Large-scale Urban Environments Research Articles

An efficient wastewater collection model for groundwater resource protection in smart cities

Efficient wastewater collection is a critical concern in the development of smart cities, where sustainable urban infrastructure is paramount. In the context of smart city wastewater optimization, this study highlights the need for a comprehensive approach that considers both surface water and groundwater dynamics. Existing methods often fall short in addressing groundwater-related concerns, with limitations in accounting for potential contamination and aquifer vulnerability. The proposed method integrates a nuanced understanding of groundwater aspects, providing a more robust and sustainable solution for urban water resource management. This research introduces a new approach that harnesses the power of Divide-And-Conquer (DAC) and Variable Neighborhood Search (VNS) to optimize wastewater collection systems in smart cities. The DAC strategy divides the city into manageable zones, simplifying the optimization problem for parallel processing in large-scale urban environments. VNS fine-tunes wastewater collection networks within each zone by exploring diverse neighborhood solutions. The DAC and VNS offers several benefits, including improved efficiency in wastewater transport, reduced energy consumption, and minimized environmental impact. Zoning the urban landscape is a strategic approach to optimize wastewater collection in smart cities. It involves dividing the city into manageable zones based on specific criteria such as geographical features, population density, and infrastructure layout. Each zone is treated as an independent unit for focused analysis and optimization. The optimization process employs a scoring function that combines weighted criteria, yielding a composite score for each geographical location. Applying a threshold or clustering algorithm group's locations into zones, facilitating tailored wastewater management strategies. By optimizing collection routes and infrastructure design, this approach assists smart cities in achieving sustainability goals while efficiently managing wastewater. The study showcases the potential of DAC and VNS as a robust and adaptable solution for wastewater collection in smart cities, contributing to the development of greener, more resource-efficient urban areas.

CrowdLOC-S: Crowdsourced seamless localization framework based on CNN-LSTM-MLP enhanced quality indicator

Seamless positioning ability has become an essential requirement in large-scale smart city scenes with the development of Artificial Intelligence of Things technology. The performance of seamless positioning is limited by the inaccurate crowdsourced navigation database, cumulative error of built-in sensors, and changeable measurement errors of different location sources. In order to solve these problems, this paper presents the CrowdLOC-S framework, which provides a concrete and accurate indoor/outdoor localization performance using the combination of crowdsourced Wi-Fi fingerprinting, Global Navigation Satellite System (GNSS), and low-cost sensors. A data and model dual-driven based trajectory estimator is developed for improving the long-term positioning performance of built-in sensors, and a hybrid one-dimensional convolutional neural network (1D-CNN), Bi-directional Long Short-Term Memory (Bi-LSTM), and Multilayer Perceptron (MLP) enhanced quality indicator is proposed for quality evaluation of crowdsourced trajectories and further Wi-Fi fingerprinting database construction. Besides, the transfer learning approach is applied in the quality indicator for autonomously predicting the location errors towards different indoor and outdoor location sources and realizing seamless scenes switching. Finally, a unified extended Kalman filter is developed to realize multi-source integration-based seamless localization using the positioning information provided by indoor and outdoor location sources and corresponding quality indicator results. Comprehensive experiments demonstrate that the presented CrowdLOC-S system is proven to realize precise and efficient indoor and outdoor positioning performance in complex and large-scale urban environments.

RNGC-VIWO: Robust Neural Gyroscope Calibration Aided Visual-Inertial-Wheel Odometry for Autonomous Vehicle

Accurate and robust localization using multi-modal sensors is crucial for autonomous driving applications. Although wheel encoder measurements can provide additional velocity information for visual-inertial odometry (VIO), the existing visual-inertial-wheel odometry (VIWO) still cannot avoid long-term drift caused by the low-precision attitude acquired by the gyroscope of a low-cost inertial measurement unit (IMU), especially in visually restricted scenes where the visual information cannot accurately correct for the IMU bias. In this work, leveraging the powerful data processing capability of deep learning, we propose a novel tightly coupled monocular visual-inertial-wheel odometry with neural gyroscope calibration (NGC) to obtain accurate, robust, and long-term localization for autonomous vehicles. First, to cure the drift of the gyroscope, we design a robust neural gyroscope calibration network for low-cost IMU gyroscope measurements (called NGC-Net). Following a carefully deduced mathematical calibration model, NGC-Net leverages the temporal convolutional network to extract different scale features from raw IMU measurements in the past and regress the gyroscope corrections to output the de-noised gyroscope. A series of experiments on public datasets show that our NGC-Net has better performance on gyroscope de-noising than learning methods and competes with state-of-the-art VIO methods. Moreover, based on the more accurate de-noised gyroscope, an effective strategy for combining the advantages of VIWO and NGC-Net outputs is proposed in a tightly coupled framework, which significantly improves the accuracy of the state-of-the-art VIO/VIWO methods. In long-term and large-scale urban environments, our RNGC-VIWO tracking system performs robustly, and experimental results demonstrate the superiority of our method in terms of robustness and accuracy.

Learning-Based UAV Coverage-Aware Path Planning in Large-scale Urban Environments

In our research, the coverage-aware path planning problem of unmanned aerial vehicles (UAVs) in large-scale urban environments is studied. The goal of our research is to train the intelligent UAV to autonomously cover the area with satisfactory communication quality and finally arrive at the objective place without colliding with numerous skyscrapers. Such a multi-objective path planning problem is regularly non-convex and thus hard to converge. To this end, a distributed deep reinforcement learning (DRL)-based approach called Distributed-RPPO is developed to address the problem. To be specific, firstly we formulate our proposed problem as a Markov decision process (MDP). Since communication connectivity is the core constraint, a proximal policy optimization (PPO)-based SIR prediction network is designed for guiding the UAV to cover the area with superior communication connectivity, using only the UAV’s current location. Then we combine the PPO algorithm with the Long short-term memory (LSTM) structure to solve the basic navigation problem while only the historical interactive data is exploited for updating the parameter vector of the entire network. Simulation results demonstrate that our approach is capable of allowing the UAV to execute coverage-aware path planning tasks in large-scale urban environments. Furthermore, the learning efficiency is greatly improved compared to existing DRL-based approaches.

Quantification through deep learning of sky view factor and greenery on urban streets during hot and cool seasons

The urban heat island effect has gained attention worldwide. Built environment characteristics such as sky view factor (SVF) and green view index (GVI) can affect urban thermal environments and pedestrians’ thermal comfort. With recent technological advances, Google Street View (GSV) can be used to rapidly obtain panoramic street-view images with high reliability, enabling convenient and low-cost environmental assessment of urban settings. In addition, deep learning technology for quantifying the characteristics of urban environments has advanced considerably. This study sought to (1) determine the consistency between deep learning and manual classification of urban environment characteristics and (2) investigate the effects of street-level SVF and GVI on thermal comfort, especially the differences in their effects during hot and cool seasons. The study was conducted in the West District of Taichung City, and GSV was used to capture images from which SVF and GVI were calculated. A total of 50 sample locations were selected for an onsite questionnaire and thermal comfort was measured to determine the effects of SVF and GVI. The results indicated deep learning and manual classifications of SVF and GVI to be highly correlated. With regard to effects, SVF had a significant positive effect on physiological equivalent temperature and thermal sensation votes. GVI also had a significant positive effect on physiological equivalent temperature, but no effect on thermal sensation votes. Thus, reducing SVF and implementing greening projects may improve thermal comfort of pedestrians on the streets. These results offer implications for future urban planning and large-scale urban thermal environment assessments.

A Lightweight Real-Time 3D LiDAR SLAM for Autonomous Vehicles in Large-Scale Urban Environment

For autonomous vehicles, real-time localization and mapping in the unknown environment is very important. In this paper, a fast and lightweight 3D LiDAR simultaneously localization and mapping (SLAM) is presented for the localization of autonomous vehicles in large-scale urban environments. A novel encoding approach based on depth information is proposed to encode unordered point clouds with various resolutions, which avoids missing dimensional information in the projection of point clouds onto a 2D plane. Principal components analysis (PCA) is modified by dynamically selecting neighborhood points according to the encoded depth information to fit the local plane with less time consuming. The threshold and the number of feature points are adaptive according to distance intervals, results in sparse feature points extracted and uniformly distributed in the three-dimensional space. The extracted significant feature points improve the accuracy of the odometer and speed up the alignment of the point cloud. The effectiveness and robustness of the proposed algorithm are verified on the KITTI odometry benchmark and MVSECD. A fast runtime of 21 ms is obtained for the odometer estimation. Compared to several typical state-of-the-art methods on the KITTI odometry benchmark, the proposed approach reduces translation errors by at least 19% and rotation errors by 7.1%.

End-to-end simulation environment for mobile edge computing

Performances analysis of resource management techniques and algorithms for edge computing is a crucial step that reveals the effectiveness of edge service placement and migration strategies in terms of delay and usage. To be able to gauge how different optimisations affect the end user quality of experience a holistic approach is needed, so that the end-to-end delay can be measured in a combined setup where the edge infrastructure is integrated in the 5G system architecture. For these purposes we put forward an open source workflow based on the integration of proven simulators as SUMO, OMNeT++ and CloudSim, that will provide the means to create large scale urban mobile simulation environments. This paper discusses the benefits and challenges of such an approach, and provides example results that showcase a few aspects of the potential end-to-end delay analysis by processing the gathered simulation output.

A news picture geo-localization pipeline based on deep learning and street view images

ABSTRACT Numerous news or event pictures are taken and shared on the internet every day that have abundant information worth being mined, but only a small fraction of them are geotagged. The visual content of the news image hints at clues of the geographical location because they are usually taken at the site of the incident, which provides a prerequisite for geo-localization. This paper proposes an automated pipeline based on deep learning for the geo-localization of news pictures in a large-scale urban environment using geotagged street view images as a reference dataset. The approach obtains location information by constructing an attention-based feature extraction network. Then, the image features are aggregated, and the candidate street view image results are retrieved by the selective matching kernel function. Finally, the coordinates of the news images are estimated by the kernel density prediction method. The pipeline is tested in the news pictures in Hong Kong. In the comparison experiments, the proposed pipeline shows stable performance and generalizability in the large-scale urban environment. In addition, the performance analysis of components in the pipeline shows the ability to recognize localization features of partial areas in pictures and the effectiveness of the proposed solution in news picture geo-localization.

A Prior Level Fusion Approach for the Semantic Segmentation of 3D Point Clouds Using Deep Learning

Three-dimensional digital models play a pivotal role in city planning, monitoring, and sustainable management of smart and Digital Twin Cities (DTCs). In this context, semantic segmentation of airborne 3D point clouds is crucial for modeling, simulating, and understanding large-scale urban environments. Previous research studies have demonstrated that the performance of 3D semantic segmentation can be improved by fusing 3D point clouds and other data sources. In this paper, a new prior-level fusion approach is proposed for semantic segmentation of large-scale urban areas using optical images and point clouds. The proposed approach uses image classification obtained by the Maximum Likelihood Classifier as the prior knowledge for 3D semantic segmentation. Afterwards, the raster values from classified images are assigned to Lidar point clouds at the data preparation step. Finally, an advanced Deep Learning model (RandLaNet) is adopted to perform the 3D semantic segmentation. The results show that the proposed approach provides good results in terms of both evaluation metrics and visual examination with a higher Intersection over Union (96%) on the created dataset, compared with (92%) for the non-fusion approach.

3D map reconstruction using a monocular camera for smart cities

Large-scale high-resolution three-dimensional (3D) maps play a vital role in the development of smart cities. In this work, a novel deep learning-based multi-view-stereo method is proposed for reconstructing the 3D maps in large-scale urban environments by exploiting a monocular camera. Compared with other existing works, the proposed method can perform 3D depth estimation more efficiently in terms of computational complexity and graphics processing unit memory usage. As a result, the proposed method can practically perform depth estimation for each pixel before generating 3D maps for even large-scale scenes. Extensive experiments on the well-known DTU dataset and real-life data collected on our campus confirm the good performance of the proposed method.

Efficient Pairwise 3-D Registration of Urban Scenes via Hybrid Structural Descriptors

Automatic registration of point clouds captured by terrestrial laser scanning (TLS) plays an important role in many fields including remote sensing (e.g., transportation management, 3-D reconstruction in large-scale urban areas and environment monitoring), computer vision, and virtual reality and robotics. However, noise, outliers, nonuniform point density, and small overlaps are inevitable when collecting multiple views of data, which poses great challenges to 3-D registration of point clouds. Since conventional registration methods aim to find point correspondences and estimate transformation parameters directly in the original point space, the traditional way to address these difficulties is to introduce many restrictions during the scanning process (e.g., more scanning and careful selection of scanning positions), thus making the data acquisition more difficult. In this article, we present a novel 3-D registration framework that performs in a “middle-level structural space” and is capable of robustly and efficiently reconstructing urban, semiurban, and indoor scenes, despite disturbances introduced in the scanning process. The new structural space is constructed by extracting multiple types of middle-level geometric primitives (planes, spheres, cylinders, and cones) from the 3-D point cloud. We design a robust method to find effective primitive combinations corresponding to the 6-D poses of the raw point clouds and then construct hybrid-structure-based descriptors. By matching descriptors and computing rotation and translation parameters, successful registration is achieved. Note that the whole process of our method is performed in the structural space, which has the advantages of capturing geometric structures (the relationship between primitives) and semantic features (primitive types and parameters) in larger fields. Experiments show that our method achieves state-of-the-art performance in several point cloud registration benchmark datasets at different scales and even obtains good registration results for data without overlapping areas.

Large-Scale LiDAR SLAM with Factor Graph Optimization on High-Level Geometric Features.

Although visual SLAM (simultaneous localization and mapping) methods obtain very accurate results using optimization of residual errors defined with respect to the matching features, the SLAM systems based on 3-D laser (LiDAR) data commonly employ variants of the iterative closest points algorithm and raw point clouds as the map representation. However, it is possible to extract from point clouds features that are more spatially extended and more meaningful than points: line segments and/or planar patches. In particular, such features provide a natural way to represent human-made environments, such as urban and mixed indoor/outdoor scenes. In this paper, we perform an analysis of the advantages of a LiDAR-based SLAM that employs high-level geometric features in large-scale urban environments. We present a new approach to the LiDAR SLAM that uses planar patches and line segments for map representation and employs factor graph optimization typical to state-of-the-art visual SLAM for the final map and trajectory optimization. The new map structure and matching of features make it possible to implement in our system an efficient loop closure method, which exploits learned descriptors for place recognition and factor graph for optimization. With these improvements, the overall software structure is based on the proven LOAM concept to ensure real-time operation. A series of experiments were performed to compare the proposed solution to the open-source LOAM, considering different approaches to loop closure computation. The results are compared using standard metrics of trajectory accuracy, focusing on the final quality of the estimated trajectory and the consistency of the environment map. With some well-discussed reservations, our results demonstrate the gains due to using the high-level features in the full-optimization approach in the large-scale LiDAR SLAM.

RSS-Based Localization and Mobility Evaluation Using a Single NB-IoT Cell.

Low Power Wide Area Networks (LPWAN) have the ability to localize a mobile transmitter using signals of opportunity, as a low power and low cost alternative to satellite-based solutions. In this paper, we evaluate the accuracy of three localization approaches based on the Received Signal Strength (RSS). More specifically, the performance of a proximity, range-based and optimized fingerprint-based algorithm is evaluated in a large-scale urban environment using a public Narrowband Internet of Things (NB-IoT) network. The results show a mean location estimation error of 340, 320 and 204 m, respectively. During the measurement campaign, we discovered a mobility issue in NB-IoT. In contrast to other LPWAN and cellular technologies which use multiple gateways or cells to locate a device, only a single cell antenna can be used for RSS-based localization in NB-IoT. Therefore, we address this limitation in the current NB-IoT hardware and software by studying the mobility of the cellular-based 3GPP standard in a localization context. Experimental results show that the lack of handover support leads to increased cell reselection time and poor cell sector reliability, which in turn results in reduced localization performance.

Visual Coverage Path Planning for Urban Environments

View planning for visual coverage is a fundamental robotics problem. Coverage for small objects (e.g. for inspection) or small scale indoor scenes have been studied extensively. However, view planning to cover a large scale urban environment remains challenging. Algorithms that can scale up to the size of such environments while providing performance guarantees are missing. In this letter, we model urban environments as a set of surfaces with k distinct surface normals whose viewing cones must be visited by a robot. We model the resulting coverage problem as a novel variant of Traveling Salesman Problem with Neighborhoods (TSPN). The neighborhoods are defined as cones, which constrain the path coverage quality. We present a polynomial time algorithm which admits an approximation factor of O(k/tan(α) max [L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">B</sub> , W <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">B</sub> , H <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">B</sub> ]), where α is the maximum viewing angle, and L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">B</sub> , H <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">B</sub> , W <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">B</sub> are respectively the length, width, and height of a minimum enclosing box of a city scene B. In addition to the analytical upper bounds, we show in simulations that our method outperforms three baseline methods in both trajectory length and run-time. We also demonstrate our method and evaluate the coverage quality of a city containing more than 70 buildings in a photo-realistic rendering software.

An efficient method of evaluating large scale urban residential skylight environment and an empirical study of Beijing main area

A good skylight environment in urban residential areas is an important component of a healthy city, and has always been highly valued. With the rapid development of new-type urbanization, the density of buildings continues to increase, and megacities have entered the stage of stock transformation. An effective method for evaluating the skylight environment of large-scale urban residential areas is urgently needed. However, there is still a lack of empirical research methods and cases of large-scale residential skylight environment. In this regard, this article takes the megacity Beijing as the research object, and proposes an efficient analysis method of residential skylight environment that integrates multiple real-world data at city scale. In terms of data, it collects and integrates 3D data of urban-scale building space and residential boundary data; in terms of algorithm, Sky View Factor (SVF) is used as the evaluation index of residential skylight environment, and an efficient analysis method of urban-scale skylight environment based on cloud parallel simulation is realized. Through analysis, it is found that: (1) the average SVF value of Beijing residential area is 61%, which means that its skylight quality is in general level; (2) the skylight environment of Beijing residential area is distributed in a circle, and there are 4 types of skylight environment quality residential areas; (3) The skylight environment of Beijing residential area is relatively weakly related to the distance from the residential area to the city center and the average height of the residential buildings, and is closely related to the plot volume ratio, the residential building density and the shading from surrounding buildings. The highlight of this study lies in the empirical research on the skylight environment of mega-city residential areas that incorporates multiple real data for the first time, which can promote the study of skylight environment on a city scale and provide a reference for the updating of Beijing’s residential daylight environment.

LONG-TERM VISUAL LOCALIZATION IN LARGE SCALE URBAN ENVIRONMENTS EXPLOITING STREET LEVEL IMAGERY

Abstract. In this paper, we present our approach for robust long-term visual localization in large scale urban environments exploiting street level imagery. Our approach consists of a 2D-image based localization using image retrieval (NetVLAD) to select reference images. This is followed by a 3D-structure based localization with a robust image matcher (DenseSfM) for accurate pose estimation. This visual localization approach is evaluated by means of the ‘Sun’ subset of the RobotCar seasons dataset, which is part of the Visual Localization benchmark. As the results on the RobotCar benchmark dataset are nearly on par with the top ranked approaches, we focused our investigations on reproducibility and performance with own data. For this purpose, we created a dataset with street-level imagery. In order to have independent reference and query images, we used a road-based and a tram-based mapping campaign with a time difference of four years. The approximately 90% successfully oriented images of both datasets are a good indicator for the robustness of our approach. With about 50% success rate, every second image could be localized with a position accuracy better than 0.25 m and a rotation accuracy better than 2°.

On the Opportunistic Topology of Taxi Networks in Urban Mobility Environment

Understanding and characterizing the connectivity of vehicular networks has become increasingly important because of their wide applications and fast development. To address the dynamical links in vehicular networks, time-varying graph (TVG) is one of the most important models. Nowadays, due to the fact that lots of vehicular applications can tolerate a small amount of latency in communication, opportunistic reachability graph (ORG) characterizes the connectivity better by introducing delay tolerance to the model. However, people still do not have a high-level summarization, i.e., the topology, of the vehicular network on how nodes are clustered and isolated. In this paper, based on ORG model, we analyze the opportunistic topology of taxi networks in urban mobility environment by mainly focusing on the number, location and evolution of connected components and the size of the largest components to reveal the unique properties of the taxi networks instead of just links and hops. Our analysis is based on the real taxi traces of big cities and reflects the real urban mobility environment. We find that the opportunistic topology of the networks with delay tolerance is substantially different from the instantaneous topology without considering the delay. Moreover, we unveil the fundamental relationships and trade-offs between the dynamical topology and the key network parameters related to mobility, e.g., delay tolerance, transmission distance, etc. To the best of our knowledge, our study is the first work to reveal the characteristics of opportunistic topology models in the large-scale urban mobility environment with real traces.

An Effective MEC Sustained Charging Data Transmission Algorithm in VANET-Based Smart Grids

Available charging information exchanges between mobile electric vehicles (EVs) and charging stations are significantly critical in spatio-temporal coordinated charging services introduced by smart girds. In this paper, we propose an efficient information transmission strategy for intelligent charging navigations of enormous moving EVs in large-scale urban environments. Specifically, we firstly design a heterogeneous VANET-based (vehicular ad hoc network) communication framework by means of mobile edge computing concept. In addition, based on the established multi-objective communication optimization problem, we propose an effective charging information dissemination algorithm between mobile edge computing servers and moving EVs. Moreover, in order to further increase charging information delivery efficiency and reduce redundant overheads, an improved local relaying scheme for charging information is designed on the basis of the formulated waiting time model. Finally, a series of simulation experiments are implemented to demonstrate the excellence and feasibility of our charging information transmission strategy.

Retrieval practice enhances near but not far transfer of spatial memory.

Students learn more effectively through repeated retrieval of study materials relative to repeated exposure to the materials, a phenomenon known as the testing effect or retrieval practice. This pattern has been demonstrated repeatedly with verbal materials, and more recently with visuospatial materials. The extent to which retrieval practice produces spatial memories that successfully transfer to more diverse task demands remains unknown. Transferring spatial memory to novel task demands can involve challenging orientation and perspective transformations, possibly limiting the benefits of retrieval practice for application to realistic spatial tasks. In 4 experiments, participants learned a map of a large-scale urban environment, engaging in either study practice (repeated exposure) or retrieval practice (exposure and testing). Across experiments we varied the retrieval demands of the final memory test, increasing the breadth of transfer from study to test (from near to far transfer). Final memory tests included reconstructing a map from memory (Experiment 1), judgments of relative direction from an allocentric perspective (Experiment 2), judgments of relative direction from an egocentric perspective (Experiment 3), and navigating between target landmarks within the learned environment (Experiment 4). Results demonstrated that retrieval practice enhances near to medium transfer of memory for the map itself, including accessing spatial memory from varied orientations. However, it does not assist in medium to far transfer of spatial knowledge to pointing or navigation tasks performed from an alternate perspective. Results are considered in the context of domain-specific theories of spatial memory and navigation, and domain-general theories of learning strategies and transfer. (PsycINFO Database Record (c) 2019 APA, all rights reserved).

A Study on the System Legitimacy and Normativity of Small-Scale Housing

저출산&#65381;고령화 영향과 구도심의 빈집 증가는 쓰레기 무단투기와 범죄발생 등 도시의 주거여건 악화를 야기하였으며, 장기적으로는 도시의 공동화와 인구소멸로 주거기능을 상실하게 될 우려가 있다. 구도심의 빈집 방치는 도시의 미관을 훼손하고 헌법상 쾌적한 주거환경을 조성하여야 할 국가의 책무를 소홀히 할 뿐만 아니라 토지의 효율적인 활용 면에서 국가적인 손실로 이어지고 있다. 그리고 기존의 &#65378;도시정비법&#65379;은 대규모 도시주거환경의 정비사업을 주요내용으로 하고 있어서 저소득층의 거주환경개선을 위한 제도적 지원이 미흡한 실정이다. 이러한 문제를 해결하기 위하여, 2017년 2월에 &#65378;소규모주택정비법&#65379;이 제정되어, 2018년 2월에 시행되었다. 소규모주택정비사업은 비용과 시간이 많이 소요되는 대규모 정비사업의 한계를 극복하고자 도입된 제도로서, 건축규제 완화, 사업 절차 간소화 등의 이점이 있다. 그러나, 소규모사업이다 보니, 높은 공사단가로 인한 사업추진비용 부담의 증가로 사업성이 낮을 뿐만 아니라, 최근 부동산 규제강화로 인하여 부동산시장이 냉각되면서, 사업 활성화의 동력이 떨어지고 있다. 이러한 현상을 개선하고, 소규모주택정비사업을 활성화시키고자, 관련 법제도를 분석하고, 개선방안을 제안하고자 한다. 첫째, 법체계정당성의 측면에서, &#65378;도시정비법&#65379;과 &#65378;소규모주택정비법&#65379;은 일반법과 특별법의 지위를 가지므로, &#65378;소규모주택정비법&#65379;에서 소규모주택정비사업상의 특성을 반영하여 제도를 개선할 것을 제안한다. 구체적인 예로는, 조합설립을 위한 임의기구로서의 추진위원회, 주민대표회의 또는 공공관리 강화 등을 고려해 볼 것을 제안하였다. 그리고 빈집의 정비&#65381;관리는 &#65378;소규모주택정비법&#65379;, &#65378;농어촌정비법&#65379; 그리고 &#65378;건축물관리법&#65379;이라는 3개의 법이 해체나 철거의 처분권한과 처분절차에 관하여 대동소이한 대집행절차를 직접 규정하고 있다. 그러므로 법규정의 간소화차원에서 &#65378;행정조사법&#65379;과 &#65378;행정대집행법&#65379;을 준용하여도 되는 부분은 준용하도록 하고, 해당 법률상의 절차에 특별한 것만을 규율하여, 법령의 내용을 간략히 할 것을 제안한다. 또한 ‘빈집’ 혹은 ‘빈 건축물’에 관한 구체적인 규정이 가장 잘 정비되어 있는 &#65378;소규모주택정비법&#65379;을 기본법으로 보고, 필요한 부분은 &#65378;소규모주택정비법&#65379;을 준용하도록 법체계를 정비하는 것도 한 방편이다. 둘째, 세제 개선의 측면에서 자율주택정비사업과 빈집상속 등에 있어서 양도소득세를 비과세 혹은 감면하거나 해야 할 부분들을 제시하였으며, &#65378;지방세법&#65379;상 빈집에 대한 재산세 과세합리화와 &#65378;지방세특례제한법&#65379;에 따른 취득세 감면대상 조정 및 조합원 분양분에 대한 부가가치세 면제 적용 등을 구체적으로 제안하였다. 마지막으로 기타 개선방안으로는 소규모정비사업과 관련된 부담금(광역교통시설부담금) 감면범위, 보조금 지급의 확대 등을 제안하였다.Low birth rates, aging populations, and the increase of vacant homes in old towns have worsened the urban living conditions, including fly tipping and crime. In the long run, there is a fear that the housing function will be lost due to the urban empiness and depopulation. Negligence of unoccupied houses in the old city neglects the duty of the nation to create a constitutional pleasant living environment, and it is also a national loss due to the inefficient use of land. The existing Urban Redevelopment Act is mainly focused on the maintenance of large-scale urban residential environments, and there is a lack of institutional support for improving the living environment for low-income families. In order to solve this problem, the Small-Scale House Improvement Act was enacted in February 2017 and was implemented in February 2018. The small-scale housing improvement project was introduced to overcome the limitations of costly and time-consuming large-scale maintenance projects. It has the advantages of easing building regulations and simplifying business procedures. However, since the cost of construction is high because it is a small project, the business value is low due to an increase in business promotion cost. In addition, as the real estate market has cooled due to the recent tightening of real estate regulations, the driving force of business activation is falling. In order to improve this phenomenon and to revitalize small-scale housing improvement projects, the relevant legal system will be analyzed and improvement plans will be proposed. First, in terms of the System Legitimacy, the Urban Improvement Act and the Small-Scale House Improvement Act have the status of general and special law. Therefore, this paper proposes to improve the system by reflecting the characteristics of the Small-Scale House Improvement project in the Small-Scale House Improvement Act. As a specific example, it is suggested to consider the promotors’ committee as an arbitrary organization for the establishment of a association, a residents representatives’ committee, strengthening public management system in improvement projects. And the improvement and management of unoccupied house has three Small-Scale House Improvement Act, the Agricultural and Fishing Villages Improvement Act, and the Building Management Act, which directly define similar the disposal rights and disposal procedures of vicarious execution. Therefore, in order to simplify the legislation, it is suggested that the Administrative Investigation Act and the Administrative Vicarious Execution Act be applied mutatis mutandis, and the contents of the legislation should be simplified by regulating only those specific to the legal procedures. In addition, the Small-Scale House Improvement Act, where the specific rules for unoccupied house or unoccupied building are best maintained, is considered the basic law. In some cases, the legal system is adapted to comply with the Small-Scale House Improvement Act. Second, in terms of taxation improvement, non-taxation, reduction, exemption and transfer of income tax is suggested in an autonomos housing improvement project and unoccupied housing inheritance. In addition, the taxation rationalization of property tax on unoccupied housing under the Local Tax Act, the reduction and exemption of acqusition tax under the Restriction of Special Local Taxation Act, and the application of VAT exemption on the units allocated to association members. Finally, other improvement measures were proposed, to increase the scope of reduction and exemption from charges for the Metropolitan Transportation Facilities, subsidies for the Small-Scale House Improvement project.