Abstract
In this paper, automatic extraction of multi-context and multi-scale land use/land cover vegetation from high-resolution remote sensing images is tackled, aiming to solve typical challenges in classifying remote sensing images at a pixel level. To solve small inter-class differences and large intra-class differences between the vegetation and background, we introduce a vegetation-feature-sensitive focus perception (FP) module. Considering the intrinsic properties of vegetation objects, we established an adaptive context inference (ACI) model under a supervised setting that includes a context model to represent relationships between a center pixel and its neighbors under semantic constraints, as well as the spatial structures of vegetation features. Comparative experiments on the ZY-3 and Gaofen Image Dataset (GID) datasets demonstrate the effectiveness of our proposed automatic vegetation extraction model against the baseline Deeplab v3+ model. Taking precision, kappa coefficient, mean intersection over union (miou), precision rate, and F1-score as the evaluation indexes, the results showed an improvement in the precision by at least 1.44% and miou by 2.47%, over the baseline Deeplab v3+ model. In addition, the ACI module improved the precision and miou by 2% and 3.88%, and the FP module improved the precision and miou by 1.13% and 1.65%. These results and statistics of these comprehensive experiments illustrated that our adaptive and effective vegetation extraction model could satisfy different requirements of land use/land cover mapping applications.
Highlights
The main contributions of this paper are as follows: (1) We introduced a focus perception (FP) module to extract sensitive features from different types of vegetation and an integrated attention mechanism containing high-level and low-level semantic information to solve the problem of small interclass and large intra-class differences; (2) We established an adaptive context inference (ACI) model under a supervised setting to satisfy the inference of spatial structure relations, based on the data-driven pattern recognition methodology; (3) We conducted comparative experiments to analyze the influences of different modules on vegetation extraction results, as well as an ablation study and parameter sensitivity analysis on ACI module, which gave some conclusions about different modules’ influences
As shown in Figure 3, the proposed approach consists of two novel components, a FP module to extract sensitive features from different types of vegetation and an ACI module to refine the boundary location of extracted segments in the framework of a fully convolutional neural network
The original baseline Deeplab v3+ model is introduced in Section 3, part A, details of the FP module and ACI module are illustrated in Section 3, part B and Section 3, part C
Summary
Classification of HRRSI is exposed to new challenges and potentials in different applications, The associate editor coordinating the review of this manuscript and approving it for publication was Chao Tong. Such as urban planning, precision agriculture, and resource management. To satisfy requirements to infer the land properties for land use or land cover applications, it’s indispensable to combine heuristic, empirical, or physicallybased models integrated with ground-knowledge or user interpretation [11].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
