Intelligent Mapping of Urban Forests from High-Resolution Remotely Sensed Imagery Using Object-Based U-Net-DenseNet-Coupled Network

He, Shaobai; Du, Huaqiang; Zhou, Guomo; Li, Xuejian; Mao, Fangjie; Zhu, Di’en; Xu, Yabei; Meng, Zhongjie; Huang, Zihao; Liu, Hua; Luo, Xin

doi:10.3390/rs12233928

Cited by 16 publications

(9 citation statements)

References 65 publications

(71 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors found that these satellites offer temporal resolution and other characteristics, such as wavelength, were deemed useful for the analysis of urban forest at the landscape scale. However, He et al [87], argue that spectral indices derived from medium resolution imagery are still limited in extensive use in cities since many elements have similar spectral signatures, which cause strong heterogeneity and make object classification difficult.…”

Section: Satellite Imagerymentioning

confidence: 99%

“…WorldView 3 (WV3), which achieves a higher spatial resolution (2 m) in the spectral bands compared to WV2, was used as the unique data source in two studies [86,87]. Namely, Vahidi et al [86] used WV3 for tree identification in urban orchards obtaining 91% accuracy.…”

Section: Satellite Imagerymentioning

confidence: 99%

“…However, these characteristics make use of this method limited to the inventory of trees in small and homogeneous areas within the city. Meanwhile, He et al [87] used WV3 for automatic mapping of wooded areas in the Yuhang District in China. This research was based on the use of vegetation indices from the visible spectrum bands of WV3 and the NIR.…”

Section: Satellite Imagerymentioning

confidence: 99%

See 2 more Smart Citations

Remotely Sensed Tree Characterization in Urban Areas: A Review

et al. 2021

View full text Add to dashboard Cite

Urban trees and forests provide multiple ecosystem services (ES), including temperature regulation, carbon sequestration, and biodiversity. Interest in ES has increased amongst policymakers, scientists, and citizens given the extent and growth of urbanized areas globally. However, the methods and techniques used to properly assess biodiversity and ES provided by vegetation in urban environments, at large scales, are insufficient. Individual tree identification and characterization are some of the most critical issues used to evaluate urban biodiversity and ES, given the complex spatial distribution of vegetation in urban areas and the scarcity or complete lack of systematized urban tree inventories at large scales, e.g., at the regional or national levels. This often limits our knowledge on their contributions toward shaping biodiversity and ES in urban areas worldwide. This paper provides an analysis of the state-of-the-art studies and was carried out based on a systematic review of 48 scientific papers published during the last five years (2016–2020), related to urban tree and greenery characterization, remote sensing techniques for tree identification, processing methods, and data analysis to classify and segment trees. In particular, we focused on urban tree and forest characterization using remotely sensed data and identified frontiers in scientific knowledge that may be expanded with new developments in the near future. We found advantages and limitations associated with both data sources and processing methods, from which we drew recommendations for further development of tree inventory and characterization in urban forestry science. Finally, a critical discussion on the current state of the methods, as well as on the challenges and directions for future research, is presented.

show abstract

Section: Satellite Imagerymentioning

confidence: 99%

Section: Satellite Imagerymentioning

confidence: 99%

Section: Satellite Imagerymentioning

confidence: 99%

See 1 more Smart Citation

Remotely Sensed Tree Characterization in Urban Areas: A Review

et al. 2021

View full text Add to dashboard Cite

show abstract

“…To solve these boundary problems, the most commonly used method is skip connections, where shallow layers are fused in the CNNs due to the rich contour information [12,31]. Mou et al [32] proposed a method that combined FCN [33] and a recurrent neural network (RNN [34]) for achieving accurate object boundary inference and semantic segmentation [35].…”

Section: Boundary Problemsmentioning

confidence: 99%

HRCNet: High-Resolution Context Extraction Network for Semantic Segmentation of Remote Sensing Images

Zhang

et al. 2020

Remote Sensing

101

View full text Add to dashboard Cite

Semantic segmentation is a significant method in remote sensing image (RSIs) processing and has been widely used in various applications. Conventional convolutional neural network (CNN)-based semantic segmentation methods are likely to lose the spatial information in the feature extraction stage and usually pay little attention to global context information. Moreover, the imbalance of category scale and uncertain boundary information meanwhile exists in RSIs, which also brings a challenging problem to the semantic segmentation task. To overcome these problems, a high-resolution context extraction network (HRCNet) based on a high-resolution network (HRNet) is proposed in this paper. In this approach, the HRNet structure is adopted to keep the spatial information. Moreover, the light-weight dual attention (LDA) module is designed to obtain global context information in the feature extraction stage and the feature enhancement feature pyramid (FEFP) structure is promoted and employed to fuse the contextual information of different scales. In addition, to achieve the boundary information, we design the boundary aware (BA) module combined with the boundary aware loss (BAloss) function. The experimental results evaluated on Potsdam and Vaihingen datasets show that the proposed approach can significantly improve the boundary and segmentation performance up to 92.0% and 92.3% on overall accuracy scores, respectively. As a consequence, it is envisaged that the proposed HRCNet model will be an advantage in remote sensing images segmentation.

show abstract

“…The extraction methods of urban land use information mainly include support vector machines [7,8], decision trees [9], random forest (RF) models [10,11], and deep learning [12][13][14]. Most of these methods are based on supervised learning, which requires many labeled samples for model training [15].…”

Section: Introductionmentioning

confidence: 99%

A Novel Query Strategy-Based Rank Batch-Mode Active Learning Method for High-Resolution Remote Sensing Image Classification

Luo

Zhou

et al. 2021

Remote Sensing

Self Cite

View full text Add to dashboard Cite

An informative training set is necessary for ensuring the robust performance of the classification of very-high-resolution remote sensing (VHRRS) images, but labeling work is often difficult, expensive, and time-consuming. This makes active learning (AL) an important part of an image analysis framework. AL aims to efficiently build a representative and efficient library of training samples that are most informative for the underlying classification task, thereby minimizing the cost of obtaining labeled data. Based on ranked batch-mode active learning (RBMAL), this paper proposes a novel combined query strategy of spectral information divergence lowest confidence uncertainty sampling (SIDLC), called RBSIDLC. The base classifier of random forest (RF) is initialized by using a small initial training set, and each unlabeled sample is analyzed to obtain the classification uncertainty score. A spectral information divergence (SID) function is then used to calculate the similarity score, and according to the final score, the unlabeled samples are ranked in descending lists. The most “valuable” samples are selected according to ranked lists and then labeled by the analyst/expert (also called the oracle). Finally, these samples are added to the training set, and the RF is retrained for the next iteration. The whole procedure is iteratively implemented until a stopping criterion is met. The results indicate that RBSIDLC achieves high-precision extraction of urban land use information based on VHRRS; the accuracy of extraction for each land-use type is greater than 90%, and the overall accuracy (OA) is greater than 96%. After the SID replaces the Euclidean distance in the RBMAL algorithm, the RBSIDLC method greatly reduces the misclassification rate among different land types. Therefore, the similarity function based on SID performs better than that based on the Euclidean distance. In addition, the OA of RF classification is greater than 90%, suggesting that it is feasible to use RF to estimate the uncertainty score. Compared with the three single query strategies of other AL methods, sample labeling with the SIDLC combined query strategy yields a lower cost and higher quality, thus effectively reducing the misclassification rate of different land use types. For example, compared with the Batch_Based_Entropy (BBE) algorithm, RBSIDLC improves the precision of barren land extraction by 37% and that of vegetation by 14%. The 25 characteristics of different land use types screened by RF cross-validation (RFCV) combined with the permutation method exhibit an excellent separation degree, and the results provide the basis for VHRRS information extraction in urban land use settings based on RBSIDLC.

show abstract

Intelligent Mapping of Urban Forests from High-Resolution Remotely Sensed Imagery Using Object-Based U-Net-DenseNet-Coupled Network

Cited by 16 publications

References 65 publications

Remotely Sensed Tree Characterization in Urban Areas: A Review

Remotely Sensed Tree Characterization in Urban Areas: A Review

HRCNet: High-Resolution Context Extraction Network for Semantic Segmentation of Remote Sensing Images

A Novel Query Strategy-Based Rank Batch-Mode Active Learning Method for High-Resolution Remote Sensing Image Classification

Contact Info

Product

Resources

About