Multi-target indoor localization and tracking on video monitoring system in a wireless sensor network

doi:10.1016/j.jnca.2012.08.013

Journal of Network and Computer Applications

Volume 36, Issue 1, January 2013, Pages 228-234

https://doi.org/10.1016/j.jnca.2012.08.013 Get rights and content

Abstract

The development of wireless sensor networks (WSNs) has greatly encouraged the use of sensors for multi-target tracking. The high efficiency detection and location monitoring are critical requirements for multi-target tracking in a WSN. In this paper, we present an indoor tracking model using IEEE 802.15.4 compliant radio frequency and video monitoring system to monitor targets in a special way. Our motivation is to manipulate the erratic or unstable received signal strength indicator (RSSI) signals to deliver the stable and precise position information in the indoor environment. We propose a localization algorithm based on statistical uncorrelated vectors and develop a smoothing algorithm to minimize the noise in RSSI values. We also present a solution combining the WSN with the Ethernet technology to decrease the RSSI interference by buildings. The developed system can realize the functions of multi-target detection and tracking, and specific target inquiries, alarms and monitoring. The system architecture, hardware and software organization, as well as the solutions for multiple targets tracking, RSSI interference and localization accuracy have been introduced in details.

Graphical Abstract

Highlights

► We present an indoor tracking model to monitor targets. ► We propose localization algorithm based on statistical uncorrelated vectors. ► A smoothing algorithm is developed for minimizing noise in RSSI. ► We present a solution to decrease the RSSI interference by buildings.

Introduction

The popularity of wireless communication technologies and embedded micro-sensing technologies has greatly promoted the development of wireless sensor networks (WSNs). The basic function of a WSN (Patwari et al., 2005, Hyo-Sung and Wonpil, 2009, Dai et al., 2011) is to connect a series of spatially distributed sensor nodes through the self-organizing wireless network, transfer the collected data, and carry out the appropriate data analysis and processing. So, WSNs can be used to perform the collaborative monitoring and controlling of the physical or environmental situations in a large space.

There are two major advantages of WSNs: the ease of configuration and the flexibility of deployment. WSNs have been widely used in various fields such as transportation (Khanafer et al., 2010), manufacturing (Delen et al., 2011), health care (Huanjiaet al., 2011), environmental protection (Mittal and Bhatia, 2010), and military applications (Lowell, 2011). Many researchers have studied WSNs, including design issues related to the physical and media access layers, routing and transporting protocols (Freris et al., 2010, Baronti et al., 2007).

Localization of objects and tracking of moving objects are essential to many location-based services (Ni et al., 2011; Hao et al., 2009). Tracking objects is basically consisted of detecting and monitoring the location of real-world objects, where different technologies such as WiFi, radio frequency identification (RFID), ultrasound, infrared, and video tracking, may be used. Active Bat (Andy and Alan, 1997) and Cricket (Priyantha et al., 2000) are well-known in-building mobile locating and tracking approaches that estimate the position of a target from the time difference between sent and received ultrasonic signals and offer high tracking precision. Active Badge (Want et al., 1992) employs the infrared technology for locating people in an office environment. However, these technologies often require collateral mechanism and some parts are expensive and highly susceptible to damage.

As an inexpensive localization solution, the received signal strength indicator (RSSI) model predicts positions using radio frequency (RF) signals. Researchers have attempted to adapt the existing system to the estimation of location in numerous ways. LANDMARC (Ni et al., 2003) is one of the most popular RF-based localization technologies using active RFID tags. It adopts the coordinates of the K nearest reference tags to compute the coordinates of the tracking tag. However, since the RSSI is easily influenced by environment, the chosen K nearest reference tags may not be close to the target. Therefore, if this method is applied in a large field, the tracking accuracy drops dramatically. One prominent solution is the WiFi-based positioning system (Lassabe et al., 2006), which utilizes the existing wireless local area network to predict locations. However, the WiFi-based positioning system is usually not reliable in spaces containing obstacles. Transceiver-free technologies (Zhang et al., 2007) can be used to detect the object's trajectory pattern without requiring the target to carry any device. It is based on a simple observation that wireless signals are quite stable in a static environment. When links are disturbed (for example, signal strength changes dramatically), it is very likely there are moving objects nearby. Although the dynamics of RSSI is robust to the environmental change, the densely deployed sensors cause heavy communication overhead and may introduce more interference. As a result, its localization accuracy is also limited. Cocktail (Zhang et al., 2010) is a hybrid RFID/WSN implementation. Sensors use the dynamic performance of RSSI to choose a cluster of reference tags as candidates. The final target location is estimated according to the RSSI relationship between the target tag and candidate reference tags. WSNs provide a new opportunity for objects localization and tracking. Boon-Giin and Wan-Yong (2011) have introduced an indoor tracking model using IEEE 802.15.4 compliant radio frequency and immersive 3-D graphics to present data. They proposed an accuracy refinement algorithm to filter out noise in radio-frequency transmission between sensors, and the locations of targets can be displayed on a mobile device like PDA.

Considering a WSN of a set of wireless sensor nodes deployed in a closed field, a sensor node can detect the movement of an object and report the received signal strength information when the object enters or remains in the sensing area of this node. Since WSN is a self-organizing network, we can use the mutual information connection between nodes to achieve the functions of detection, localization and tracking. In this work, detection, localization and tracking of targets are realized based on WSNs, and the real-time indoor monitoring is achieved by integrating WSNs and video monitoring systems. When the wireless signals are seriously weakened by the building walls, it becomes difficult to locate and track a target continuously in different rooms and different floors. We combine the WSN with the Ethernet technology, and design routing methods to solve this problem. Since the layout of rooms and corridors can be quite different, we propose different location algorithms for different scenarios. In addition, since the wireless signal is usually disturbed by various noises in the indoor environment, we develop a smoothing algorithm to minimize the noise in the RSSI and locate the target by our localization algorithm based on statistical uncorrelated vectors.

Section snippets

System architecture

The purposes of this research are to build a RSSI-based real-time in-building detecting and tracking system, to construct the network topology to address the serious interference on the RSSI by different floors and walls, to propose a new localization algorithm and a smoothing method to reduce the influence of the ranging error on the positioning accuracy, and to combine with video monitoring systems to monitor targets intelligently.

After comparing different available chips, we select

Indoor location

The commercial CC2431 module has a basic built-in algorithm for calculating location by the trilateration method. This localization algorithm is inadequate since it is based on RSSI values containing noises from the environment, and it does not provide reliable output for use in a real-time situation. Although the CC2431 module only uses relatively strong signals received from reference nodes, the signals are appropriate for computation. The real-time location prediction should be robust and

Experimental results

The objective of the experiments is to detect the number of targets in the networks and further observe the precise locations of multiple targets based on RSSI values. Experiments were conducted in an office building. Various indoor conditions that may bring interference to RSSI values during transmission were carefully taken into consideration, for example, the human activity in particular spaces, different objects such as chairs, desktop computers and tables (typically around 70% of spaces

Conclusions

We propose a novel localization algorithm based on statistical uncorrelated vectors to increase the precision of real-time multi-target tracking in the indoor environment. We apply the RSSI smoothing method to removes noise and abrupt changes in the received RSSI values before they are used for distance computation. We design the nearest neighbor algorithm for locating and tracking targets in the corridor. By combining the WSN with the Ethernet technology, and designing routing methods to solve

Acknowledgments

This work is supported by the Fundamental Research Funds for the Central Universities (JUSRP20914, JUDCF10031), the 111 Project (B12018) and PAPD of Jiangsu Higher Education Institutions.

References (20)

P. Baronti et al.
Wireless sensor networks: a survey on the state of the art and the 802.15.4 and ZigBee standards
Computer Communications
(2007)
W. Andy et al.
A new location technique for the active office
IEEE Personal Communications
(1997)
Lee Boon-Giin et al.
Multitarget three-dimensional indoor navigation on a PDA in a wireless sensor network
IEEE Sensors Journal
(2011)
H. Dai et al.
Localisation algorithm for large-scale and low-density wireless sensor networks
IET Electronics Letters
(2011)
D. Delen et al.
The promise of RFID-based sensors in the perishables supply chain
IEEE Wireless Communications
(2011)
N.M. Freris et al.
Fundamentals of large sensor networks: connectivity, capacity, clocks, and computation
Proceedings of the IEEE
(2010)
Q. Hao et al.
Multiple human tracking and identification with wireless distributed pyroelectric sensor systems
IEEE Systems Journal
(2009)
Yang Huanjia et al.
Hybrid Zigbee RFID sensor network for humanitarian logistics centre management
Journal of Network and Computer Applications
(2011)
Ahn Hyo-Sung et al.
Environmental-adaptive RSSI-based indoor localization
IEEE Transactions on Automation Science and Engineering
(2009)
M. Khanafer et al.
Intrusion detection system for WSN-based intelligent transportation systems
IEEE GLOBECOM
(2010)

There are more references available in the full text version of this article.

Cited by (21)

An overview on low energy wake-up radio technology: Active and passive circuits associated with MAC and routing protocols
2021, Journal of Network and Computer Applications
Citation Excerpt :
Environmental monitoring applications are mainly based on WSN which are worthy to perform the ability of a passive WuR method. It is a collaboration of many sensor nodes distributed all over a city (smart city Skouby and Lynggaard, 2014; Paradells et al., 2014) or it could be integrated into many other applications such as smart gate (Gamm et al., 2013), smart building (Benzaama et al., 2020; Grindvoll et al., 2012; Jacquemod et al., 2014; Queiroz et al., 2017), security systems (Jelicic et al., 2014; Magno et al., 2013), indoor localization (Simon et al., 2015; Zhang et al., 2011; Dai et al., 2013), WSN for urban area (Rashid and Rehmani, 2016), smart wildlife monitoring (Picco et al., 2015; Dressler et al., 2016b), green IoT (Deng et al., 2019), industrial internet of things (IIoT) (Lara et al., 2020), unmanned aerial vehicles/system (UAV/UAS) (Chen et al., 2019) (Toth and Jóźków, 2016) and many others. Another new sensor technology is the smart grid that includes communication, observation, control, and testing potentialities to the electricity grid in order to enhance the electricity reservoir chain.
The Internet of Things (IoT) is currently used in many wireless sensor network (WSN) applications. Conventionally, the WSN’s energy consumption is considered as one of the prime concerns. The energy consumption is mostly due to the sensing, data processing, communications and other wasted energies such as idle listening, collisions and overhearing. These sensor nodes are regularly powered by an external power source and consequently have a shorter lifetime. Fortunately, different approaches for wireless energy harvesting (WEH) have been improved. Thus, wake-up radio (WuR) becomes a remedy for WEH which provides active, passive and semi-passive circuits consumption and other protocols. For instance, the most used, convincing and productive go to passive WuR which can significantly increase the network lifetime in a sensor network (SN) by decreasing unnecessary idle listening. Eventually, this paper proposes a state of the art in active, semi-passive, centering more on passive WuR and covers the applications areas. Then, an overview of WuR related to physical, medium access control (MAC) and routing layers. Lastly, the paper accentuates the potential research opportunities for wake-up technology for future IoT applications.
Object tracking sensor networks in smart cities: Taxonomy, architecture, applications, research challenges and future directions
2020, Future Generation Computer Systems
The development of pervasive communication devices and the emergence of the Internet of Things (IoT) have acted as an essential part in the feasibility of smart city initiatives. Wireless sensor network (WSN) as a key enabling technology in IoT offers the potential for cities to get smarter. WSNs gained tremendous attention during the recent years because of their rising number of applications that enables remote monitoring and tracking in smart cities. One of the most exciting applications of WSNs in smart cities is detection, monitoring, and tracking which is referred to as object tracking sensor networks (OTSN). The adaptation of OTSN into urban cities brought new exciting challenges for reaching the goal of future smart cities. Such challenges focus primarily on problems related to active monitoring and tracking in smart cities. In this paper, we present the essential characteristics of OTSN, monitoring and tracking application used with the content of smart city. Moreover, we discussed the taxonomy of OTSN along with analysis and comparison. Furthermore, research challenges are investigated concerning energy reservation, object detection, object speed, accuracy in tracking, sensor node collaboration, data aggregation and object recovery position estimation. This review can serve as a benchmark for researchers for future development of smart cities in the context of OTSN. Lastly, we provide future research direction.
Device-free human localization and tracking with UHF passive RFID tags: A data-driven approach
2018, Journal of Network and Computer Applications
Localizing and tracking human movement in a device-free and passive manner is promising in two aspects: i) it neither requires users to wear any sensors or devices, ii) nor it needs them to consciously cooperate during the localization. Such indoor localization technique underpins many real-world applications such as shopping navigation, intruder detection, surveillance care of seniors etc. However, current passive localization techniques either need expensive/sophisticated hardware such as ultra-wideband radar or infrared sensors, or have an issue of invasion of privacy such as camera-based techniques, or need regular maintenance such as the replacement of batteries. In this paper, we build a novel data-driven localization and tracking system upon a set of commercial ultra-high frequency passive radio-frequency identification tags in an indoor environment. Specifically, we formulate human localization problem as finding a location with the maximum posterior probability given the observed received signal strength indicator from passive radio-frequency identification tags. In this regard, we design a series of localization schemes to capture the posterior probability by taking the advance of supervised-learning models including Gaussian Mixture Model, $k$ Nearest Neighbor and Kernel-based Learning. For tracking a moving target, we mathematically model the task as searching a location sequence with the most likelihood, in which we first augment the probabilistic estimation learned in localization to construct the Emission Matrix and propose two human mobility models to approximate the Transmission Matrix in the Hidden Markov Model. The proposed tracking model is able to transfer the pattern learned in localization into tracking but also reduce the location-state candidates at each transmission iteration, which increases both the computation efficiency and tracking accuracy. The extensive experiments in two real-world scenarios reveal that our approach can achieve up to 94% localization accuracy and an average 0.64 m tracking error, outperforming other state-of-the-art radio-frequency identification based indoor localization systems.
Positioning technology of mobile vehicle using self-repairing heterogeneous sensor networks
2017, Journal of Network and Computer Applications
Citation Excerpt :
Due to the cumulative position errors of SINS approach, other positioning technologies are considered to be integrated with pure SINS, which can provide stable position results (Hoeflinger et al., 2013). Wireless sensor network (WSN) has attracted much attention in the industrial applications (Dai et al., 2013; Guo et al., 2014). WSN has the ability to sense, process, and communicate, and can collaboratively form a self-organizing network map (Xie and Wang, 2014; Milioris et al., 2014).
Mobile vehicle positioning can provide the reference to navigation, tracking and multi vehicles collaboration. Applying spatiotemporal distribution characteristics of positioning errors between strap-down inertial navigation system (SINS) and wireless sensor network (WSN) approaches, a mobile vehicle positioning is proposed as a component of heterogeneous sensor networks (HSN). The attitude, velocity and position equations of mobile vehicle are derived based on the kinematics parameter constraints and inertial parameter errors. Meanwhile, WSN approach can provide position estimation using inaccurate anchor nodes. However, SINS is known for its cumulative errors over long time, while WSN approach can have large positioning errors in certain areas. As an effort to overcome the limitations of pure SINS or WSN approach, an integrated SINS and WSN approach is proposed to form a self-repairing HSN approach, which can provide sound position and attitude for mobile vehicle. Then, multi-parameter interaction and cooperative correction strategy are explored when SINS or WSN measurement is abnormal. Finally, a comprehensive set of experiments of position and attitude estimations for mobile vehicle are performed on the actual environment platform.
On analyzing user location discovery methods in smart homes: A taxonomy and survey
2016, Journal of Network and Computer Applications
Citation Excerpt :
To improve the localization accuracy, they developed a scalable platform where they can add any other modality to help in making better decisions; for instance, additional modalities based on vision and on using accelerometers. A combination of different technologies is presented in Dai et al. (2013), where an indoor tracking model using the IEEE 802.15.4 compliant radio frequency is set up to work with a video monitoring system for target monitoring. The concept is that the erratic or unstable RSSI signals can be manipulated to deliver stable and precise position information in the indoor environment.
User Location Discovery (ULD) is a key issue in smart home ecosystems, as it plays a critical role in many applications. If a smart home management system cannot detect the actual location of the users, the desired applications may not be able to work successfully. This article proposes a new taxonomy with a broad coverage of ULD methods in terms of user satisfaction and technical features. In addition, we provide a state-of-the-art survey of ULD methods and apply our taxonomy to map these methods. Mapping contributes to gap analysis for existing ULDs and also validates the applicability and accuracy of the taxonomy. Using this systematic approach, the features and characteristics of the current ULD methods are identified (i.e., equipment and algorithms). Next, the weaknesses and advantages of these methods are analyzed utilizing ten important evaluation metrics. Although we mainly focus on smart homes, the results of this article can be generalized to other spaces such as smart offices and eHealth environments.
OASys: An opportunistic and agile system to detect free on-street parking using intelligent boards embedded in surveillance cameras
2014, Journal of Network and Computer Applications
Citation Excerpt :
The cluster head will be responsible to build the parking space map using the data sent from the other vehicles. A direct derivative problem is tracking of vehicles or people (Rios-Cabrera et al., 2012; Mandellos et al., 2011; Dai et al., 2013; Lee et al., 2012). This idea could be use to increase the security in the parking space.
This work proposes an embedded system that opportunistically detects free on-street parking by using surveillance cameras. Intelligent boards are embedded in the cameras allowing a distributed processing and communication. The task of looking for free parking spaces demands a significant amount of drivers׳ time. This problem generally takes place in urban areas where there is a large number of vehicles and few available parking spaces (on-street or off-street). Decreasing the time spent in this task could reduce the traffic jam or, in an extreme perspective, alleviate the toxic gases emission or the fossil combustible consumption. Initially, it was evaluated three classical techniques for image processing applied to detect free on-street parking. The best one presents a success detection rate close to 100%. After that, it was evaluated the performance of the embedded system by using only the best image processing technique. This performance evaluation considers three different scenarios: centralized, hybrid, and embedded. The last one is the main proposal and contribution. The results reveal that embedded proposal had an average requisition time of 2.10 s vs. 0.38 s of centralized one. The hybrid one presents the worst results.

View all citing articles on Scopus

View full text

Multi-target indoor localization and tracking on video monitoring system in a wireless sensor network

Abstract

Graphical Abstract

Highlights

Introduction

Section snippets

System architecture

Indoor location

Experimental results

Conclusions

Acknowledgments

Computer Communications

A new location technique for the active office

IEEE Personal Communications

Multitarget three-dimensional indoor navigation on a PDA in a wireless sensor network

IEEE Sensors Journal

Localisation algorithm for large-scale and low-density wireless sensor networks

IET Electronics Letters

The promise of RFID-based sensors in the perishables supply chain

IEEE Wireless Communications

Fundamentals of large sensor networks: connectivity, capacity, clocks, and computation

Proceedings of the IEEE

Multiple human tracking and identification with wireless distributed pyroelectric sensor systems

IEEE Systems Journal

Hybrid Zigbee RFID sensor network for humanitarian logistics centre management

Journal of Network and Computer Applications

Environmental-adaptive RSSI-based indoor localization

IEEE Transactions on Automation Science and Engineering

Intrusion detection system for WSN-based intelligent transportation systems

IEEE GLOBECOM