Objects In Indoor Spaces Research Articles

Indoor Scene Recognition Mechanism Based on Direction-Driven Convolutional Neural Networks.

Indoor location-based services constitute an important part of our daily lives, providing position and direction information about people or objects in indoor spaces. These systems can be useful in security and monitoring applications that target specific areas such as rooms. Vision-based scene recognition is the task of accurately identifying a room category from a given image. Despite years of research in this field, scene recognition remains an open problem due to the different and complex places in the real world. Indoor environments are relatively complicated because of layout variability, object and decoration complexity, and multiscale and viewpoint changes. In this paper, we propose a room-level indoor localization system based on deep learning and built-in smartphone sensors combining visual information with smartphone magnetic heading. The user can be room-level localized while simply capturing an image with a smartphone. The presented indoor scene recognition system is based on direction-driven convolutional neural networks (CNNs) and therefore contains multiple CNNs, each tailored for a particular range of indoor orientations. We present particular weighted fusion strategies that improve system performance by properly combining the outputs from different CNN models. To meet users' needs and overcome smartphone limitations, we propose a hybrid computing strategy based on mobile computation offloading compatible with the proposed system architecture. The implementation of the scene recognition system is split between the user's smartphone and a server, which aids in meeting the computational requirements of CNNs. Several experimental analysis were conducted, including to assess performance and provide a stability analysis. The results obtained on a real dataset show the relevance of the proposed approach for localization, as well as the interest in model partitioning in hybrid mobile computation offloading. Our extensive evaluation demonstrates an increase in accuracy compared to traditional CNN scene recognition, indicating the effectiveness and robustness of our approach.

The parahippocampal place area and hippocampus encode the spatial significance of landmark objects

Landmark objects are points of reference that can anchor one's internal cognitive map to the external world while navigating. They are especially useful in indoor environments where other cues such as spatial geometries are often similar across locations. We used functional magnetic resonance imaging (fMRI) and multivariate pattern analysis (MVPA) to understand how the spatial significance of landmark objects is represented in the human brain. Participants learned the spatial layout of a virtual building with arbitrary objects as unique landmarks in each room during a navigation task. They were scanned while viewing the objects before and after learning. MVPA revealed that the neural representation of landmark objects in the right parahippocampal place area (rPPA) and the hippocampus transformed systematically according to their locations. Specifically, objects in different rooms became more distinguishable than objects in the same room. These results demonstrate that rPPA and the hippocampus encode the spatial significance of landmark objects in indoor spaces.

Locating Objects in Warehouses Using BLE Beacons & Machine Learning

Warehouse management plays a pivotal role to boost the entire supply chain. To increase productivity, enterprises are focusing on different object localization approaches to achieve better accuracy amid high interferences. This helps to reduce the overall time for order taking & perform effective stock management. For this purpose, we propose a cost-effective system to achieve better accuracy for locating objects in indoor spaces with the help of BLE beacons. BLE is the term used for the Bluetooth wireless standard for low power consumption. BLE beacons are used as technology enablers because BLE supports all the major mobile smart devices and tablets. The measurement is performed using Received Signal Strength Indication (RSSI). Also, improved the location accuracy with the help of machine learning algorithms & utilizing neighborhood beacons for real-world use cases of warehouse management. The target object & neighborhood beacons provide the raw data to the system & the mobile device acts as a receiver. Our results show that the proposed work provides high accuracy for finding resources, taking orders & improving the overall stock process in warehouse management.

C-tree: efficient cell-based indexing of indoor mobile objects

With the increasing popularity of indoor positioning system technologies, many applications have become available that allow moving objects to be monitored and queried on the basis of their indoor locations. At the center of these applications is a data structure that is used for indexing the moving objects. For most of the current applications, the indexing is based on certain modifications of methods from the established research area of indexing objects moving in outdoor spaces. But the approach to indexing objects moving in indoor spaces should be more radically different. The nature of indoor spaces, which essentially consist of cells and connections between cells, and the concept of cell-based adjacency, as opposed to metric-based adjacency, require a significantly different focus and approach. In this paper, we present a cell-based index structure, which is called the C-tree (‘C’ for ‘cell’), for efficiently grouping and managing updates of moving objects in indoor spaces. The C-tree can efficiently serve indoor spatial queries, topological queries, adjacency queries and density-based queries. In addition, as shown in the paper, the density of indoor cells can play an important role in the performance of the index data structure. Taking cell density into account, we extend the application of the C-tree to construct what is called a density-based index tree, which substantially improves the performance of the index structure when the indoor space contains high density cells.

Spatial data managements in indoor environments

PurposeWith the rapid development of the indoor spaces positioning technologies such as the radio-frequency identification (RFID), Bluetooth and WI-FI, the locations of indoor spatial objects (static or moving) constitute an important foundation for a variety of applications. However, there are many challenges and limitations associated with the structuring and querying of spatial objects in indoor spaces. The purpose of this study is to address the current trends, limitations and future challenges associated with the structuring and querying of spatial objects in indoor spaces. Also it addresses the related features of indoor spaces such as indoor structures, positioning technologies and others.Design/methodology/approachIn this paper, the author focuses on understanding the aspects and challenges of spatial database managements in indoor spaces. The author explains the differences between indoor spaces and outdoor spaces. Also examines the issues pertaining to indoor spaces positioning and the impact of different shapes and structures within these spaces. In addition, the author considers the varieties of spatial queries that relate specifically to indoor spaces.FindingsMost of the research on data management in indoor spaces does not consider the issues and the challenges associated with indoor positioning such as the overlapping of Wi-Fi. The future trend of the indoor spaces includes included different shapes of indoors beside the current 2D indoor spaces on which the majority of the data structures and query processing for spatial objects have focused on. The diversities of the indoor environments features such as directed floors, multi-floors cases should be considered and studied. Furthermore, indoor environments include many special queries besides the common ones queries that used in outdoor spaces such as KNN, range and temporal queries. These special queries need to be considered in data management and querying of indoor environments.Originality/valueTo the best of the author’s knowledge, this paper successfully addresses the current trends, limitations and future challenges associated with the structuring and querying of spatial objects in indoor spaces.

UBIQUITOUS INDOOR GEOLOCATION: A CASE STUDY OF JEWELLERY MANAGEMENT SYSTEM

Abstract. Addressing and geolocation for indoor environments are important fields of research in the recent years. The problem of finding location of objects in indoor spaces is proposed to solve in two ways. The first, is to assign coordinates to objects and second is to divide space into cells and detect the presence or absence of objects in each cell to track them. In this paper the second approach is discussed by using Radio Frequency Identification technology to identify and track high value objects in jewellery retail industry. In Ubiquitous Sensor Networks, the reactivity or proactivity of the environment are important issues. Reactive environments wait for a request to response to it. Instead, in proactive spaces, the environment acts in advance to deal with an expected action. In this research, a geo-sensor network containing RFID readers, tags, and antennas which continuously exchange radio frequency signal streams is proposed to manage and monitor jewellery galleries ubiquitously. The system is also equipped with a GIS representation which provides a more user-friendly system to manage a jewellery gallery.

A Semantic-Based Indexing for Indoor Moving Objects

The increasing availability of indoor positioning, driven by techniques like RFID, Bluetooth, and smart phones, enables a variety of indoor location-based services (LBSs). Efficient queries based on semantic-constraint in indoor spaces play an important role in supporting and boosting LBSs. However, the existing indoor index techniques cannot support these semantic constraints-based queries. To solve this problem, this paper addresses the challenge of indexing moving objects in indoor spaces, in which both the moving objects and the indoor environments include semantic meanings. We present an indoor semantic-based model, which gives the formal description of semantics of indoor cells and moving objects. Then, a new semantic-based index is proposed for indoor environment, which can support queries under semantic constraint. In addition, we develop efficient algorithms for two new queries, which are the nearest neighbor query based on semantic constraints for static indoor cells and moving objects, respectively. The conducted experiment demonstrates that the proposed index structure is effective, robust, and efficient.

Spatiotemporal indexing for moving objects in an indoor cellular space

To facilitate a variety of indoor applications, positioning technologies have been developed in indoor spaces (such as WI-FI and RFID). Thus, the requirement for the tracking and monitoring of moving objects in indoor spaces has increased considerably. The indexing of moving objects in indoor spaces is of essential importance, as these are different from outdoor spaces in many respects, such as the measurements and the positioning technologies. Therefore, in this paper, we propose a new adjacency-index structure for objects moving in indoor space which includes both spatial and temporal properties. The spatial index is based on the connectivity (adjacency) between the indoor environment cells. Moreover, we propose two temporal indexes with different methods to store the temporal data, which can support and enable efficient query processing and efficient updates for objects moving in indoor space. The proposed indexes can efficiently serve different types of spatial queries, such as KNN and indoor range, and a variety of temporal queries which are essential in an indoor environment. An empirical performance study suggests that the proposed data structures are effective, efficient, and robust.