Cascaded Residual Attention Enhanced Road Extraction from Remote Sensing Images

Efficient and accurate road extraction from remote sensing imagery is important for applications related to navigation and Geographic Information System updating. Existing data-driven methods based on semantic segmentation recognize roads from images pixel by pixel, which generally uses only local spatial information and causes issues of discontinuous extraction and jagged boundary recognition. To address these problems, we propose a cascaded attention-enhanced architecture to extract boundary-refined roads from remote sensing images. Our proposed architecture uses spatial attention residual blocks on multi-scale features to capture long-distance relations and introduce channel attention layers to optimize the multi-scale features fusion. Furthermore, a lightweight encoder-decoder network is connected to adaptively optimize the boundaries of the extracted roads. Our experiments showed that the proposed method outperformed existing methods and achieved state-of-the-art results on the Massachusetts dataset. In addition, our method achieved competitive results on more recent benchmark datasets, e.g., the DeepGlobe and the Huawei Cloud road extraction challenge.

Segmentation of Agricultural Parcels in Satellite Images Based on Historical Vegetation Index Data

This paper considered the issue of agricultural fields boundary recognition in satellite images. A novel algorithm based on the aggregated history of vegetation index data obtained via open satellite data, Sentinel-2, was proposed. The proposed algorithm included several basic steps, namely the detection of parcel regions on aggregated index data; the calculation of aggregated edge maps; the segmentation of parcel regions using the edges obtained; the computation of connected components and their contour extraction. In this paper, we showed that the use of aggregated vegetation index data and boundary maps allow for much more accurate agricultural field segmentation compared to the instant vegetation index approach. The quality of segmentation within regions of Russia and the Ukraine was estimated. The dataset that was used and Python implementation of the proposed algorithm were provided.

HTLinker: A Head-to-Tail Linker for Nested Named Entity Recognition

Named entity recognition (NER) aims to extract entities from unstructured text, and a nested structure often exists between entities. However, most previous studies paid more attention to flair named entity recognition while ignoring nested entities. The importance of words in the text should vary for different entity categories. In this paper, we propose a head-to-tail linker for nested NER. The proposed model exploits the extracted entity head as conditional information to locate the corresponding entity tails under different entity categories. This strategy takes part of the symmetric boundary information of the entity as a condition and effectively leverages the information from the text to improve the entity boundary recognition effectiveness. The proposed model considers the variability in the semantic correlation between tokens for different entity heads under different entity categories. To verify the effectiveness of the model, numerous experiments were implemented on three datasets: ACE2004, ACE2005, and GENIA, with F1-scores of 80.5%, 79.3%, and 76.4%, respectively. The experimental results show that our model is the most effective of all the methods used for comparison.

Paragraph Boundary Recognition in Novels for Story Understanding

The understanding of narrative stories by computer is an important task for their automatic generation. To date, high-performance neural-network technologies such as BERT have been applied to tasks such as the Story Cloze Test and Story Completion. In this study, we focus on the text segmentation of novels into paragraphs, which is an important writing technique for readers to deepen their understanding of the texts. This type of segmentation, which we call “paragraph boundary recognition”, can be considered to be a binary classification problem in terms of the presence or absence of a boundary, such as a paragraph between target sentences. However, in this case, the data imbalance becomes a bottleneck because the number of paragraphs is generally smaller than the number of sentences. To deal with this problem, we introduced several cost-sensitive loss functions, namely. focal loss, dice loss, and anchor loss, which were robust for imbalanced classification in BERT. In addition, introducing the threshold-moving technique into the model was effective in estimating paragraph boundaries. As a result of the experiment on three newly created datasets, BERT with dice loss and threshold moving obtained a higher F1 than the original BERT had using cross-entropy loss as its loss function (76% to 80%, 50% to 54%, 59% to 63%).

Development of the innovative differential tool wear modeling for high-feed milling and its experimental verification

During the high-feed milling process, the vibrations generated by interrupted cutting cause changes in the instantaneous tool posture, as well as in the working angle and the distribution of the thermal stress coupling fields of each tool blade. These changes result in significant differences in the wear distribution of each tool blade. In this research, well-designed experiments for the high-feed milling of titanium alloys were carried out to identify the key factors affecting the differential wear on the milling tool insert blades. A differential tool wear model for the tool blades was developed in order to comprehensively describe the effects of the location error of the blades, the vibrations in the tool posture, and the working angle of each tool blade. The wear status of the milling tool was simulated based on the dynamic tool trajectories and postures derived by the model, and the entire simulated wear distribution was investigated with an innovative wear boundary recognition method. The differential tool wear model was evaluated and validated by the milling experiments and further supported by simulations.

Bidirectional Sliding Window for Boundary Recognition of Pavement Construction Area Using GPS-RTK

Unmanned pavement construction is of great significance in China, and the primary issue to be solved is how to identify the boundaries of the Pavement Construction Area (PCA). In this paper, we present a simple yet effective method, named the Bidirectional Sliding Window (BSW) method, for PCA boundary recognition. We first collected the latitude and longitude coordinates of the four vertices of straight quadrilaterals using the Global Positioning System—Real Time Kinematic (GPS-RTK) measurement principle for precise single-point positioning, analyzed single-point positioning accuracy, and determined the measurement error distribution models. Next, we took points at equal intervals along one straight line segment and two curved line segments with curvature radii of 70 m to 300 m, for simulation experiments. BSW was adopted to recognize the Possible Irrelevant Points (PIP) and Relevant Points (RP), which were used to identify PCA boundaries. Experiments show that when the proposed BSW algorithm is used and the single-point positioning accuracy is at the centimeter level, PCA boundary recognition for straight polygons reaches single-point positioning accuracy, and that for curved polygons reaches decimeter-level accuracy.