AOI-shapes: An Efficient Footprint Algorithm to Support Visualization of User-defined Urban Areas of Interest

Understanding urban areas of interest (AOIs) is essential in many real-life scenarios, and such AOIs can be computed based on the geographic points that satisfy user queries. In this article, we study the problem of efficient and effective visualization of user-defined urban AOIs in an interactive manner. In particular, we first define the problem of user-defined AOI visualization based on a real estate data visualization scenario, and we illustrate why a novel footprint method is needed to support the visualization. After extensively reviewing existing “footprint” methods, we propose a parameter-free footprint method, named AOI-shapes, to capture the boundary information of a user-defined urban AOI. Next, to allow interactive query refinements by the user, we propose two efficient and scalable algorithms to incrementally generate urban AOIs by reusing existing visualization results. Finally, we conduct extensive experiments with both synthetic and real-world datasets to demonstrate the quality and efficiency of the proposed methods.

Inter-Level Feature Balanced Fusion Network for Street Scene Segmentation

Semantic segmentation, as a pixel-level recognition task, has been widely used in a variety of practical scenes. Most of the existing methods try to improve the performance of the network by fusing the information of high and low layers. This kind of simple concatenation or element-wise addition will lead to the problem of unbalanced fusion and low utilization of inter-level features. To solve this problem, we propose the Inter-Level Feature Balanced Fusion Network (IFBFNet) to guide the inter-level feature fusion towards a more balanced and effective direction. Our overall network architecture is based on the encoder–decoder architecture. In the encoder, we use a relatively deep convolution network to extract rich semantic information. In the decoder, skip-connections are added to connect and fuse low-level spatial features to restore a clearer boundary expression gradually. We add an inter-level feature balanced fusion module to each skip connection. Additionally, to better capture the boundary information, we added a shallower spatial information stream to supplement more spatial information details. Experiments have proved the effectiveness of our module. Our IFBFNet achieved a competitive performance on the Cityscapes dataset with only finely annotated data used for training and has been greatly improved on the baseline network.

Cross-Boundary Information Sharing By Knowledge Brokers During A Disaster

<p>This thesis explores and investigates the process of cross-boundary information sharing by knowledge brokers (KB) during a disaster using lenses of knowledge management and naturalistic decision making. The study integrated interpretivist and positivist stances, conducted using qualitative methods. It used a multiple case embedded research design and in-depth face-to-face interviews as the method of inquiry and an inductive process of theory generation. The cases were in the context of disasters that occurred in New Zealand. The unit of analysis was the scenarios that KB experienced during disasters. Based on a four stage analysis of the data, there were two phases that KB went through in assessing the veracity of the information they received and deciding to whom the information is relevant. In each phase, KB were relying on different cognitive resources to filter and to match the information. It was also found that there were different types of boundary, information and disasters. Interestingly, it was found that KB used different tactics to make the decision on the information’s veracity and to whom it is relevant. The primary contribution of this thesis is the generation and explanation of the theoretical model of cross-boundary information sharing by KB during a disaster. This theory can also be used by practitioners as a guide to improve disaster management training and for the community to prepare stronger resilience plans.</p>

Cross-Boundary Information Sharing By Knowledge Brokers During A Disaster

<p>This thesis explores and investigates the process of cross-boundary information sharing by knowledge brokers (KB) during a disaster using lenses of knowledge management and naturalistic decision making. The study integrated interpretivist and positivist stances, conducted using qualitative methods. It used a multiple case embedded research design and in-depth face-to-face interviews as the method of inquiry and an inductive process of theory generation. The cases were in the context of disasters that occurred in New Zealand. The unit of analysis was the scenarios that KB experienced during disasters. Based on a four stage analysis of the data, there were two phases that KB went through in assessing the veracity of the information they received and deciding to whom the information is relevant. In each phase, KB were relying on different cognitive resources to filter and to match the information. It was also found that there were different types of boundary, information and disasters. Interestingly, it was found that KB used different tactics to make the decision on the information’s veracity and to whom it is relevant. The primary contribution of this thesis is the generation and explanation of the theoretical model of cross-boundary information sharing by KB during a disaster. This theory can also be used by practitioners as a guide to improve disaster management training and for the community to prepare stronger resilience plans.</p>

CLASSIC-Utterance-Boundary: A chunking-based model of early naturalistic word segmentation.

Word segmentation is a crucial step in children’s vocabulary learning. Evaluation of computational models has focused on capturing infants’ segmentation performance in small-scale, artificial tasks, with less attention given to models’ performance on large-scale corpora of child-directed speech. Here, we extended CLASSIC (Jones et al., 2021) - a corpus-trained chunking model that can simulate several language learning and memory phenomena - to allow it to perform word segmentation using utterance boundary information, CLASSIC-UB. Further, we addressed current practices of limited model-child comparisons and compared our model to children on a wide range of new and traditional measures. We show that the combination of chunking and utterance-boundary information used by CLASSIC-UB better approximates child word segmentation performance than other models. We conclude that a chunking-based learning mechanism might explain how infants perform word segmentation in naturalistic settings.

Application of 3D Dynamic Image Technology in Industrial Products

Aiming at the problems of manual testing of industrial products, a measurement method of industrial products based on three-dimensional dynamic imaging technology is proposed. The products on the production line are dynamically photographed from different angles and within a certain period of time by using cameras. Then the obtained Image denoising processing and contour tracking based on chain code table and line segment table to obtain boundary information and regional information of each enclosed area of the image. Experimental tests show that the test accuracy of this method is 100%, which is suitable for real-time detection. Fully automated research on product testing provides the foundation.

Matching Document Pairs using Multi-Feature Semantic Fusion Based on Knowledge Graph

Discriminating the homology and heterogeneity of two documents in information retrieval is very important and difficult step. Existing methods mainly focus on word-based document duplicate checking or sentence pairs matching except manual verification which need a lot of human resource cost. The word-based document duplicate checking can not judge the similarity of two documents from the semantic level and the matching sentence pair methods can not effectively mine the semantic information from a long text which is frequent retrieval results. A concept-based Multi-Feature Semantic Fusion Model (MFSFM) is proposed. It employs multi-feature enhanced semantics to construct a concept map for represent the document, and employs a multi-convolution mixed residual CNN module to introduce local attention mechanism for improve the sensitivity of conceptual boundary information. To improve the feasibility of the proposed MFSFM based on concept maps, two multi-feature document data sets are set up. Each of them consists of about 500 actual scientific and technological project feasibility reports. Experimental results based on the actual datasets show that the proposed MFSFM converges quickly while expanding the latest methods of natural language matching at the accuracy rate.

Multi-Object Segmentation in Complex Urban Scenes from High-Resolution Remote Sensing Data

Terrestrial features extraction, such as roads and buildings from aerial images using an automatic system, has many usages in an extensive range of fields, including disaster management, change detection, land cover assessment, and urban planning. This task is commonly tough because of complex scenes, such as urban scenes, where buildings and road objects are surrounded by shadows, vehicles, trees, etc., which appear in heterogeneous forms with lower inter-class and higher intra-class contrasts. Moreover, such extraction is time-consuming and expensive to perform by human specialists manually. Deep convolutional models have displayed considerable performance for feature segmentation from remote sensing data in the recent years. However, for the large and continuous area of obstructions, most of these techniques still cannot detect road and building well. Hence, this work’s principal goal is to introduce two novel deep convolutional models based on UNet family for multi-object segmentation, such as roads and buildings from aerial imagery. We focused on buildings and road networks because these objects constitute a huge part of the urban areas. The presented models are called multi-level context gating UNet (MCG-UNet) and bi-directional ConvLSTM UNet model (BCL-UNet). The proposed methods have the same advantages as the UNet model, the mechanism of densely connected convolutions, bi-directional ConvLSTM, and squeeze and excitation module to produce the segmentation maps with a high resolution and maintain the boundary information even under complicated backgrounds. Additionally, we implemented a basic efficient loss function called boundary-aware loss (BAL) that allowed a network to concentrate on hard semantic segmentation regions, such as overlapping areas, small objects, sophisticated objects, and boundaries of objects, and produce high-quality segmentation maps. The presented networks were tested on the Massachusetts building and road datasets. The MCG-UNet improved the average F1 accuracy by 1.85%, and 1.19% and 6.67% and 5.11% compared with UNet and BCL-UNet for road and building extraction, respectively. Additionally, the presented MCG-UNet and BCL-UNet networks were compared with other state-of-the-art deep learning-based networks, and the results proved the superiority of the networks in multi-object segmentation tasks.