SlideShare a Scribd company logo
1 of 48
Summary of IPIN 2017
Competition Track4
Track Chairs: Masakatsu Kourogi, Ryosuke Ichikari (AIST)
Contributor: Ryo Shimomura (U. of Tsukuba)1
Sponsors
Characteristics of Track4
• Competition using data measured in real warehouse
– 7 picking workers are measured
for about 3 hours
– Competitors submit trajectory of workers.
• Multiple sources of localization
– Senor data for PDR, WMS(warehouse
management system) log, map and
obstacles information, RSSI of BLE tag
• Various actions
– Walking / Picking at shelves/ Operating the
terminals / Carrying goods using carts
• Realistic walking style
– free route, forward/side/back step, stop
• Data measurement by smartphone
2
Data shared for competition
3
P1 P2
P3
Picking log data from
WMS
Smartphone Sensor data
(gyro. ,acceleration, magnetism,
air pressure, BLE log)
Information about
Warehouse
(Map, Shelves, Obstacles)
Ground Truth: Selected WMS log
X Y time1
X Y time2
X Y time3
WMS data
X Y time n-2
X Y time n-1
Shared as
reference points
Used as
ground truth
X Y time n-3
X Y time0
X Y time 1
X Y time 2
X Y time 3
X Y time 0
X Y time n-2
X Y time n-1
X Y time n
X Y time n-3
X Y time n
Original
Ratio of Reference: Ground Truth ⇒ 1:1(Easy), 1:3 (Hard)
Evaluation Metrics
Accuracy metrics
• Integrated positioning error evaluation (Ed)
• PDR error evaluation (Es)
Naturalness metrics
• Human moving velocity evaluation (Ev)
• Update frequency evaluation (Ef)
Warehouse-dedicated metric
• Obstacle interference evaluation (Eo)
• Picking work evaluation (Ep)
5
Integrated positioning error (Ed)
6
Score function
• Median of all positional errors at
evaluation points (points with ground truth)
PDR error evaluation (Es)
• Error metrics for accumulation error.
• Error accumulation can be evaluated by the slope of
regression line [Abe et al. IPIN2016]
7
Close to
Reference points
Far from
Reference points
Score function of PDR error
8
Picking work evaluation (Ep)
• Metric for naturalness
of trajectory around
picking points
• Checks movements
around picking
(+/-1.5 sec.)
9
Pi: Number of times of picking whose
movement distance bellow 1m
Pmax : Number of all true positions.
Human moving velocity evaluation (Ev)
• Metric for naturalness of moving velocity
• Checks velocity compared to threshold
[1.5m/s].
10
vi: Number of times that it is determined to
be a human moving velocity*.vmax: Number
between all trajectory positions.
Obstacle interference evaluation (Eo)
• Metric for obstacle interference of trajectory
• Checks how many pixels of trajectory (not only
submitted points) are in the obstacles area
11
oi: Pixels of trajectory without obstacle
interference*. omax: Total pixels of trajectory.
Update frequency evaluation (Ef)
• Frequency of trajectories are expected to
more than 1Hz.
12
fi: The number of frames whose updated
frequency is more than 1[Hz]
fmax: The total number of frames of trajectory.
Comprehensive evaluation (C.E.)
• Integrated positioning error evaluation (Ed)
• PDR error evaluation (Es)
• Picking work evaluation (Ep)
• Human moving velocity evaluation (Ev)
• Obstacle interference evaluation (Eo)
• Update frequency evaluation (Ef)
13
Our competitiors
Team 1
(ETRI)
A Multi-Sensor Fusion Technique for Pedestrian Localization in a Warehouse
Youngjae Lee, Haemin Lee, Jinhong Kim, Dongyeop, Kang, Kiyoung Moon (ETRI,
Korea), Seong Yun Cho (Kyeongil University, Korea)
Team 2
(KDDI)
No PDR, No future
Yoshihiro Ito, Hisashi Hoshi (KDDI R&D Laboratories Inc., Japan)
Team 3
(XMU)
A Smartphone Based Indoor Positioning System
Lingxiang Zheng, Yizhen Wang, Ao Peng, Zhenyang Wu, Dihong Wu, Biyu Tang, Hai
Lu, Haibin Shi ( Xiamen University, China), Huiru Zheng (University of Ulster, Ireland)
Team 4
(Nagoya)
Trajectory Estimation Using PDR and Simulation of Human-Like Movement
Kotaro Hananouchi, Junto Nozaki, Kenta Urano, Kei Hiroi, Nobuo Kawaguchi
(Nagoya University, Japan)
Team 5
(YZU)
Moving Trajectory Estimation Based on Sensors
Ho-Ti Cheng, Wen-Chen Lu, Chia-Min Lin, Yu-Shen Lai, Yun-Yeh, Huan-Wei Liu, Shih-
Hau Fang (Yuan Ze University, Taiwan) Ying-Ren Chien (National Ilan University,
Taiwan), Yu Tsao (Academia Sinica, Taiwan)
14
Results
15
Submitted Trajectories
• Terminal 2
16
Our estimation (Terminal 2)
17
Submitted Trajectories
• Terminal 3
18
Our estimation (Terminal 3)
19
Submitted Trajectories
• Terminal 4
20
Our estimation (Terminal 4)
21
Submitted Trajectories
• Terminal 5
22
Our estimation (Terminal 5)
23
Submitted Trajectories
• Terminal 6
24
Our estimation (Terminal 6)
25
Submitted Trajectories
• Terminal 7
26
Our estimation (Terminal 7)
27
Submitted Trajectories
• Terminal 8
28
Our estimation (Terminal 8)
29
Scores
30
Scores for Terminal 2
31
Team Level Ed Es Ep Ev Eo Ef Error
median
C.E.
ETRI Easy 66.875 96.028 100 99.995 46.375 17.335 10.606 68.22
6
KDDI Easy 72.558 99.367 34.783 100 100 100 8.958 91.12
4
Nagoya Easy 73.333 100 81.818 94.132 95.581 99.201 8.733 91.47
2
XMU Easy 81.970 99.419 81.818 97.177 70.970 99.995 6.229 86.23
6
YZU Easy 77.841 99.007 100 99.167 65.816 100 7.426 84.99
0
Scores for Terminal 3
32
Team Level Ed Es Ep Ev Eo Ef Error
median
C.E.
ETRI Hard 67.895 97.096 97.531 99.997 23.072 3.736 10.310 60.170
KDDI Hard 64.811 97.926 53.086 100 100 100 11.205 90.202
Nagoya Hard 68.639 100 77.215 79.382 94.470 98.345 10.095 87.671
XMU Hard 84.049 98.811 82.927 97.172 71.450 99.992 5.626 86.728
YZU Hard 79.346 98.196 97.436 99.197 44.607 100 6.990 78.642
Score for Terminal 4
33
Team Level Ed Es Ep Ev Eo Ef Error
median
C.E.
ETRI Easy 72.763 93.155 91.892 99.999 45.523 18.338 8.899 68.268
KDDI Easy 72.078 96.349 35.135 100 99.944 100 9.097 90.425
Nagoya Easy 61.929 98.569 63.888 76.866 89.704 99.144 12.041 83.650
XMU Easy 78.043 95.052 89.189 95.526 69.168 99.992 7.368 84.157
YZU Easy 62.918 93.986 100 98.922 61.038 100 11.754 79.531
Scores for Terminal 5
34
Team Level Ed Es Ep Ev Eo Ef Error
median
C.E.
ETRI Easy 60.493 99.915 96.551 100 80.028 15.257 12.457 77.444
KDDI Easy 66.197 99.712 41.379 100 99.187 100 10.803 90.007
Nagoya Easy 61.564 99.417 65.517 93.544 94.464 99.770 12.146 87.820
XMU Easy 82.752 100 66.666 94.697 67.671 97.701 6.002 84.160
YZU Easy 70.976 99.786 89.655 99.662 31.440 100 9.417 73.016
Scores for Terminal 6
35
Team Level Ed Es Ep Ev Eo Ef Error
median
C.E.
ETRI Easy 59.002 95.525 100 100 64.104 1.951 12.889 70.332
KDDI Easy 85.239 100 44 100 100 100 5.281 94.248
Nagoya Easy 72.843 97.139 61.905 86.017 94.006 99.389 8.876 88.135
XMU Easy 81.450 99.399 92 95.164 46.881 99.638 6.379 79.072
YZU Easy 78.335 99.187 100 98.492 35.990 100 7.283 76.075
Scores for Terminal 7
36
Team Level Ed Es Ep Ev Eo Ef Error
median
C.E.
ETRI Hard - - - - - - - -
KDDI Hard 73.622 97.054 56.881 100 100 100 8.650 91.979
Nagoya Hard 73.903 99.276 82.569 92.002 93.027 99.499 8.568 90.423
XMU Hard 41.548 92.034 92.157 94.728 43.730 97.713 17.951 68.424
YZU Hard 75.627 96.245 99.083 98.917 42.906 100 8.068 77.038
Scores for Terminal 8
37
Team Level Ed Es Ep Ev Eo Ef Error
median
C.E.
ETRI Hard - - - - - - - -
KDDI Hard 71.963 95.375 39.552 100 100 100 9.131 90.445
Nagoya Hard 81.768 100 76.119 92.901 93.593 99.548 6.287 92.127
XMU Hard 23.646 87.706 90 95.133 47.490 99.641 23.143 65.252
YZU Hard 82.347 97.746 96.212 99.292 36.909 100 6.119 76.796
Final Results
38
Prize
• 1) PDR module (Sugihara SEI Co. &Lt.,
200,000 JPY worth) + 100,000 JPY
or
• 2) 150,000 JPY
39
Final Score
RANKING TEAM
AVERAGE OF
C.E.
Winner(1st) KDDI 91.163
Runner-up(2nd) Nagoya U. 88.921
3rd XMU 78.437
40
Ave. Scores for ALL Terminals
41
Team Ed Es Ep Ev Eo Ef Error
median
C.E.
ETRI 65.406 96.344 97.195 99.998 51.821 11.323 11.032 65.741
KDDI 72.353 97.969 43.545 100 99.876 100 9.018 91.163
Nagoya 70.569 99.200 72.719 87.835 93.549 99.271 9.535 88.921
XMU 67.637 96.060 84.965 95.657 59.623 99.239 10.385 78.437
YZU 75.341 97.736 97.484 99.093 45.530 100 8.151 77.947
42
Picture of Ed(1st)
Graph of Es(1st)
43
Terminal ID slop
Terminal2 0.06234699249
81115
Terminal3 0.090435326
4159421
Terminal4 0.121188344
408936
Terminal5 0.055607695
6764035
Terminal6 0.048479055
3534408
Terminal7 0.107438470
408959
Terminal8 0.140182398
620238
y = 0.0623x
0
5
10
15
20
25
30
0 50 100 150 200 250 300 350 400 450
positionerror
time
KDDI Terminal2
Picture of Eo(1st)
44
45
Picture of Ed(2nd)
Graph of Es(2nd)
46
y = 0.0484x
0
10
20
30
40
50
60
70
0 100 200 300 400 500 600
positionerror
time
Nagoya Terminal2
Terminal ID slop
Terminal2 0.04842440929
53409
Terminal3 0.038564395
4126861
Terminal4 0.077903625
1886814
Terminal5 0.061358972
1000901
Terminal6 0.105793910
255521
Terminal7 0.064109388
7045351
Terminal8 0.039750897
7779014
Picture of Eo(2st)
47
Thank you for participation
48

More Related Content

More from Kurata Takeshi

「遠隔リハビリのための多感覚XR-AI技術基盤構築と保健指導との互恵ケア連携」で目指すところ
「遠隔リハビリのための多感覚XR-AI技術基盤構築と保健指導との互恵ケア連携」で目指すところ「遠隔リハビリのための多感覚XR-AI技術基盤構築と保健指導との互恵ケア連携」で目指すところ
「遠隔リハビリのための多感覚XR-AI技術基盤構築と保健指導との互恵ケア連携」で目指すところKurata Takeshi
 
遠隔リハビリ研究とオンライン学会運営から見たコミュニケーションDX
遠隔リハビリ研究とオンライン学会運営から見たコミュニケーションDX遠隔リハビリ研究とオンライン学会運営から見たコミュニケーションDX
遠隔リハビリ研究とオンライン学会運営から見たコミュニケーションDXKurata Takeshi
 
Analyzing Operations on a Manufacturing Line using Geospatial Intelligence T...
Analyzing Operations on a Manufacturing Line using Geospatial Intelligence T...Analyzing Operations on a Manufacturing Line using Geospatial Intelligence T...
Analyzing Operations on a Manufacturing Line using Geospatial Intelligence T...Kurata Takeshi
 
国際標準化におけるAR/MR用語の使われ方
国際標準化におけるAR/MR用語の使われ方国際標準化におけるAR/MR用語の使われ方
国際標準化におけるAR/MR用語の使われ方Kurata Takeshi
 
XRに基づく遠隔リハの研究・事業事例調査報告
XRに基づく遠隔リハの研究・事業事例調査報告XRに基づく遠隔リハの研究・事業事例調査報告
XRに基づく遠隔リハの研究・事業事例調査報告Kurata Takeshi
 
「遠隔リハビリのための多感覚XR-AI技術基盤構築と保健指導との互恵ケア連携」の概要
「遠隔リハビリのための多感覚XR-AI技術基盤構築と保健指導との互恵ケア連携」の概要「遠隔リハビリのための多感覚XR-AI技術基盤構築と保健指導との互恵ケア連携」の概要
「遠隔リハビリのための多感覚XR-AI技術基盤構築と保健指導との互恵ケア連携」の概要Kurata Takeshi
 
サービス学とか何か(応用サービス工学)
サービス学とか何か(応用サービス工学)サービス学とか何か(応用サービス工学)
サービス学とか何か(応用サービス工学)Kurata Takeshi
 
XR/xDRによる労働生産性の向上、QoW向上
XR/xDRによる労働生産性の向上、QoW向上XR/xDRによる労働生産性の向上、QoW向上
XR/xDRによる労働生産性の向上、QoW向上Kurata Takeshi
 
地理空間インテリジェンス技術を用いた 製造ラインでの作業分析
地理空間インテリジェンス技術を用いた 製造ラインでの作業分析地理空間インテリジェンス技術を用いた 製造ラインでの作業分析
地理空間インテリジェンス技術を用いた 製造ラインでの作業分析Kurata Takeshi
 
Geospatial Intelligence for Health and Productivity Management in Japanese Re...
Geospatial Intelligence for Health and Productivity Management in Japanese Re...Geospatial Intelligence for Health and Productivity Management in Japanese Re...
Geospatial Intelligence for Health and Productivity Management in Japanese Re...Kurata Takeshi
 
製造業・サービス業での人とシステムとの協調
製造業・サービス業での人とシステムとの協調製造業・サービス業での人とシステムとの協調
製造業・サービス業での人とシステムとの協調Kurata Takeshi
 
地理空間インテリジェンス:屋内測位技術を用いた現場のラボ化に基づくサービス研究事例
地理空間インテリジェンス:屋内測位技術を用いた現場のラボ化に基づくサービス研究事例地理空間インテリジェンス:屋内測位技術を用いた現場のラボ化に基づくサービス研究事例
地理空間インテリジェンス:屋内測位技術を用いた現場のラボ化に基づくサービス研究事例Kurata Takeshi
 
Benchmarking of indoor localization and tracking systems (LTSs)
Benchmarking of indoor localization and tracking systems (LTSs)Benchmarking of indoor localization and tracking systems (LTSs)
Benchmarking of indoor localization and tracking systems (LTSs)Kurata Takeshi
 
健康経営のための地理空間インテリジェンス(GSI)に関する一考察
健康経営のための地理空間インテリジェンス(GSI)に関する一考察健康経営のための地理空間インテリジェンス(GSI)に関する一考察
健康経営のための地理空間インテリジェンス(GSI)に関する一考察Kurata Takeshi
 
Communication beyond spatiotemporal constraints
Communication beyond spatiotemporal constraintsCommunication beyond spatiotemporal constraints
Communication beyond spatiotemporal constraintsKurata Takeshi
 
応用サービス工学研究室紹介2020
応用サービス工学研究室紹介2020応用サービス工学研究室紹介2020
応用サービス工学研究室紹介2020Kurata Takeshi
 
OTASCE Map: A Mobile Map Tool with Customizable Audio-Tactile Cues for the Vi...
OTASCE Map: A Mobile Map Tool with Customizable Audio-Tactile Cues for the Vi...OTASCE Map: A Mobile Map Tool with Customizable Audio-Tactile Cues for the Vi...
OTASCE Map: A Mobile Map Tool with Customizable Audio-Tactile Cues for the Vi...Kurata Takeshi
 
PDRと統合測位で製造業の『働き方改革』!
PDRと統合測位で製造業の『働き方改革』!PDRと統合測位で製造業の『働き方改革』!
PDRと統合測位で製造業の『働き方改革』!Kurata Takeshi
 
インドア測位技術の現況:UWBビジネス元年到来?!
インドア測位技術の現況:UWBビジネス元年到来?!インドア測位技術の現況:UWBビジネス元年到来?!
インドア測位技術の現況:UWBビジネス元年到来?!Kurata Takeshi
 
位置合わせや(屋内)測位に関する国際コンペと標準化
位置合わせや(屋内)測位に関する国際コンペと標準化位置合わせや(屋内)測位に関する国際コンペと標準化
位置合わせや(屋内)測位に関する国際コンペと標準化Kurata Takeshi
 

More from Kurata Takeshi (20)

「遠隔リハビリのための多感覚XR-AI技術基盤構築と保健指導との互恵ケア連携」で目指すところ
「遠隔リハビリのための多感覚XR-AI技術基盤構築と保健指導との互恵ケア連携」で目指すところ「遠隔リハビリのための多感覚XR-AI技術基盤構築と保健指導との互恵ケア連携」で目指すところ
「遠隔リハビリのための多感覚XR-AI技術基盤構築と保健指導との互恵ケア連携」で目指すところ
 
遠隔リハビリ研究とオンライン学会運営から見たコミュニケーションDX
遠隔リハビリ研究とオンライン学会運営から見たコミュニケーションDX遠隔リハビリ研究とオンライン学会運営から見たコミュニケーションDX
遠隔リハビリ研究とオンライン学会運営から見たコミュニケーションDX
 
Analyzing Operations on a Manufacturing Line using Geospatial Intelligence T...
Analyzing Operations on a Manufacturing Line using Geospatial Intelligence T...Analyzing Operations on a Manufacturing Line using Geospatial Intelligence T...
Analyzing Operations on a Manufacturing Line using Geospatial Intelligence T...
 
国際標準化におけるAR/MR用語の使われ方
国際標準化におけるAR/MR用語の使われ方国際標準化におけるAR/MR用語の使われ方
国際標準化におけるAR/MR用語の使われ方
 
XRに基づく遠隔リハの研究・事業事例調査報告
XRに基づく遠隔リハの研究・事業事例調査報告XRに基づく遠隔リハの研究・事業事例調査報告
XRに基づく遠隔リハの研究・事業事例調査報告
 
「遠隔リハビリのための多感覚XR-AI技術基盤構築と保健指導との互恵ケア連携」の概要
「遠隔リハビリのための多感覚XR-AI技術基盤構築と保健指導との互恵ケア連携」の概要「遠隔リハビリのための多感覚XR-AI技術基盤構築と保健指導との互恵ケア連携」の概要
「遠隔リハビリのための多感覚XR-AI技術基盤構築と保健指導との互恵ケア連携」の概要
 
サービス学とか何か(応用サービス工学)
サービス学とか何か(応用サービス工学)サービス学とか何か(応用サービス工学)
サービス学とか何か(応用サービス工学)
 
XR/xDRによる労働生産性の向上、QoW向上
XR/xDRによる労働生産性の向上、QoW向上XR/xDRによる労働生産性の向上、QoW向上
XR/xDRによる労働生産性の向上、QoW向上
 
地理空間インテリジェンス技術を用いた 製造ラインでの作業分析
地理空間インテリジェンス技術を用いた 製造ラインでの作業分析地理空間インテリジェンス技術を用いた 製造ラインでの作業分析
地理空間インテリジェンス技術を用いた 製造ラインでの作業分析
 
Geospatial Intelligence for Health and Productivity Management in Japanese Re...
Geospatial Intelligence for Health and Productivity Management in Japanese Re...Geospatial Intelligence for Health and Productivity Management in Japanese Re...
Geospatial Intelligence for Health and Productivity Management in Japanese Re...
 
製造業・サービス業での人とシステムとの協調
製造業・サービス業での人とシステムとの協調製造業・サービス業での人とシステムとの協調
製造業・サービス業での人とシステムとの協調
 
地理空間インテリジェンス:屋内測位技術を用いた現場のラボ化に基づくサービス研究事例
地理空間インテリジェンス:屋内測位技術を用いた現場のラボ化に基づくサービス研究事例地理空間インテリジェンス:屋内測位技術を用いた現場のラボ化に基づくサービス研究事例
地理空間インテリジェンス:屋内測位技術を用いた現場のラボ化に基づくサービス研究事例
 
Benchmarking of indoor localization and tracking systems (LTSs)
Benchmarking of indoor localization and tracking systems (LTSs)Benchmarking of indoor localization and tracking systems (LTSs)
Benchmarking of indoor localization and tracking systems (LTSs)
 
健康経営のための地理空間インテリジェンス(GSI)に関する一考察
健康経営のための地理空間インテリジェンス(GSI)に関する一考察健康経営のための地理空間インテリジェンス(GSI)に関する一考察
健康経営のための地理空間インテリジェンス(GSI)に関する一考察
 
Communication beyond spatiotemporal constraints
Communication beyond spatiotemporal constraintsCommunication beyond spatiotemporal constraints
Communication beyond spatiotemporal constraints
 
応用サービス工学研究室紹介2020
応用サービス工学研究室紹介2020応用サービス工学研究室紹介2020
応用サービス工学研究室紹介2020
 
OTASCE Map: A Mobile Map Tool with Customizable Audio-Tactile Cues for the Vi...
OTASCE Map: A Mobile Map Tool with Customizable Audio-Tactile Cues for the Vi...OTASCE Map: A Mobile Map Tool with Customizable Audio-Tactile Cues for the Vi...
OTASCE Map: A Mobile Map Tool with Customizable Audio-Tactile Cues for the Vi...
 
PDRと統合測位で製造業の『働き方改革』!
PDRと統合測位で製造業の『働き方改革』!PDRと統合測位で製造業の『働き方改革』!
PDRと統合測位で製造業の『働き方改革』!
 
インドア測位技術の現況:UWBビジネス元年到来?!
インドア測位技術の現況:UWBビジネス元年到来?!インドア測位技術の現況:UWBビジネス元年到来?!
インドア測位技術の現況:UWBビジネス元年到来?!
 
位置合わせや(屋内)測位に関する国際コンペと標準化
位置合わせや(屋内)測位に関する国際コンペと標準化位置合わせや(屋内)測位に関する国際コンペと標準化
位置合わせや(屋内)測位に関する国際コンペと標準化
 

Recently uploaded

Bhosari ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready For ...
Bhosari ( Call Girls ) Pune  6297143586  Hot Model With Sexy Bhabi Ready For ...Bhosari ( Call Girls ) Pune  6297143586  Hot Model With Sexy Bhabi Ready For ...
Bhosari ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready For ...tanu pandey
 
Work-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptxWork-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptxJuliansyahHarahap1
 
Block diagram reduction techniques in control systems.ppt
Block diagram reduction techniques in control systems.pptBlock diagram reduction techniques in control systems.ppt
Block diagram reduction techniques in control systems.pptNANDHAKUMARA10
 
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756dollysharma2066
 
Double Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torqueDouble Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torqueBhangaleSonal
 
Call Girls Walvekar Nagar Call Me 7737669865 Budget Friendly No Advance Booking
Call Girls Walvekar Nagar Call Me 7737669865 Budget Friendly No Advance BookingCall Girls Walvekar Nagar Call Me 7737669865 Budget Friendly No Advance Booking
Call Girls Walvekar Nagar Call Me 7737669865 Budget Friendly No Advance Bookingroncy bisnoi
 
Design For Accessibility: Getting it right from the start
Design For Accessibility: Getting it right from the startDesign For Accessibility: Getting it right from the start
Design For Accessibility: Getting it right from the startQuintin Balsdon
 
data_management_and _data_science_cheat_sheet.pdf
data_management_and _data_science_cheat_sheet.pdfdata_management_and _data_science_cheat_sheet.pdf
data_management_and _data_science_cheat_sheet.pdfJiananWang21
 
chapter 5.pptx: drainage and irrigation engineering
chapter 5.pptx: drainage and irrigation engineeringchapter 5.pptx: drainage and irrigation engineering
chapter 5.pptx: drainage and irrigation engineeringmulugeta48
 
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXssuser89054b
 
Booking open Available Pune Call Girls Pargaon 6297143586 Call Hot Indian Gi...
Booking open Available Pune Call Girls Pargaon  6297143586 Call Hot Indian Gi...Booking open Available Pune Call Girls Pargaon  6297143586 Call Hot Indian Gi...
Booking open Available Pune Call Girls Pargaon 6297143586 Call Hot Indian Gi...Call Girls in Nagpur High Profile
 
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Standamitlee9823
 
Unleashing the Power of the SORA AI lastest leap
Unleashing the Power of the SORA AI lastest leapUnleashing the Power of the SORA AI lastest leap
Unleashing the Power of the SORA AI lastest leapRishantSharmaFr
 
Booking open Available Pune Call Girls Koregaon Park 6297143586 Call Hot Ind...
Booking open Available Pune Call Girls Koregaon Park  6297143586 Call Hot Ind...Booking open Available Pune Call Girls Koregaon Park  6297143586 Call Hot Ind...
Booking open Available Pune Call Girls Koregaon Park 6297143586 Call Hot Ind...Call Girls in Nagpur High Profile
 
Online banking management system project.pdf
Online banking management system project.pdfOnline banking management system project.pdf
Online banking management system project.pdfKamal Acharya
 

Recently uploaded (20)

Bhosari ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready For ...
Bhosari ( Call Girls ) Pune  6297143586  Hot Model With Sexy Bhabi Ready For ...Bhosari ( Call Girls ) Pune  6297143586  Hot Model With Sexy Bhabi Ready For ...
Bhosari ( Call Girls ) Pune 6297143586 Hot Model With Sexy Bhabi Ready For ...
 
Work-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptxWork-Permit-Receiver-in-Saudi-Aramco.pptx
Work-Permit-Receiver-in-Saudi-Aramco.pptx
 
Block diagram reduction techniques in control systems.ppt
Block diagram reduction techniques in control systems.pptBlock diagram reduction techniques in control systems.ppt
Block diagram reduction techniques in control systems.ppt
 
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
FULL ENJOY Call Girls In Mahipalpur Delhi Contact Us 8377877756
 
Double Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torqueDouble Revolving field theory-how the rotor develops torque
Double Revolving field theory-how the rotor develops torque
 
Call Girls Walvekar Nagar Call Me 7737669865 Budget Friendly No Advance Booking
Call Girls Walvekar Nagar Call Me 7737669865 Budget Friendly No Advance BookingCall Girls Walvekar Nagar Call Me 7737669865 Budget Friendly No Advance Booking
Call Girls Walvekar Nagar Call Me 7737669865 Budget Friendly No Advance Booking
 
Design For Accessibility: Getting it right from the start
Design For Accessibility: Getting it right from the startDesign For Accessibility: Getting it right from the start
Design For Accessibility: Getting it right from the start
 
data_management_and _data_science_cheat_sheet.pdf
data_management_and _data_science_cheat_sheet.pdfdata_management_and _data_science_cheat_sheet.pdf
data_management_and _data_science_cheat_sheet.pdf
 
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced LoadsFEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
FEA Based Level 3 Assessment of Deformed Tanks with Fluid Induced Loads
 
chapter 5.pptx: drainage and irrigation engineering
chapter 5.pptx: drainage and irrigation engineeringchapter 5.pptx: drainage and irrigation engineering
chapter 5.pptx: drainage and irrigation engineering
 
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort ServiceCall Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Netaji Nagar, Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
 
(INDIRA) Call Girl Bhosari Call Now 8617697112 Bhosari Escorts 24x7
(INDIRA) Call Girl Bhosari Call Now 8617697112 Bhosari Escorts 24x7(INDIRA) Call Girl Bhosari Call Now 8617697112 Bhosari Escorts 24x7
(INDIRA) Call Girl Bhosari Call Now 8617697112 Bhosari Escorts 24x7
 
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
 
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort ServiceCall Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
Call Girls in Ramesh Nagar Delhi 💯 Call Us 🔝9953056974 🔝 Escort Service
 
Booking open Available Pune Call Girls Pargaon 6297143586 Call Hot Indian Gi...
Booking open Available Pune Call Girls Pargaon  6297143586 Call Hot Indian Gi...Booking open Available Pune Call Girls Pargaon  6297143586 Call Hot Indian Gi...
Booking open Available Pune Call Girls Pargaon 6297143586 Call Hot Indian Gi...
 
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night StandCall Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
Call Girls In Bangalore ☎ 7737669865 🥵 Book Your One night Stand
 
Unleashing the Power of the SORA AI lastest leap
Unleashing the Power of the SORA AI lastest leapUnleashing the Power of the SORA AI lastest leap
Unleashing the Power of the SORA AI lastest leap
 
Booking open Available Pune Call Girls Koregaon Park 6297143586 Call Hot Ind...
Booking open Available Pune Call Girls Koregaon Park  6297143586 Call Hot Ind...Booking open Available Pune Call Girls Koregaon Park  6297143586 Call Hot Ind...
Booking open Available Pune Call Girls Koregaon Park 6297143586 Call Hot Ind...
 
Water Industry Process Automation & Control Monthly - April 2024
Water Industry Process Automation & Control Monthly - April 2024Water Industry Process Automation & Control Monthly - April 2024
Water Industry Process Automation & Control Monthly - April 2024
 
Online banking management system project.pdf
Online banking management system project.pdfOnline banking management system project.pdf
Online banking management system project.pdf
 

Summary of PDR Challenge in Warehouse Picking (IPIN 2017 Competition Track 4)

  • 1. Summary of IPIN 2017 Competition Track4 Track Chairs: Masakatsu Kourogi, Ryosuke Ichikari (AIST) Contributor: Ryo Shimomura (U. of Tsukuba)1 Sponsors
  • 2. Characteristics of Track4 • Competition using data measured in real warehouse – 7 picking workers are measured for about 3 hours – Competitors submit trajectory of workers. • Multiple sources of localization – Senor data for PDR, WMS(warehouse management system) log, map and obstacles information, RSSI of BLE tag • Various actions – Walking / Picking at shelves/ Operating the terminals / Carrying goods using carts • Realistic walking style – free route, forward/side/back step, stop • Data measurement by smartphone 2
  • 3. Data shared for competition 3 P1 P2 P3 Picking log data from WMS Smartphone Sensor data (gyro. ,acceleration, magnetism, air pressure, BLE log) Information about Warehouse (Map, Shelves, Obstacles)
  • 4. Ground Truth: Selected WMS log X Y time1 X Y time2 X Y time3 WMS data X Y time n-2 X Y time n-1 Shared as reference points Used as ground truth X Y time n-3 X Y time0 X Y time 1 X Y time 2 X Y time 3 X Y time 0 X Y time n-2 X Y time n-1 X Y time n X Y time n-3 X Y time n Original Ratio of Reference: Ground Truth ⇒ 1:1(Easy), 1:3 (Hard)
  • 5. Evaluation Metrics Accuracy metrics • Integrated positioning error evaluation (Ed) • PDR error evaluation (Es) Naturalness metrics • Human moving velocity evaluation (Ev) • Update frequency evaluation (Ef) Warehouse-dedicated metric • Obstacle interference evaluation (Eo) • Picking work evaluation (Ep) 5
  • 6. Integrated positioning error (Ed) 6 Score function • Median of all positional errors at evaluation points (points with ground truth)
  • 7. PDR error evaluation (Es) • Error metrics for accumulation error. • Error accumulation can be evaluated by the slope of regression line [Abe et al. IPIN2016] 7 Close to Reference points Far from Reference points
  • 8. Score function of PDR error 8
  • 9. Picking work evaluation (Ep) • Metric for naturalness of trajectory around picking points • Checks movements around picking (+/-1.5 sec.) 9 Pi: Number of times of picking whose movement distance bellow 1m Pmax : Number of all true positions.
  • 10. Human moving velocity evaluation (Ev) • Metric for naturalness of moving velocity • Checks velocity compared to threshold [1.5m/s]. 10 vi: Number of times that it is determined to be a human moving velocity*.vmax: Number between all trajectory positions.
  • 11. Obstacle interference evaluation (Eo) • Metric for obstacle interference of trajectory • Checks how many pixels of trajectory (not only submitted points) are in the obstacles area 11 oi: Pixels of trajectory without obstacle interference*. omax: Total pixels of trajectory.
  • 12. Update frequency evaluation (Ef) • Frequency of trajectories are expected to more than 1Hz. 12 fi: The number of frames whose updated frequency is more than 1[Hz] fmax: The total number of frames of trajectory.
  • 13. Comprehensive evaluation (C.E.) • Integrated positioning error evaluation (Ed) • PDR error evaluation (Es) • Picking work evaluation (Ep) • Human moving velocity evaluation (Ev) • Obstacle interference evaluation (Eo) • Update frequency evaluation (Ef) 13
  • 14. Our competitiors Team 1 (ETRI) A Multi-Sensor Fusion Technique for Pedestrian Localization in a Warehouse Youngjae Lee, Haemin Lee, Jinhong Kim, Dongyeop, Kang, Kiyoung Moon (ETRI, Korea), Seong Yun Cho (Kyeongil University, Korea) Team 2 (KDDI) No PDR, No future Yoshihiro Ito, Hisashi Hoshi (KDDI R&D Laboratories Inc., Japan) Team 3 (XMU) A Smartphone Based Indoor Positioning System Lingxiang Zheng, Yizhen Wang, Ao Peng, Zhenyang Wu, Dihong Wu, Biyu Tang, Hai Lu, Haibin Shi ( Xiamen University, China), Huiru Zheng (University of Ulster, Ireland) Team 4 (Nagoya) Trajectory Estimation Using PDR and Simulation of Human-Like Movement Kotaro Hananouchi, Junto Nozaki, Kenta Urano, Kei Hiroi, Nobuo Kawaguchi (Nagoya University, Japan) Team 5 (YZU) Moving Trajectory Estimation Based on Sensors Ho-Ti Cheng, Wen-Chen Lu, Chia-Min Lin, Yu-Shen Lai, Yun-Yeh, Huan-Wei Liu, Shih- Hau Fang (Yuan Ze University, Taiwan) Ying-Ren Chien (National Ilan University, Taiwan), Yu Tsao (Academia Sinica, Taiwan) 14
  • 31. Scores for Terminal 2 31 Team Level Ed Es Ep Ev Eo Ef Error median C.E. ETRI Easy 66.875 96.028 100 99.995 46.375 17.335 10.606 68.22 6 KDDI Easy 72.558 99.367 34.783 100 100 100 8.958 91.12 4 Nagoya Easy 73.333 100 81.818 94.132 95.581 99.201 8.733 91.47 2 XMU Easy 81.970 99.419 81.818 97.177 70.970 99.995 6.229 86.23 6 YZU Easy 77.841 99.007 100 99.167 65.816 100 7.426 84.99 0
  • 32. Scores for Terminal 3 32 Team Level Ed Es Ep Ev Eo Ef Error median C.E. ETRI Hard 67.895 97.096 97.531 99.997 23.072 3.736 10.310 60.170 KDDI Hard 64.811 97.926 53.086 100 100 100 11.205 90.202 Nagoya Hard 68.639 100 77.215 79.382 94.470 98.345 10.095 87.671 XMU Hard 84.049 98.811 82.927 97.172 71.450 99.992 5.626 86.728 YZU Hard 79.346 98.196 97.436 99.197 44.607 100 6.990 78.642
  • 33. Score for Terminal 4 33 Team Level Ed Es Ep Ev Eo Ef Error median C.E. ETRI Easy 72.763 93.155 91.892 99.999 45.523 18.338 8.899 68.268 KDDI Easy 72.078 96.349 35.135 100 99.944 100 9.097 90.425 Nagoya Easy 61.929 98.569 63.888 76.866 89.704 99.144 12.041 83.650 XMU Easy 78.043 95.052 89.189 95.526 69.168 99.992 7.368 84.157 YZU Easy 62.918 93.986 100 98.922 61.038 100 11.754 79.531
  • 34. Scores for Terminal 5 34 Team Level Ed Es Ep Ev Eo Ef Error median C.E. ETRI Easy 60.493 99.915 96.551 100 80.028 15.257 12.457 77.444 KDDI Easy 66.197 99.712 41.379 100 99.187 100 10.803 90.007 Nagoya Easy 61.564 99.417 65.517 93.544 94.464 99.770 12.146 87.820 XMU Easy 82.752 100 66.666 94.697 67.671 97.701 6.002 84.160 YZU Easy 70.976 99.786 89.655 99.662 31.440 100 9.417 73.016
  • 35. Scores for Terminal 6 35 Team Level Ed Es Ep Ev Eo Ef Error median C.E. ETRI Easy 59.002 95.525 100 100 64.104 1.951 12.889 70.332 KDDI Easy 85.239 100 44 100 100 100 5.281 94.248 Nagoya Easy 72.843 97.139 61.905 86.017 94.006 99.389 8.876 88.135 XMU Easy 81.450 99.399 92 95.164 46.881 99.638 6.379 79.072 YZU Easy 78.335 99.187 100 98.492 35.990 100 7.283 76.075
  • 36. Scores for Terminal 7 36 Team Level Ed Es Ep Ev Eo Ef Error median C.E. ETRI Hard - - - - - - - - KDDI Hard 73.622 97.054 56.881 100 100 100 8.650 91.979 Nagoya Hard 73.903 99.276 82.569 92.002 93.027 99.499 8.568 90.423 XMU Hard 41.548 92.034 92.157 94.728 43.730 97.713 17.951 68.424 YZU Hard 75.627 96.245 99.083 98.917 42.906 100 8.068 77.038
  • 37. Scores for Terminal 8 37 Team Level Ed Es Ep Ev Eo Ef Error median C.E. ETRI Hard - - - - - - - - KDDI Hard 71.963 95.375 39.552 100 100 100 9.131 90.445 Nagoya Hard 81.768 100 76.119 92.901 93.593 99.548 6.287 92.127 XMU Hard 23.646 87.706 90 95.133 47.490 99.641 23.143 65.252 YZU Hard 82.347 97.746 96.212 99.292 36.909 100 6.119 76.796
  • 39. Prize • 1) PDR module (Sugihara SEI Co. &Lt., 200,000 JPY worth) + 100,000 JPY or • 2) 150,000 JPY 39
  • 40. Final Score RANKING TEAM AVERAGE OF C.E. Winner(1st) KDDI 91.163 Runner-up(2nd) Nagoya U. 88.921 3rd XMU 78.437 40
  • 41. Ave. Scores for ALL Terminals 41 Team Ed Es Ep Ev Eo Ef Error median C.E. ETRI 65.406 96.344 97.195 99.998 51.821 11.323 11.032 65.741 KDDI 72.353 97.969 43.545 100 99.876 100 9.018 91.163 Nagoya 70.569 99.200 72.719 87.835 93.549 99.271 9.535 88.921 XMU 67.637 96.060 84.965 95.657 59.623 99.239 10.385 78.437 YZU 75.341 97.736 97.484 99.093 45.530 100 8.151 77.947
  • 43. Graph of Es(1st) 43 Terminal ID slop Terminal2 0.06234699249 81115 Terminal3 0.090435326 4159421 Terminal4 0.121188344 408936 Terminal5 0.055607695 6764035 Terminal6 0.048479055 3534408 Terminal7 0.107438470 408959 Terminal8 0.140182398 620238 y = 0.0623x 0 5 10 15 20 25 30 0 50 100 150 200 250 300 350 400 450 positionerror time KDDI Terminal2
  • 46. Graph of Es(2nd) 46 y = 0.0484x 0 10 20 30 40 50 60 70 0 100 200 300 400 500 600 positionerror time Nagoya Terminal2 Terminal ID slop Terminal2 0.04842440929 53409 Terminal3 0.038564395 4126861 Terminal4 0.077903625 1886814 Terminal5 0.061358972 1000901 Terminal6 0.105793910 255521 Terminal7 0.064109388 7045351 Terminal8 0.039750897 7779014
  • 48. Thank you for participation 48

Editor's Notes

  1. score c.e.