RFID based People-Object Direction of Pass Detection Ral Parada a , - - PowerPoint PPT Presentation

▶
rfid based people object direction of pass detection
SMART_READER_LITE
LIVE PREVIEW

RFID based People-Object Direction of Pass Detection Ral Parada a , - - PowerPoint PPT Presentation

Nov 15, 2022 737 likes •1.14k views

RFID based People-Object Direction of Pass Detection Ral Parada a , Joan Meli-Segu b , c and Rafael Pous a Universitat Pompeu Fabra (UPF) a Departament de Tecnologies de la Informaci i les Comunicacions (DTIC) Universitat Oberta de

slide-1
SLIDE 1

RFID based People-Object Direction of Pass Detection

Raúl Paradaa, Joan Melià-Seguíb,c and Rafael Pousa Universitat Pompeu Fabra (UPF)

aDepartament de Tecnologies de la Informació i les Comunicacions (DTIC)

Universitat Oberta de Catalunya (UOC)

bEstudis d’Informàtica, Multimèdia i Telecomunicació (EIMT) cInternet Interdisciplinary Institut (IN3)

12th International Conference

  • n Intelligent Environments

London, United Kingdom - September 12-16, 2016

slide-2
SLIDE 2

Customer behavior

slide-3
SLIDE 3

Table of Contents

1 Introduction 2 People-Object Movement Detection Principle 3 Methodology 4 Experiments and Results 5 Conclusion & Future Work

slide-4
SLIDE 4

Table of Contents

1 Introduction 2 People-Object Movement Detection Principle 3 Methodology 4 Experiments and Results 5 Conclusion & Future Work

slide-5
SLIDE 5

Motivation & Research Objectives

  • Retailers do not know the hot-spots

within their stores, to increase sales.

  • A study of different methods to

correctly classify the people-object direction of pass.

  • A comparison of different

state-off-the-art RFID antennas to increase the people-object direction

  • f pass detection rate.
  • An extensive empirical analysis of

people-object direction of pass with multiple tags and events.

Raúl Parada 1/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-6
SLIDE 6

Motivation & Research Objectives

  • Retailers do not know the hot-spots

within their stores, to increase sales.

  • A study of different methods to

correctly classify the people-object direction of pass.

  • A comparison of different

state-off-the-art RFID antennas to increase the people-object direction

  • f pass detection rate.
  • An extensive empirical analysis of

people-object direction of pass with multiple tags and events.

Raúl Parada 1/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-7
SLIDE 7

Motivation & Research Objectives

  • Retailers do not know the hot-spots

within their stores, to increase sales.

  • A study of different methods to

correctly classify the people-object direction of pass.

  • A comparison of different

state-off-the-art RFID antennas to increase the people-object direction

  • f pass detection rate.
  • An extensive empirical analysis of

people-object direction of pass with multiple tags and events.

Raúl Parada 1/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-8
SLIDE 8

Motivation & Research Objectives

  • Retailers do not know the hot-spots

within their stores, to increase sales.

  • A study of different methods to

correctly classify the people-object direction of pass.

  • A comparison of different

state-off-the-art RFID antennas to increase the people-object direction

  • f pass detection rate.
  • An extensive empirical analysis of

people-object direction of pass with multiple tags and events.

Raúl Parada 1/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-9
SLIDE 9

Related Work (I)

Using computer vision and sensors

Chung et al., Locomotive wireless video recorder and recording system, 2014. Ahmed et al., Design and implementation of a mobile based gate passing detection method, 2015.

Raúl Parada 2/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-10
SLIDE 10

Related Work (II)

Only using RFID data

Lee et al., A gate sensor for construction logistics, 2008. Nikitin et al., Phase based spatial identification of UHF RFID tags, 2010.

Raúl Parada 3/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-11
SLIDE 11

Related Work (III)

Also using RFID data

Oikawa et al., Tag movement direction estimation methods in an RFID gate system., 2009.

Raúl Parada 4/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-12
SLIDE 12

Table of Contents

1 Introduction 2 People-Object Movement Detection Principle 3 Methodology 4 Experiments and Results 5 Conclusion & Future Work

slide-13
SLIDE 13

Direction of Pass Principle

  • Based on the
  • rder in detecting

labeled objects from the antennas

  • The object A is

leaving when first read by Ant1 and last by Ant 2

  • Or entering with
  • pposite read
  • rder "Object B"

Raúl Parada 5/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-14
SLIDE 14

Direction of Pass Principle

  • Based on the
  • rder in detecting

labeled objects from the antennas

  • The object A is

leaving when first read by Ant1 and last by Ant 2

  • Or entering with
  • pposite read
  • rder "Object B"

Raúl Parada 5/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-15
SLIDE 15

Direction of Pass Principle

  • Based on the
  • rder in detecting

labeled objects from the antennas

  • The object A is

leaving when first read by Ant1 and last by Ant 2

  • Or entering with
  • pposite read
  • rder "Object B"

Raúl Parada 5/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-16
SLIDE 16

RFID

  • Semantic indicators
  • Identification code (96-bit typically)
  • Antenna Port
  • Timestamp
  • Additional indicators
  • Received signal strength indicator (RSSI)
  • Radio frequency phase (PHASE)
  • Read Count

Raúl Parada 6/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-17
SLIDE 17

RFID indicators

  • Extract RFID indicators from a passive RFID tag
  • The RSSI indicator shows a dynamic behavior of a passive

tag

Raúl Parada 7/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-18
SLIDE 18

RFID indicators

  • Extract RFID indicators from a passive RFID tag
  • The RSSI indicator shows a dynamic behavior of a passive

tag

Raúl Parada 7/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-19
SLIDE 19

Features’ generation

  • Generated RFID features from low and high-level

indicators

1 BEAM: Positive and negative numeric identifiers to tag

each antenna lobe depending on their position.

2 TIME: Interval of time in seconds between the first sample

and the rest.

3 AV_TIME: Mean of the feature TIME in seconds from each

antenna port indicator.

4 MINUS TIME: Interval of time in seconds between the last

sample and the rest.

5 M1: Product of multiplying TIME per BEAM. 6 M2: Product of multiplying MINUS TIME per BEAM.

Raúl Parada 8/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-20
SLIDE 20

Methods and Weights

  • Designed methods to detect direction of pass using

uniquely RFID data

1 Slope: Based on a lineal model from the BEAM and TIME

features.

2 Average Time: Based on the AV_TIME feature. 3 Momentum: Based on the M1 and M2 features.

  • Implemented weights to enhance the methods:

1 W1: It is the read count indicator. 2 W2: Difference of a given RSSI indicator value and the

minimum among all the samples.

3 W3: Result of multiplying the weights W1 and W2.

Raúl Parada 9/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-21
SLIDE 21

Table of Contents

1 Introduction 2 People-Object Movement Detection Principle 3 Methodology 4 Experiments and Results 5 Conclusion & Future Work

slide-22
SLIDE 22

Experimental Setup

  • Two RFID antennas (with different directivity and gain)
  • Eight labeled-objects (two diverse passive tags)
  • RFID reader:
  • ThingMagic M6e (ETSI)
  • Read rate: 400 tags/second

Raúl Parada 10/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-23
SLIDE 23

Experimental Setup

1 2 3 4 1 2

PHASED ARRAY SYSTEM TILTED SYSTEM

  • Two scenarios:

1 Phased array: Four beams generated Using a phase

shifter

2 Tilted: Tilt antennas to project beams in opposite directions

Raúl Parada 11/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-24
SLIDE 24

Tests

  • RFID Antennas
  • 1x3 array
  • 2x2 array
  • 1x1 air array
  • Reading mode
  • Sequential
  • Autonomous
  • Antenna’s position
  • No-tilted
  • Tilted
  • Phased
  • Read Power
  • 30 dBm
  • 27 dBm
  • Passive RFID Tags
  • Web G2iL
  • Frog 3D
  • Different products
  • Material
  • Size
  • Shape
  • Multitag
  • Multiple

labeled-objects

  • Multievent
  • Entering
  • Leaving
  • Static

Raúl Parada 12/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-25
SLIDE 25

Table of Contents

1 Introduction 2 People-Object Movement Detection Principle 3 Methodology 4 Experiments and Results 5 Conclusion & Future Work

slide-26
SLIDE 26

RFID Antennas (I)

Phased - RFID Antenna: 1x3 array - Read Power: 30 dBm

25 50 75 1 – 2 1 – 2 – 3 – 4 1 – 3 1 – 4 2 – 3 2 – 4 3 – 4 Combination of beams Accuracy [%]

Methods Slope...No.weight Slope...W1 Slope...W2 Slope...W3 Average.Time...No.Weight Average.Time...W1 Average.Time...W2 Average.Time...W3 Momentum...No.weight Momentum...W1 Momentum...W2 Momentum...W3

Raúl Parada 13/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-27
SLIDE 27

RFID Antennas (II)

Phased - RFID Antenna: 2x2 array - Read Power: 30 dBm

25 50 75 100 1 − 2 1 − 2 − 3 − 4 1 − 3 1 − 4 2 − 3 2 − 4 3 − 4 Combination of beams Accuracy [%]

Methods Slope...No.weight Slope...W1 Slope...W2 Slope...W3 Average.Time...No.Weight Average.Time...W1 Average.Time...W2 Average.Time...W3 Momentum...No.weight Momentum...W1 Momentum...W2 Momentum...W3

Raúl Parada 14/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-28
SLIDE 28

RFID Antennas (III)

Phased - RFID Antenna: 1x1 air array - Read Power: 30 dBm

25 50 75 100 1 − 2 1 − 2 − 3 − 4 1 − 3 1 − 4 2 − 3 2 − 4 3 − 4 Combination of beams Accuracy [%]

Methods Slope...No.weight Slope...W1 Slope...W2 Slope...W3 Average.Time...No.Weight Average.Time...W1 Average.Time...W2 Average.Time...W3 Momentum...No.weight Momentum...W1 Momentum...W2 Momentum...W3

Raúl Parada 15/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-29
SLIDE 29

Reading mode and Antenna’s position

No-Tilt and Tilt - RFID Antennas: 1x1 air array and 2x2 array - Reading Mode: Sequential and Autonomous Read Power: 30 dBm

25 50 75 100 AUT – No Tilt – 2x2 AUT – No Tilt – air 1x1 AUT – Tilt – 2x2 AUT – Tilt – air 1x1 SEQ – No Tilt – 2x2 SEQ – No Tilt – air 1x1 SEQ – Tilt – 2x2 SEQ – Tilt – air 1x1

Reading Mode − Antenna Position − Antenna Type Accuracy [%]

Methods Slope...No.weight Slope...W1 Slope...W2 Slope...W3 Average.Time...No.Weight Average.Time...W1 Average.Time...W2 Average.Time...W3 Momentum...No.weight Momentum...W1 Momentum...W2 Momentum...W3

Raúl Parada 16/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-30
SLIDE 30

Passive RFID tags and Read Power

Tilt - RFID Antenna: 2x2 array - Passive RFID tag: Web G2iL and Frog 3D - Read Power: 27 and 30 dBm

25 50 75 100 Frog3D − 27 dBm Frog3D − 30 dBm Web – 27 dBm Web – 30 dBm

Passive tag − Read Power Accuracy [%]

Methods Slope...No.weight Slope...W1 Slope...W2 Slope...W3 Average.Time...No.Weight Average.Time...W1 Average.Time...W2 Average.Time...W3 Momentum...No.weight Momentum...W1 Momentum...W2 Momentum...W3

Raúl Parada 17/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-31
SLIDE 31

Multitag

Tilt - RFID Antenna: 2x2 array - Read Power: 30 dBm - Diverse Labeled-Object

25 50 75 100 1 – Wool Robe 2 – Plastic Doll 3 – Plastic Rainboot4 – Ceramic Mug 5 – Plastic Bowl 6 – Polyester dress

Products Accuracy [%]

Methods Slope...No.weight Slope...W1 Slope...W2 Slope...W3 Average.Time...No.Weight Average.Time...W1 Average.Time...W2 Average.Time...W3 Momentum...No.weight Momentum...W1 Momentum...W2 Momentum...W3

Raúl Parada 18/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-32
SLIDE 32

Multievent

Tilt - RFID Antenna: 2x2 array - Read Power: 30 dBm - Diverse Labeled-Object and Events

25 50 75 100 1 − Static 2 − IN 3 − IN 4 − OUT 5 – OUT 6 − Static

Product − Event Accuracy [%]

Methods Slope...No.weight Slope...W1 Slope...W2 Slope...W3 Average.Time...No.Weight Average.Time...W1 Average.Time...W2 Average.Time...W3 Momentum...No.weight Momentum...W1 Momentum...W2 Momentum...W3

Raúl Parada 19/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-33
SLIDE 33

Table of Contents

1 Introduction 2 People-Object Movement Detection Principle 3 Methodology 4 Experiments and Results 5 Conclusion & Future Work

slide-34
SLIDE 34

Conclusion & Research Contributions

  • Designed two approaches of people-object direction of

pass detection using uniquely RFID data and off-the-shelf antennas.

  • Both tilted and phased array approach achieved a 100%

accuracy on reading and detecting the direction of pass of passively labeled-objects

  • Experiments confirmed the reliability of our methods to

detect multiple tags and events

  • Suitable solution for real retail store environments

Raúl Parada 20/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-35
SLIDE 35

Conclusion & Research Contributions

  • Designed two approaches of people-object direction of

pass detection using uniquely RFID data and off-the-shelf antennas.

  • Both tilted and phased array approach achieved a 100%

accuracy on reading and detecting the direction of pass of passively labeled-objects

  • Experiments confirmed the reliability of our methods to

detect multiple tags and events

  • Suitable solution for real retail store environments

Raúl Parada 20/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-36
SLIDE 36

Conclusion & Research Contributions

  • Designed two approaches of people-object direction of

pass detection using uniquely RFID data and off-the-shelf antennas.

  • Both tilted and phased array approach achieved a 100%

accuracy on reading and detecting the direction of pass of passively labeled-objects

  • Experiments confirmed the reliability of our methods to

detect multiple tags and events

  • Suitable solution for real retail store environments

Raúl Parada 20/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-37
SLIDE 37

Conclusion & Research Contributions

  • Designed two approaches of people-object direction of

pass detection using uniquely RFID data and off-the-shelf antennas.

  • Both tilted and phased array approach achieved a 100%

accuracy on reading and detecting the direction of pass of passively labeled-objects

  • Experiments confirmed the reliability of our methods to

detect multiple tags and events

  • Suitable solution for real retail store environments

Raúl Parada 20/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-38
SLIDE 38

Future Work

  • Test in autonomous mode the phased array approach.
  • Increase the number of products for each event: IN, OUT

and static.

  • Study the performance of our approaches with other

products material, size, shape, etc. and antennas

  • Implement our approaches in a real retail store

environment.

Raúl Parada 21/21 Introduction The proposed system Methodology Evaluation Conclusion

slide-39
SLIDE 39

RFID based People-Object Direction of Pass Detection

Raúl Parada Medina http://rparada.com DTIC, Universitat Pompeu Fabra