Classification of VHR Imagery

Cited by 53 publications

References 43 publications

Identifying Vegetation in Arid Regions Using Object-Based Image Analysis with RGB-Only Aerial Imagery

Identifying Vegetation in Arid Regions Using Object-Based Image Analysis with RGB-Only Aerial Imagery

Deep Feature Fusion with Integration of Residual Connection and Attention Model for Classification of VHR Remote Sensing Images

Deep CNN-based Features for Hand-Drawn Sketch Recognition via Transfer Learning Approach

Contact Info

Product

Resources

About