DSN686978 1 11

DSN686978 1 11 Research Article International Journal of Distributed Sensor Networks 2017, Vol 13(1) � The Author(s) 2017 DOI 10 1177/1550147716686978 journals sagepub com/home/ijdsn Deep combining of[.]

International Journal of Distributed Sensor Networks

2017, Vol 13(1)

Ó The Author(s) 2017 DOI: 10.1177/1550147716686978 journals.sagepub.com/home/ijdsn

Deep combining of local phase

quantization and histogram of oriented

gradients for indoor positioning based

on smartphone camera

Jichao Jiao and Zhongliang Deng

Abstract

To achieve high accuracy in indoor positioning using a smartphone, there are two limitations: (1) limited computational and memory resources of the smartphone and (2) the human walking in large buildings To address these issues, we pro-pose a new feature descriptor by deeply combining histogram of oriented gradients and local phase quantization This fea-ture is a local phase quantization of a salient histogram of oriented gradient visualizing image, which is robust in indoor scenarios Moreover, we introduce a base station–based indoor positioning system for assisting to reduce the image matching at runtime The experimental results show that accurate and efficient indoor location positioning is achieved

Keywords

Indoor positioning, smartphone, salient region detection, deep combining of histogram of oriented gradients and local phase quantization, histogram of oriented gradient visualization

Date received: 27 June 2016; accepted: 24 November 2016

Academic Editor: Gang Wang

Introduction

Indoor positioning is considered an enabler for a variety

of applications, such as guidance of passengers on

air-ports, conference attendees, visitors in shopping malls,

and for many novel context-aware services, which can

play a significant role for monetarization The demand

for an indoor positioning service or indoor

location-based services (iLBS) has also accelerated given that

people spend the majority of their time indoors.1 Over

the last decade, researchers have studied many indoor

positioning techniques.2 In addition, with the

develop-ment of the integrated circuit technology, multi-sensors,

for example, camera, Earths magnetic field, WiFi,

Bluetooth, inertial module, have been integrated in

smartphones Therefore, smartphones are becoming

powerful platforms for location awareness

The traditionally used outdoor localization method,

Global Navigation Satellite System (GNSS), is not

available in indoor environments, even though naviga-tion tasks on street level are very precise A catalog of alternative localization techniques has been investi-gated, such as infrared-,3 sensor-,3,4 wireless-,5,6 com-munication basestation–based technologies,7 pseudolite8or visual markers.9However, most of these technologies, relying on wireless technology, face issues

in the presence of radio frequency interference (RFI) and interference of non-line of sight (NLOS) caused by dense forests, urban canyons, and terrain.1Moreover, some of these technologies work in a limited area such

School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China

Corresponding author:

Jichao Jiao, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Xitu Road, Haidian, Beijing 100876, China Email: jiaojichao@gmail.com

Creative Commons CC-BY: This article is distributed under the terms of the Creative Commons Attribution 3.0 License

(http://www.creativecommons.org/licenses/by/3.0/) which permits any use, reproduction and distribution of the work without further permission provided the original work is attributed as specified on the SAGE and Open Access pages (http://www.uk.sagepub.com/aboutus/ openaccess.htm).

as inertial sensor–based approaches or some need a

particular environmental infrastructure and

augmenta-tion such as Locata, that is, a pseudolite posiaugmenta-tioning

system.8 Therefore, smartphone camera–based indoor

positioning is a promising approach for accurate

indoor positioning without the need for expensive

infrastructure such as access points or beacons

The key method of camera-based localization is

image matching Images taken by a smartphone camera

are matched to previously acquired reference images

with known position and orientation The matching of

smartphone recordings with a database of

geo-referenced images allows for meter accurate

infrastructure-free localization.10 According to the

matched reference image, the location of the

smart-phone is calculated In mobile indoor scenarios that are

shown by Figure 2, users usually walk during

position-ing and navigation procedure Therefore, the captured

images by smartphone cameras are scaled, rotated, and

even blurred because of hands shaking Moreover,

most of the researchers recently focus on invariant

fea-ture extraction Ravi et al.11 extracted color

histo-grams, wavelet decomposition, and image shape for

image matching to locate a user’s position Kim and

Jun12 proposed a method based on image color

histo-gram feature for positioning using augmented reality

tool However, the positioning accuracy of those two

methods would work inefficiently in the varying light

and crowded scenarios In order to extract the

invar-iant features, SIFT and its improved algorithms are

widely used for image-based indoor localization

Kawaji et al used principal component analysis-scale

invariant feature transform (PCA-SIFT) feature for

railway museum indoor positioning Werner et al.13

proposed a camera-based indoor positioning using

speeded up robust features (SURF) feature for

speed-ing up the image matchspeed-ing Li and Wang14 introduced

affine-scale invariant feature transform (A-SIFT)

fea-ture for image matching achieved by random sample

consensus (RANSAC), which increased the matching

accuracy Heikkila¨ et al.15proposed a similar method14

for indoor positioning

However, those two complex computational

meth-ods are not suitable for smartphone-based indoor

posi-tioning This is because the limited computational

resources of mobile devices16extracted the edge-based

features from the visual tag image, and those features

are fused with inertial information for indoor

naviga-tion Kim and Jun12 used the Sobel filter integrating

mean structural similarity index for estimating the

arri-val of angle and height during the indoor localization

However, these two methods need additional visual

marks for assisting smartphone camera for detecting

features, which increases the indoor positioning cost

Meanwhile, all of these research works mainly focus on

improving image-matching accuracy Some of these

algorithms are, however, quite demanding in terms of their computational complexity and therefore not sui-ted to run on mobile devices, which need smartphones with high hardware configuration Although smart-phones are inexpensive, they have even more limited performance than Tablet and PCs Phones are embedded systems with severe limitations in both the computational facilities and memory bandwidth Therefore, natural feature extraction and matching on phones have largely been considered prohibitive and have not been successfully demonstrated to date.17To address these issues, Van Opdenbosch et al.10 used the improved vector of locally aggregated descriptors’ (VLAD) image signature and emerging binary feature descriptor binary robust independent elementary fea-tures (BRIEF) to achieve the smartphone camera-based indoor positioning Besides, in order to reduce the overall computational complexity, they proposed a scalable streaming approach for loading the reference images to the phones Different with their method, this article proposed an efficient feature descriptor named Turbo Fusing Histogram of oriented gradients (HOG) and Local phase quantization (LPQ) Salient feature (TFHLS) The TFHLS features are extracted from the partial image which are salient image regions, and they are invariant to the illumination, scale, rotation, and blur caused by camera shaking Moreover, a wireless-based indoor positioning system time&code division-orthogonal frequency division multiplexing (TC-OFDM) is introduced to calculate the coarse positions for supporting the floor number to the smartphone, which would reduce the number of images which are downloaded to the smartphones Using this approach, our camera-based indoor positioning algorithm results

in the reduction in computational complexity, hard-ware requirement, and network latency

This article is organized as follows to achieve our investigations First of all, we discuss the related work on HOG and LPQ feature extraction in section ‘‘Related work.’’ Then, we introduce our image feature extraction based on fusing HOG and LPQ in section ‘‘Proposed smartphone camera-based indoor positioning.’’ After that, we test the proposed algorithm on the Technische Universita¨t Mu¨nchen (TUM) indoor dataset18 and the Beijing University of Posts and Telecommunications (BUPT) indoor dataset collected by our lab, and the evo-lution of our algorithm is also shown in this section Finally, in Section ‘‘Conclusion,’’ we conclude the article and provide a future work on possible extensions

Related work Finding efficient and discriminative descriptors is cru-cial for indoor complex scenarios HOG descriptor was proposed by Dalal and Triggs19 for human detection

The main idea behind HOG is based on the local edge

information.15 Because of its efficient performance,

HOG feature are widely used in human detection,20,21

face recognition,22,23and image searching.24All of these

applications show that HOG feature is invariant to the

illumination According to our experiment, HOG

fea-ture is not robust when the humans are crowded and

the images are blurred Wang et al.25 combined the

HOG and local binary pattern (LBP) features for

human detection However, they concluded that their

detector cannot handle the articulated deformation of

people Our visualizations reveal that the world that

features see is slightly different from the world that the

human eye perceives

Recently, LPQ is insensitive to image blurring, and

it has proven to be a very efficient descriptor in face

recognition from blurred and sharp images.15,26 LPQ

was originally designed by Ojansivu and Heikkila

simi-lar to the LBP methodology as a texture descriptor.27

In our opinion, robust and efficient image matching

requires several different kinds of appearance

informa-tion to be taken into account, suggesting the use of

het-erogeneous feature sets In our proposed algorithm, the

HOG features are extracted from the salient regions,

and LPQ features are extracted from the HOG

visualiz-ing image Therefore, the HOG and LPQ are integrated

for building an efficient feature, that is, TFHLS for

indoor image matching

Proposed smartphone camera-based

indoor positioning

The smartphone camera-based indoor positioning

pro-cedure using TFHLS feature is shown in Figure 1

Study materials

In order to test and evaluate the proposed algorithm,

two databases are used The first one is supported by

TUM.28 In TUM dataset, there are 54,896 reference

views, which covers 3431 positions with 1-m accuracy

Another dataset is collected by our lab which captured

1000 indoor images using smartphone cameras in

BUPT campus Different with TUM dataset in

calcu-lating the reference positions, a static measurement

sys-tem based on TC-OFDM and BeiDou real-time

kinematic is introduced The scalable locations with

positioning accuracy 0.1–1 m are obtained The BUPT

dataset covers four buildings and results in a total of

2189 positions

Superpixel-based, sparsifying, high-resolution image

Inspired by the human vision system (HVS), the

fea-tures extracted from salient regions are invariant to

viewpoint change, insensitivity to image perturbations and repeatability under intra-class variation.29 These features are extracted from some regions of the image, but not the whole image This procedure is called spar-sifying image in this article Therefore, the salient region

is introduced for the image matching In this article, a superpixel-based approach, simple linear iterative clus-tering (SLIC), proposed by Achanta et al.30 is used to pre-segment an image SLIC method generates super-pixels by clustering super-pixels based on their combined five-dimensional similarity and proximity in the image plane which is shown by the following functions

dlab=

ffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi (lk li)2+ (ak ai)2+ (bk bi)2

q

ð1Þ

dxy=

ffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi (xk xi)2+ (yk yi)2

q

ð2Þ

Figure 1 Flowchart of smartphone camera-based indoor positioning.

Ds= dlab+m

where Ds is the sum of the dlab distance and the dxy

plane is normalized by the grid interval S A variable m

is introduced in Dsallowing us to control the

compact-ness of a superpixel Equation (1) is used to calculate

the distance between two different pixels in the lab color

space Equation (2) is used to obtain the Euclidean

dis-tance between two different pixels Equation (3) is used

to transform different dimensional distances into the

same dimensional distance Based on equation (3), the

size of each superpixel can be varied with Ds, which

makes our proposed segmentation approach robust

and accurate In the SLIC method, the desired number

of superpixels should be specified, which increases the

computation complexity and is unsuitable for

segment-ing image sequences To detect salient regions from

superpixel image and not the pixel-level image using

equation (4)

<(si) = a 3 C(si) + b 3 T (si) ð4Þ

where< is the candidate salient region, siis the

super-pixel, C is the contrast, T is the superpixel entropy, and

a+ b = 1 The threshold C used for detecting salient

superpixels is calculated using equation (5)

C(si) =msi

where msi is the mean of the i superpixel, and mf is the

mean of an image Then,salient superpixel regions are

detected Moreover, in order to extract the HOG

fea-tures, each salient superpixel regions are extended into

relational rectangles which are named salient rectangles

The sizes of those rectangles are calculated using

equa-tion (6)

Ra =jxmax xminj

Rb =jymax yminj



ð6Þ

where xmax is the position of the far right pixel in the

horizontal direction, and xmin is the position of the far

left pixel in the horizontal direction ymax is the position

of the topside pixel in the vertical direction, and ymin is

the position of the downside pixel in the vertical

direc-tion The center of the salient rectangle is the centroid

of the related superpixel

TFHLS feature extraction approach

HOG feature extraction HOG descriptors are invariant

to two-dimensional (2D) rotation which has been used

in many different problems in computer vision, such as

pedestrian detection Compared to the original HOG,

the integrated HOG feature proposed by Zhu et al.21

without trilinear interpolation is easier and faster to be

computed However, the HOG’s performance would be worse than the original HOG Therefore, we intro-duced a constrained trilinear interpolation approach to replace the general trilinear interpolation Moreover, it should be noted that both Wang et al.25and Li et al.31 proposed a 7 3 7 kernel that is shown in equation (7)

to convolve the gradients for calculating the gradient orientation at each pixel However, it is a heavy com-putation procedure to convolve using the 7 3 7 kernel

A novelty 5 3 5 convolution kernel is designed to be implemented For an 8-bit image, the kernel template is shown in equation (8)

Conv77= 1

256

2 6 6 6 6 4

3 7 7 7 7 5 ð7Þ

ConvHOG= 1

256

2 6 6 4

3 7 7

Moreover, in order to reduce the space complexity of the integral image method, the kernel in equation (8) is convoluted with the salient rectangle but not the whole original image, which decreased the computational complexity

HOG feature visualization In this article, we introduced a HOG visualizing method proposed by Vondrick et al.32 Different with their complex method, a more simple method based on equation (9) is proposed

f1(y) = argmin

x2R D

where x2RD is a salient rectangle sub-image and

y = f(x) is the corresponding HOG feature descriptor

In this article, HOG feature visualization is posed to be

a feature inversion procedure In order to optimize equation (9), we used gradient-descent strategies by numerically evaluating the derivative in image space with least-squares method

LPQ feature extraction from HOG visualization image After inverting HOG features into an image YHOG, LPQ fea-tures are extracted from YHOG using a simple scalar quantizer equation (10) LPQ feature is based on quan-tifying the Fourier transform phase by considering the sign of each component in Fourier coefficients G(x) Different with LBP, LPQ features are calculated in an

image frequency transformed by fast Fourier transform

(FFT) However, the LPQ feature is extracted in a local

region of FFT domain, which is similar to LBP

According to Dhall et al.,33 the local Fourier

coeffi-cients of each pixel are computed around its four

fre-quency points After that, in order to obtain the phase

information of each pixel in superpixel area, a binary

scalar quantizer is implemented for quantifying the

signs of the real and imaginary part of each coefficient

Finally, the quantization result of each coefficient is

coded in an 8-bit binary string

qi(x) = 1 if gi(x) 0

0 otherwise



ð10Þ

where gi(x) is the ith component of G(x) Then, the

phase information of the 8-bit HOG visualizing image

is described using equation (10)

fLPQ(x) = X8

n = 1

The final LPQ features are used as feature vectors to

represent an indoor sub-image

TFHLS feature matching

The main advantage of the binarization, apart from a

reduced memory footprint, is a very fast matching

pro-cess using the normalized Hamming distance by

equa-tion (12)

d =

PN

i = 1

PN

j = 1

PM(i, j)\ QM(i, j)\ Pð R(i, j) QR(i, j)Þ + PM(i, j)\ QM(i, j)\ Pð I(i, j) QI(i, j)Þ

2 PN

i = 1

PN

j = 1

PM(i, j)\ QM(i, j)

ð12Þ

where PR(QR), PI(QI), and PM(QM) are the real part, the

imaginary part, and the mask of P(Q), respectively The

result of the Boolean operator ( ) is equal to zero if

and only if there are two bits The symbol\ represents

the AND operator, and the size of the feature matrixes

is N 3 N

Experimental results Query dataset and setup description

We recorded a query set of 128 images captured by an iPhone 6 with manually annotated position informa-tion The images are approximately 5 megapixels in size and are taken using the default settings of the iPhone 6 camera application Furthermore, the images consist of landscape photos either taken head-on in front of a building or at a slanted angle of approximately 308 After obtaining the images, next, we run the remaining query images with successfully retrieved database images through the pose estimation part of the pipeline

In order to characterize pose estimation accuracy, we first manually ground truth for the position and pose

of each query image taken This is done using the com-puter-aided design (CAD) map of the buildings in BUPT and distance measurements recorded during the query dataset collection For a detailed evaluation, the query set has been split into classes that is the same with the TUM database: high texture, low texture, hall-ways, ambiguous objects, and building structure, where each query can be assigned to more than one class (Figures 2 and 3) Meanwhile, the framework of our smartphone camera-based indoor positioning system is shown in Figure 4 It should be known that we ignore the orientation information calculation

Our method was implemented using MATLAB 2015a, and this method was programmed by integrat-ing C# and MATLAB code The hardware configura-tion of our experimental platform where our method ran is shown in Table 1

Figure 2 Exemplary queries for all classes from TUM: (a) low textures, (b) high textures, (c) blurred image, (d) building hall, (e) hallway, and (f) Illumination change.

It is noted that the camera-based positioning method

proposed by Ravi et al.11is used to compare with our

proposed method, and both the test data and the

MATLAB code of that method are supported by

Opdenbosch

Evaluation of high-resolution image sparsifying

Figure 5 shows a qualitative result for the image

sparsi-fying by detecting salient regions based on superpixels

From the second row of Figure 5 obtained by the pro-posed HVS-based approach for a variety of images from the TUM and BUPT database Preserve the sali-ent regions in each image while remaining compact and uniform in size of objects Moreover, the salient super-pixels that are detected include sparse features, which can be achieved to reduce the computation of indoor positioning

According to Figure 5, we can find that salient regions are detected even when the image is blurred, which is shown by three images in the second column

of Figure 5

According to our statistics, the number of TFHLS features in Figure 6(b) is 69% less than that in Figure 6(a) It is noted that features in Figure 6(b) are extracted from the salient regions of an image, which shows that our salient region detection approach is effi-cient and powerful Therefore, less features are used for image matching, which speeds up the process of the image matching and remains high matching ration according to Table 2

Figure 3 Exemplary queries for all classes from BUPT: (a) low textures, (b) high textures, (c) blurred image, (d) building hall, (e) hallway, and (f) illumination change.

Figure 4 The module of navigation and positioning system.

Table 1 Hardware configuration

CPU Processor Core i7 Core32:5 GHz

Qualitative evaluation of HOG visualization The third row of Figure 5 shows the HOG feature visualization results under different indoor scenarios These result visualizations allow us to analyze object

Figure 5 Exemplary queries for salient region detection and HOG feature visualization: (a) Indoor of Our Lab, (b) Hall of Our Research Building, (c) Corridor of a Building in TMU, (d) Corridor of Our Research Building, (e) Salient Map of Figure 5(a), (f) Salient Map of Figure 5(b), (g) Salient Map of Figure 5(c), (h) Salient Map of Figure 5(d), (i) HOG Feature Visualization of Figure 5(e), (j) HOG Feature Visualization of Figure 5(f), (k) HOG Feature Visualization of Figure 5(g), and (l) HOG Feature Visualization of Figure 5(h).

Figure 6 TFHLS features matching for BUPT images: (a)

TFHLS feature extraction with high density and (b) TFHLS

features sparsing.

Table 2 Matching result of different image features.

rate (%)

Running time (ms)

from the view of HOG detector, which is a new

approach and gain new insight into the detectors

fail-ures, which is different with the human salient vision

From the first and third row of Figure 5, the

high-frequency details in original images have high contrast

in HOG visualization images Paired dictionary

learn-ing tends to produce the best visualization for HOG

descriptors Although HOG does not explicitly describe

the color, we found that the paired dictionary is able to

recover color from HOG descriptors Therefore, by

visualizing feature spaces, we can obtain a more

intui-tive understanding of recognition systems

Evaluation of TFHLS feature extraction and matching

In order to identify optimal parameters for the

approach described above, several experiments are

con-ducted with varying settings Figure 7 summarizes the

performance of comparing the TFHLS feature

matching to the method proposed by Van Opdenbosch

et al.10 A smartphone running Andriod OS 4.4 was used to implementing the positioning methods which were used in this article

Qualitative results Figure 7 shows the TFHLS features matching results in four different scenarios As shown

in Figure 7(a), successful retrieval usually involves matching of object textures in both query and database images According to Figure 7(b), we can find that our proposed TFHLS feature is efficient to match the blurred images

Quantitative results Table 2 shows that we successfully match 113 of 128 images to achieve a retrieval rate of 93%, where LS means linear search and LSH means locality sensitive hashing Moreover, as shown in Table 2, the proposed method achieves to match the images of TUM database with the highest success in

Figure 7 TFHLS features matching for BUPT images: (a) TFHLS features matching for high-texture image, (b) TFHLS features matching for blurred image, (c) TFHLS features matching for low-texture image, and (d) TFHLS features matching for indoor image.

Figure 8 The performance comparison between the proposed human detectors and the state-of-the-art detectors on BUPT database.

13.2 ms for each image Figure 8 shows the

perfor-mance comparison in miss rate between our proposed

method and other two LBP-based methods

Positioning result evaluation

Figure 9 summarizes the performance of the location

information estimation and the comparison result

From Figure 9(a) and (b), we can localize the position

to within sub-meter level of accuracy for over 56% of

the query images Furthermore, 85% of the query

images are successfully localized to within 2 m of the

ground’s truth position As seen in Figure 7(a), when

the location error is less than 1 m, the TFHLS features

of the corresponding corridor signs present in both

query and database images matched together

Moreover, we find that the TFHLS detector extracted

more features,10 even though the images are blurred,

which is shown in Figure 9(b) As shown in Figure

10(a) and (b), we plot the estimated and ground-truth

locations in the horizontal and vertical directions Besides, Figure 10(c) shows the comparing locations of the query images onto the New Research Buildings 2D floor plan As seen from Figure 10, there is a close agreement between the ground truth and TFHLS-based results The root mean square error (RMSE)

Figure 9 The module of smartphone camera-based indoor positioning: (a) positioning result based on TUM dataset and

(b) positioning result based on BUPT dataset.

Figure 10 The location comparison result: (a) positioning result in horizontal direction, (b) positioning result in vertical direction, and (c) locations on the 2D floor plan.

Figure 11 Performance comparison between the proposed indoor positioning and the state-of-the-art positioning methods.

between the estimated and the ground-truth positioning

results is 1.253 m

Figure 11 shows the indoor positioning

compari-son performance in RMSE From this figure, we can

find that the proposed approach can achieve

high-accuracy indoor locations than VLAD- and

OFDM-based methods Most of the VLAD and

TC-OFDM indoor positioning results are more than 3 m,

while the positioning results based on our method is

less than 1.5 m Moreover, the proposed method is

robust because its RMSE curve is smooth, which

shows that our method can get stable results The

per-formance gap between the ground truth and

estima-tions in both Figures 9 and 11 suggests that the

TFHLS-based method can be adaptive to the

illumi-nation and the dense multipath indoor environments

which result in obtaining a higher indoor positioning

accuracy

Conclusion

We presented a scalable and efficient mobile

camera-based localization system To this end, we built a

modi-fied model of a feature that deeply combined HOG and

LPQ, and jointly addressed the problem of limited

computational capacity, as well as the required memory

footprint Moreover, we employed TC-OFDM indoor

positioning system for supporting the coarse

position-ing knowledge related to the camera location

According to our test on the TUM and BUPT

data-base, the indoor positioning based on the proposed

algorithm is less than 1.5 m Furthermore, the RMSE

between estimated and ground-truth positioning results

up to 1.25 m, which shows that our smartphone

camera-based indoor positioning algorithm is precise

and accuracy In the future work, we will study the

sub-meter indoor positioning algorithms based on the

fusion of image and wireless signals

Declaration of conflicting interests

The author(s) declared no potential conflicts of interest with

respect to the research, authorship, and/or publication of this

article.

Funding

The author(s) disclosed receipt of the following financial

sup-port for the research, authorship, and/or publication of this

article: This project was sponsored by the National Key

Research and Development Program (no 2016YFB0502002),

the National High Technology Research and Development

Program of China (no 2015AA124103), the National Natural

Science Foundation of China (no 61401040), and Beijing

University of Posts and Telecommunications Young Special

Scientific Research Innovation Plan (2016RC13).

References

1 Gonzalez MC, Hidalgo CA and Barabasi AL Under-standing individual human mobility patterns Nature 2008; 453(7196): 779–782.

2 Liu H, Darabi H, Banerjee P, et al Survey of wireless indoor positioning techniques and systems IEEE T Syst Man Cy C 2007; 37(6): 1067–1080.

3 Lee C, Chang Y, Park G, et al Indoor positioning sys-tem based on incident angles of infrared emitters In: Proceedings of the 30th annual conference of IEEE Indus-trial Electronics Society, Busan, South Korea, 2–6 November 2004, pp.2218–2222 New York: IEEE.

4 Li B, Gallagher T, Dempster AG, et al How feasible is the use of magnetic field alone for indoor positioning? In: Proceedings of the international conference on indoor positioning and indoor navigation (IPIN), Sydney, NSW, Australia, 13–15 November 2012, pp.1–9 New York: IEEE.

5 Zou H, Jiang H, Lu X, et al An online sequential extreme learning machine approach to wifi based indoor positioning In: Proceedings of the 2014 IEEE World Forum on Internet of Things (WF-IoT), Seoul, Korea, 6–

8 March 2014, pp.111–116 New York: IEEE.

6 Huang CH, Lee LH, Ho CC, et al Real-time rfid indoor positioning system based on Kalman-filter drift removal and heron-bilateration location estimation IEEE T Instrum Meas 2015; 64(3): 728–739.

7 Zhongliang D, Yanpei Y, Xie Y, et al Situation and development tendency of indoor positioning China Com-mun 2013; 10(3): 42–55.

8 Politi N, Yong L, Faisal K, et al Locata: A new technol-ogy for high precision positioning In: European naviga-tion conference, Naples, 3–6 May 2009 Institute of Navigation.

9 Kalkusch M, Lidy T, Knapp N, et al Structured visual markers for indoor pathfinding In: Proceedings of the 1st IEEE international workshop on augmented reality toolkit, Darmstadt, 29 September 2002, p.8 New York: IEEE.

10 Van Opdenbosch D, Schroth G, Huitl R, et al Camera-based indoor positioning using scalable streaming of compressed binary image signatures In: Proceedings of the IEEE international conference on image processing (ICIP), Paris, 27–30 October 2014 New York: IEEE.

11 Ravi N, Shankar P, Frankel A, et al Indoor localization using camera phones In: Proceedings of the 7th IEEE workshop on mobile computing systems and applications (WMCSA’06), Semiahmoo Resort Blaine, WA, USA, 1 August 2005, p.49 New York: IEEE.

12 Kim J and Jun H Vision-based location positioning using augmented reality for indoor navigation IEEE T Consum Electr 2008; 54(3): 954–962.

13 Werner M, Kessel M and Marouane C Indoor position-ing usposition-ing smartphone camera In: Proceedposition-ings of the international conference on indoor positioning and indoor navigation (IPIN), Sydney, NSW, Australia, 21–23 Sep-tember 2011, pp.1–6 New York: IEEE.

14 Li X and Wang J Image matching techniques for vision-based indoor navigation systems: performance analysis for 3d map based approach In: Proceedings of the