Yan Zhou

Dr. Yan Zhou

orcid

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 March 2018 in Remote Sensing
Verified
Journal Article
Open access
PDF file
FCFen Chen
Fen Chen
RRRuilong Ren
Ruilong Ren
TVTim Van de Voorde
Tim Van de Voorde
WXWenbo Xu
Wenbo Xu
Guiyun ZhouGuiyun Zhou
Guiyun Zhou
YZYan Zhou
Yan Zhou
Fast and automatic detection of airports from remote sensing images is useful for many military and civilian applications. In this paper, a fast automatic detection method is proposed to detect airports from remote sensing images based on convolutional neural networks using the Faster R-CNN algorithm. This method first applies a convolutional neural network to generate candidate airport regions. Based on the features extracted from these proposals, it then uses another convolutional neural network to perform airport detection. By taking the typical elongated linear geometric shape of airports into consideration, some specific improvements to the method are proposed. These approaches successfully improve the quality of positive samples and achieve a better accuracy in the final detection results. Experimental results on an airport dataset, Landsat 8 images, and a Gaofen-1 satellite scene demonstrate the effectiveness and efficiency of the proposed method.

Verified
Journal Article
Open access
PDF file
QXQing Xiong
Qing Xiong
QZQing Zhu
Qing Zhu
ZDZhiqiang Du
Zhiqiang Du
XZXinyan Zhu
Xinyan Zhu
YZYeting Zhang
Yeting Zhang
YZYan Zhou
Yan Zhou
Indoor emergency response plays a critically important role in disaster management for cities, which must consider the evacuation of people in a dynamic indoor environment. The spatial model is the foundation for the specific analysis of indoor emergency responses, such as evacuations. The current spatial model for evacuation has three primary pitfalls: (1) it primarily focuses on static spatial information, such as rooms, doors, and windows, and lacks dynamic information, such as events and sensors; (2) it mainly focuses on the horizontal space and the static scene and lacks a multi-story component that considers the different properties of stairs compared to planar areas; and (3) it places emphasis on the indoor navigation calculation with a 2D/3D network, which lacks individual properties that can support more complicated analysis, such as congestion and stagnation. In this paper, we propose a dynamic indoor field model with three typical characteristics. (1) It includes not only static information but also dynamic information, such as outdoor and indoor building geometry, sensors, fire spread, and personnel behavior. (2) It supports multi-story buildings from the macro level (building level and floor level) to the micro level (room level and individual level) based on horizontal and vertical indoor space. (3) It supports spatial calculations based on a three-dimensional space grid and can analyze potential congestion and stagnation during evacuation. We design a corresponding evacuation method that supports individual evacuation route finding and evacuation assessment. We perform a series of analyses of the applicability of the proposed model and the efficiency of the designed evacuation method based on multi-story evacuation studies. The simulation includes a total evacuation population exceeding 7000 individuals, and the analysis suggests that the new model and algorithm are effective in planning indoor emergency routes that avoid potential congestion or stagnation.

Verified
Journal Article
Open access
PDF file
CWChen Wu
Chen Wu
QZQing Zhu
Qing Zhu
YZYeting Zhang
Yeting Zhang
ZDZhiqiang Du
Zhiqiang Du
Xinyue YeXinyue Ye
Xinyue Ye
YZYan Zhou
Yan Zhou
With the widespread deployment of ground, air and space sensor sources (internet of things or IoT, social networks, sensor networks), the integrated applications of real-time geospatial data from ubiquitous sensors, especially in public security and smart city domains, are becoming challenging issues. The traditional geographic information system (GIS) mostly manages time-discretized geospatial data by means of the Structured Query Language (SQL) database management system (DBMS) and emphasizes query and retrieval of massive historical geospatial data on disk. This limits its capability for on-the-fly access of real-time geospatial data for online analysis in real time. This paper proposes a hybrid database organization and management approach with SQL relational databases (RDB) and not only SQL (NoSQL) databases (including the main memory database, MMDB, and distributed files system, DFS). This hybrid approach makes full use of the advantages of NoSQL and SQL DBMS for the real-time access of input data and structured on-the-fly analysis results which can meet the requirements of increased spatio-temporal big data linking analysis. The MMDB facilitates real-time access of the latest input data such as the sensor web and IoT, and supports the real-time query for online geospatial analysis. The RDB stores change information such as multi-modal features and abnormal events extracted from real-time input data. The DFS on disk manages the massive geospatial data, and the extensible storage architecture and distributed scheduling of a NoSQL database satisfy the performance requirements of incremental storage and multi-user concurrent access. A case study of geographic video (GeoVideo) surveillance of public security is presented to prove the feasibility of this hybrid organization and management approach.

Verified
Journal Article
Open access
PDF file
QZQing Zhu
Qing Zhu
YLYun Li
Yun Li
QXQing Xiong
Qing Xiong
Sisi ZlatanovaSisi Zlatanova
Sisi Zlatanova
DYDing Yulin
Ding Yulin
YZYan Zhou
Yan Zhou
The Open Geospatial Consortium (OGC) Geography Markup Language (GML) standard provides basic types and a framework for defining geo-informational data models such as CityGML and IndoorGML, which provide standard information models for 3D city modelling and lightweight indoor network navigation. Location information, which is the semantic engine that fuses big geo-information data, is however, discarded in these standards. The Chinese national standard of Indoor Multi-Dimensional Location GML (IndoorLocationGML) presented in this study can be used in ubiquitous indoor location intelligent applications for people and robots. IndoorLocationGML is intended as an indoor multi-dimensional location information model and exchange data format standard, mainly for indoor positioning and navigation. This paper introduces the standard’s main features: (1) terminology; (2) indoor location information model using a Unified Modeling Language (UML) class diagram; (3) indoor location information markup language based on GML; and (4) use cases. A typical application of the standard is then discussed. This standard is applicable to the expression, storage, and distribution of indoor multi-dimensional location information, and to the seamless integration of indoor–outdoor location information. The reference and basis are therefore relevant to publishers, managers, users, and developers of indoor navigation and location-based services (LBS).

Verified
Journal Article
Open access
PDF file
YZYan Zhou
Yan Zhou
PYPang Yuling
Pang Yuling
FCFen Chen
Fen Chen
YZYeting Zhang
Yeting Zhang
Traditional indoor navigation algorithms generally only consider the geometrical information of indoor space. However, the environmental information and semantic parameters of a fire are also important for evacuation routing in the case of a fire. It is difficult for traditional indoor navigation algorithms to dynamically find an indoor path when a fire develops. To address this problem, we developed a multi-semantic constrained three-dimensional (3D) indoor fire evacuation routing method that considers multi-dimensional indoor fire scene-related semantics, such as path accessibility, path recognition degree, and fire parameters. Our method enhances the navigation semantics of indoor space by extending the fire-related components of indoor model based on IndoorGML and integrating location semantics of IndoorLocationGML. We also propose quantifiable indoor fire-oriented routing semantics and establish a navigation cost function that evaluates semantic changes during a fire. We designed an indoor routing algorithm with multiple semantic constraints based on the A* algorithm. The indoor routing results were analyzed and compared in simulation experiments. The experimental results showed that the proposed model can remove unusable nodes and edges from the obtained navigation path and provides a safer and more effective evacuation route than traditional algorithms.

2 October 2014 in Geo-spatial Information Science
Verified
Journal Article
Open access
YZYan Zhou
Yan Zhou
WWWeisheng Wang
Weisheng Wang
DHDi He
Di He
ZWZhe Wang
Zhe Wang
Many cognitive studies have indicated that the path simplicity may be as important as its distance travelled. However, the optimality of paths for current navigation system is often judged purely on the distance travelled or time cost, and not the path simplicity. To balance these factors, this paper presented an algorithm to compute a path that not only possesses fewest turns but also is as short as possible by utilizing the breadth-first-search strategy. The proposed algorithm started searching from a starting point, and expanded layer by layer through searching zero-level reachable points until the endpoint is found, and then deleted unnecessary points in the reverse direction. The forward searching and backward cleaning strategies were presented to build a hierarchical graph of zero-level reachable points, and form a fewest-turn-path graph (G*). After that, a classic Dijkstra shortest path algorithm was executed on the G* to obtain a fewest-turn-and-shortest path. Comparing with the shortest path in Baidu map, the algorithm in this work has less than half of the turns but the nearly same length. The proposed fewest-turn-and-shortest path algorithm is proved to be more suitable for human beings according to human cognition research.