Search

Image segmentation plays a significant role in remote sensing image processing. Among numerous segmentation algorithms, the region-merging segmentation algorithm is widely used due to its well-organized structure and outstanding results. Many merging criteria (MC) were designed to improve the accuracy of region-merging segmentation, but each MC has its own shortcomings, which can cause segmentation errors. Segmentation accuracy can be improved by referring to the segmentation results. To achieve this, an approach for detecting and correcting region-merging image segmentation errors is proposed, and then an iterative optimization model is established. The main contributions of this paper are as follows: (1) The conflict types of matching segment pairs are divided into scale-expression conflict (SEC) and region-ownership conflict (ROC), and ROC is more suitable for optimization. (2) An equal-scale local evaluation method was designed to quantify the optimization potential of ROC. (3) A regional anchoring strategy is proposed to preserve the results of the previous iteration optimization. Three QuickBird satellite images of different land-cover types were used for validating the proposed approach. Both unsupervised and supervised evaluation results prove that the proposed approach can effectively improve segmentation accuracy. All explicit and implicit optimization modes are concluded, which further illustrate the stability of the proposed approach. [ABSTRACT FROM AUTHOR]

Compositing is a fundamental pre-processing for remote sensing images. Landsat series optical satellite images are influenced by cloud coverage, acquisition time, sensor types, and seasons, which make it difficult to obtain continuous cloud-free observations. It limits the potential use and analysis of time series images. Therefore, global change researchers urgently need to 'composite' multi-sensor and multi-temporal images. Many previous studies have used isolated pixel-based algorithms to composite Landsat images; however, this study is different and develops a batch pixel-based algorithm for composing continuous cloud-free Landsat images. The algorithm chooses the best scene as the reference image using the user-specified image ID or related parameters. Further, it accepts all valid pixels in the reference image as the main part of the result and develops a priority coefficient model. Development of this model is based on the criteria of five factors including cloud coverage, acquisition time, acquisition year, observation seasons, and sensor types to select substitutions for the missing pixels in batches and to merge them into the final composition. This proposed batch pixel-based algorithm may provide reasonable compositing results on the basis of the experimental test results of all Landsat 8 images in 2019 and the visualization results of 12 locations in 2020. In comparison with the isolated pixel-based algorithms, our algorithm eliminates band dispersion, requires fewer images, and enhances the composition's pixel concentration considerably. The algorithm provides a complete and practical framework for time series image processing for Landsat series satellites, and has the potential to be applied to other optical satellite images as well. [ABSTRACT FROM AUTHOR]

Automatic building extraction using a single data type, either 2D remotely-sensed images or light detection and ranging 3D point clouds, remains insufficient to accurately delineate building outlines for automatic mapping, despite active research in this area and the significant progress which has been achieved in the past decade. This paper presents an effective approach to extracting buildings from Unmanned Aerial Vehicle (UAV) images through the incorporation of superpixel segmentation and semantic recognition. A framework for building extraction is constructed by jointly using an improved Simple Linear Iterative Clustering (SLIC) algorithm and Multiscale Siamese Convolutional Networks (MSCNs). The SLIC algorithm, improved by additionally imposing a digital surface model for superpixel segmentation, namely 6D-SLIC, is suited for building boundary detection under building and image backgrounds with similar radiometric signatures. The proposed MSCNs, including a feature learning network and a binary decision network, are used to automatically learn a multiscale hierarchical feature representation and detect building objects under various complex backgrounds. In addition, a gamma-transform green leaf index is proposed to truncate vegetation superpixels for further processing to improve the robustness and efficiency of building detection, the Douglas–Peucker algorithm and iterative optimization are used to eliminate jagged details generated from small structures as a result of superpixel segmentation. In the experiments, the UAV datasets, including many buildings in urban and rural areas with irregular shapes and different heights and that are obscured by trees, are collected to evaluate the proposed method. The experimental results based on the qualitative and quantitative measures confirm the effectiveness and high accuracy of the proposed framework relative to the digitized results. The proposed framework performs better than state-of-the-art building extraction methods, given its higher values of recall, precision, and intersection over Union (IoU). [ABSTRACT FROM AUTHOR]