Gait Based Identification Of Individuals Using Multiple Skeleton Recording Devices

Tata Consultancy Services Limited
Granted App No 3837/MUM/2013 Patent 381842 Computer Science

Patent information

IP India · live record
Application number
3837/MUM/2013
Filing date
06 December 2013
Status
Granted
Legal status
Inforce
Publication number
31/2015
Publication type
INA
Invention field
Computer Science
Patent number
381842
Grant date
15 November 2021
Next renewal due
06 December 2026

Abstract

A system and a method for monitoring motion skeleton recording devices (104) is described. The method includes detecting, by a processor (110) of a monitoring system (102), at least one human skeleton in a field of view (FOV) of the first skeleton recording device (104). Based on the detection, a message is transmitted to rest of the plurality of skeleton recording devices (104) to switch ON and OFF corresponding infrared (IR) sensors in a round robin manner. The method further includes identifying one or more second skeleton recording device (104) based on a direction of traversal of the at least one human skeleton from the FOV of the first skeleton recording device (104) to a FOV of the one or more second skeleton recording devices (104). Based on the identification, the one or more second skeleton recording devices (104) are notified to activate the corresponding IR sensor.

Applicants

1
India
TATA CONSULTANCY SERVICES LIMITED Nirmal Building, 9th Floor, Nariman Point, Mumbai, Maharashtra 400021

Inventors

3
India
BANERJEE, RohanTata Consultancy Services Building 1B,Ecospace Plot - IIF/12, New Town, Rajarhat, Kolkata-700156 West Bengal
India
SINHA, AniruddhaTata Consultancy Services Building 1B,Ecospace Plot-IIF/12, New Town, Rajarhat, Kolkata-700156 West Bengal
India
CHAKRAVARTY, KingshukTata Consultancy Services Building 1B,Ecospace Plot - IIF/12, New Town, Rajarhat, Kolkata-700156 West Bengal

Claims

15
1 A method for monitoring motion using a plurality of skeleton recording devices (104), the method comprising: detecting, by a processor (110) of a monitoring system (102), at least one human skeleton in a field of view (FOV) of a first skeleton recording device (104) from the plurality of skeleton recording devices (104), wherein each of the plurality of skeleton recording devices (104) is connected with a separate monitoring device (102); based on the detection, transmitting, by the processor (110), a message to rest of the plurality of skeleton recording devices (104) to switch ON and OFF corresponding infrared (IR) sensors in a round robin manner; identifying, by the processor (110), one or more second skeleton recording devices (104) based on a direction of traversal of the at least one human skeleton from the FOV of the first skeleton recording device (104) to a FOV of the one or more second skeleton recording devices (104); and based on the identification, notifying, by the processor (110), the one or more second skeleton recording device (104) to activate the corresponding IR sensors.
2 The method as claimed in claim 1 further comprising: extracting, by the processor (110), the skeleton data tracked by the first skeleton recording device (104); and compressing, by the processor (110), the skeleton data of the skeleton recording device (104), wherein the compressed skeleton data is analyzed for identification of individuals.
3 The method as claimed in claim 2 further comprising transmitting, by the processor (110), the compressed skeleton data to a backend server (108), wherein the identification of individuals is performed at the backend server (108).
4 The method as claimed in claim 2, wherein the identification of individuals is performed at the monitoring system (102).
5 The method as claimed in claim 2, wherein the skeleton data is compressed by a lossy compression technique, wherein the lossy compression technique preserves statistical properties of the skeleton data for performing people identification with pre-defined accuracy.
6 The method as claimed in claim 5, wherein the lossy compression technique comprises performing Discrete Chebyshev Transform (DCT) on the skeleton data.
7 The method as claimed in claim 2, wherein the identification of individuals comprises: retrieving three dimensional (3D) skeleton joint coordinates from the skeleton data; aggregating the 3D skeleton joint coordinates in accordance with timestamps in time interleaving mode for obtaining a natural walking pattern of an individual; extracting a plurality of gait features of the individual, for each of the one or more gait cycles, from the 3D skeleton joint coordinates on the skeleton data; and identifying the individual based on the plurality of gait features.
8 The method as claimed in claim 1, wherein each of the plurality of skeleton recording devices (104) is associated with a weight based on a probability of detection of the at least one human skeleton by each of the plurality of skeleton recording devices (104).
9 The method as claimed in claim 8, wherein each of the plurality of skeleton recording devices (104) remain active for a pre-defined time period in absence of the detection of the at least one human skeleton, and wherein the time period is defined in accordance to the weight assigned to each of the plurality of skeleton recording devices (104).
10 The method as claimed in claim 1, wherein the tracking of the at least one human skeleton is performed by a Kalman filter technique.
11 A monitoring system (102) comprising: a processor (110); an activation module (120), coupled to the processor (110), to, detect presence of at least one human skeleton in a field of view (FOV) of a first skeleton recording device (104) from a plurality of skeleton recording devices (104); and a tracking module (122), coupled to the processor (110), track the at least one human skeleton within the FOV of the first skeleton recording device (104), wherein the tracking includes determining a direction of traversal of the at least one human skeleton and extracting skeleton data from the at least one human skeleton; and based on the determination, notify one or more skeleton recording devices (104) of the rest of the plurality of skeleton recording devices (104) to monitor the at least one human skeleton.
12 The monitoring system (102) as claimed in claim 11 further comprising a compression module (124), coupled to the processor (110), to, compress the skeleton data by utilizing a lossy compression technique; transmit the compressed data to a backend server (108) for identification of individuals.
13 The monitoring system (102) as claimed in claim 11, wherein the activation module (120) further transmits a notification to rest of the plurality of skeleton recording devices (104) to switch ON and OFF corresponding infrared (IR) sensors in a round robin manner.
14 The monitoring system (102) as claimed in claim 11, wherein each of the plurality of skeleton recording devices (104) remain active for a pre-defined time period in absence of the detection of the at least one human skeleton, and wherein the time period is defined in accordance to the weight assigned to each of the plurality of skeleton recording devices (104).
15 A non-transitory computer-readable medium having embodied thereon a computer program for executing a method comprising: detecting, by a sensor of a first skeleton recording device (104), at least one human skeleton in a field of view (FOV) of the first skeleton recording device (104), wherein based on the detection, a message is transmitted to rest of the plurality of skeleton recording devices (104) to switch ON and OFF corresponding infrared (IR) sensors in a round robin manner; extracting, by the processor (110), skeleton data pertaining to the at least one human skeleton tracked by the first skeleton recording device (104), wherein the skeleton data is extracted by the sensor of the skeleton recording device (104); identifying, by the processor (110), one or more second skeleton recording devices (104) based on a direction of traversal of the at least one human skeleton from the FOV of the first skeleton recording device (104) to a FOV of the one or more second skeleton recording devices (104); and based on the identification, notifying, by the processor (110), the one or more second skeleton recording devices (104) for monitoring the at least one human skeleton.

Specification

Show full textCollapse

DESC:MONITORING MOTION USING SKELETON RECORDING DEVICES ,CLAIMS:1. A method for monitoring motion using a plurality of skeleton recording devices (104), the method comprising: detecting, by a processor (110) of a monitoring system (102), at least one human skeleton in a field of view (FOV) of a first skeleton recording device (104) from the plurality of skeleton recording devices (104), wherein each of the plurality of skeleton recording devices (104) is connected with a separate monitoring device (102); based on the detection, transmitting, by the processor (110), a message to rest of the plurality of skeleton recording devices (104) to switch ON and OFF corresponding infrared (IR) sensors in a round robin manner; identifying, by the processor (110), one or more second skeleton recording devices (104) based on a direction of traversal of the at least one human skeleton from the FOV of the first skeleton recording device (104) to a FOV of the one or more second skeleton recording devices (104); and based on the identification, notifying, by the processor (110), the one or more second skeleton recording device (104) to activate the corresponding IR sensors. 2. The method as claimed in claim 1 further comprising: extracting, by the processor (110), the skeleton data tracked by the first skeleton recording device (104); and compressing, by the processor (110), the skeleton data of the skeleton recording device (104), wherein the compressed skeleton data is analyzed for identification of individuals. 3. The method as claimed in claim 2 further comprising transmitting, by the processor (110), the compressed skeleton data to a backend server (108), wherein the identification of individuals is performed at the backend server (108). 4. The method as claimed in claim 2, wherein the identification of individuals is performed at the monitoring system (102). 5. The method as claimed in claim 2, wherein the skeleton data is compressed by a lossy compression technique, wherein the lossy compression technique preserves statistical properties of the skeleton data for performing people identification with pre-defined accuracy. 6. The method as claimed in claim 5, wherein the lossy compression technique comprises performing Discrete Chebyshev Transform (DCT) on the skeleton data. 7. The method as claimed in claim 2, wherein the identification of individuals comprises: retrieving three dimensional (3D) skeleton joint coordinates from the skeleton data; aggregating the 3D skeleton joint coordinates in accordance with timestamps in time interleaving mode for obtaining a natural walking pattern of an individual; extracting a plurality of gait features of the individual, for each of the one or more gait cycles, from the 3D skeleton joint coordinates on the skeleton data; and identifying the individual based on the plurality of gait features. 8. The method as claimed in claim 1, wherein each of the plurality of skeleton recording devices (104) is associated with a weight based on a probability of detection of the at least one human skeleton by each of the plurality of skeleton recording devices (104). 9. The method as claimed in claim 8, wherein each of the plurality of skeleton recording devices (104) remain active for a pre-defined time period in absence of the detection of the at least one human skeleton, and wherein the time period is defined in accordance to the weight assigned to each of the plurality of skeleton recording devices (104). 10. The method as claimed in claim 1, wherein the tracking of the at least one human skeleton is performed by a Kalman filter technique. 11. A monitoring system (102) comprising: a processor (110); an activation module (120), coupled to the processor (110), to, detect presence of at least one human skeleton in a field of view (FOV) of a first skeleton recording device (104) from a plurality of skeleton recording devices (104); and a tracking module (122), coupled to the processor (110), track the at least one human skeleton within the FOV of the first skeleton recording device (104), wherein the tracking includes determining a direction of traversal of the at least one human skeleton and extracting skeleton data from the at least one human skeleton; and based on the determination, notify one or more skeleton recording devices (104) of the rest of the plurality of skeleton recording devices (104) to monitor the at least one human skeleton. 12. The monitoring system (102) as claimed in claim 11 further comprising a compression module (124), coupled to the processor (110), to, compress the skeleton data by utilizing a lossy compression technique; transmit the compressed data to a backend server (108) for identification of individuals. 13. The monitoring system (102) as claimed in claim 11, wherein the activation module (120) further transmits a notification to rest of the plurality of skeleton recording devices (104) to switch ON and OFF corresponding infrared (IR) sensors in a round robin manner. 14. The monitoring system (102) as claimed in claim 11, wherein each of the plurality of skeleton recording devices (104) remain active for a pre-defined time period in absence of the detection of the at least one human skeleton, and wherein the time period is defined in accordance to the weight assigned to each of the plurality of skeleton recording devices (104). 15. A non-transitory computer-readable medium having embodied thereon a computer program for executing a method comprising: detecting, by a sensor of a first skeleton recording device (104), at least one human skeleton in a field of view (FOV) of the first skeleton recording device (104), wherein based on the detection, a message is transmitted to rest of the plurality of skeleton recording devices (104) to switch ON and OFF corresponding infrared (IR) sensors in a round robin manner; extracting, by the processor (110), skeleton data pertaining to the at least one human skeleton tracked by the first skeleton recording device (104), wherein the skeleton data is extracted by the sensor of the skeleton recording device (104); identifying, by the processor (110), one or more second skeleton recording devices (104) based on a direction of traversal of the at least one human skeleton from the FOV of the first skeleton recording device (104) to a FOV of the one or more second skeleton recording devices (104); and based on the identification, notifying, by the processor (110), the one or more second skeleton recording devices (104) for monitoring the at least one human skeleton.

Documents

Sign in to open
Orders
Section
Application documents
1 3837-MUM-2013-Request For Certified Copy-Online(11-09-2014).pdf 11 Sep 2014
2 SPEC.pdf 11 Aug 2018
3 SPEC FOR E-FILING.pdf 11 Aug 2018
4 PD011533IN-SC_Request for Priority Documents-PCT.pdf 11 Aug 2018
5 Form-2(Online).pdf 11 Aug 2018
6 Form-18(Online).pdf 11 Aug 2018
7 FORM 3.pdf 11 Aug 2018
8 FIGURES in.pdf 11 Aug 2018
9 FIG IN.pdf 11 Aug 2018
10 ABSTRACT1.jpg 11 Aug 2018
11 3837-MUM-2013-FORM 5(25-6-2014).pdf 11 Aug 2018
12 3837-MUM-2013-FORM 5(22-5-2014).pdf 11 Aug 2018
13 3837-MUM-2013-FORM 26(11-3-2014).pdf 11 Aug 2018
14 3837-MUM-2013-FORM 1(7-4-2014).pdf 11 Aug 2018
15 3837-MUM-2013-CORRESPONDENCE(7-4-2014).pdf 11 Aug 2018
16 3837-MUM-2013-CORRESPONDENCE(25-6-2014).pdf 11 Aug 2018
17 3837-MUM-2013-CORRESPONDENCE(22-5-2014).pdf 11 Aug 2018
18 3837-MUM-2013-CORRESPONDENCE(11-3-2014).pdf 11 Aug 2018
19 3837-MUM-2013-FER.pdf 31 May 2019
20 3837-MUM-2013-FORM 3 [06-11-2019(online)].pdf 06 Nov 2019
21 3837-MUM-2013-OTHERS [27-11-2019(online)].pdf 27 Nov 2019
22 3837-MUM-2013-FER_SER_REPLY [27-11-2019(online)].pdf 27 Nov 2019
23 3837-MUM-2013-COMPLETE SPECIFICATION [27-11-2019(online)].pdf 27 Nov 2019
24 3837-MUM-2013-CLAIMS [27-11-2019(online)].pdf 27 Nov 2019
25 3837-MUM-2013-Correspondence to notify the Controller [10-08-2021(online)].pdf 10 Aug 2021
26 3837-MUM-2013-FORM-26 [01-09-2021(online)].pdf 01 Sep 2021
27 3837-MUM-2013-Written submissions and relevant documents [17-09-2021(online)].pdf 17 Sep 2021
28 3837-MUM-2013-PETITION UNDER RULE 137 [17-09-2021(online)].pdf 17 Sep 2021
29 3837-MUM-2013-Response to office action [22-09-2021(online)].pdf 22 Sep 2021
30 3837-MUM-2013-US(14)-HearingNotice-(HearingDate-03-09-2021).pdf 03 Oct 2021
31 3837-MUM-2013-PatentCertificate15-11-2021.pdf 15 Nov 2021
32 3837-MUM-2013-IntimationOfGrant15-11-2021.pdf 15 Nov 2021
33 3837-MUM-2013-RELEVANT DOCUMENTS [26-09-2023(online)].pdf 26 Sep 2023
Search strategy
13837mum2013_02-05-2019.pdf

ERegister / renewals

Inforce
3rd Renewed 23 Nov 2021 Period 06 Dec 2015 – 06 Dec 2016 · CBR 26853 · Certificate 31740 ₹4,000
4th Renewed 23 Nov 2021 Period 06 Dec 2016 – 06 Dec 2017 · CBR 26853 · Certificate 31741 ₹4,000
5th Renewed 23 Nov 2021 Period 06 Dec 2017 – 06 Dec 2018 · CBR 26853 · Certificate 31742 ₹4,000
6th Renewed 23 Nov 2021 Period 06 Dec 2018 – 06 Dec 2019 · CBR 26853 · Certificate 31743 ₹4,000
7th Renewed 23 Nov 2021 Period 06 Dec 2019 – 06 Dec 2020 · CBR 26853 · Certificate 31744 ₹12,000
8th Renewed 23 Nov 2021 Period 06 Dec 2020 – 06 Dec 2021 · CBR 26853 · Certificate 31745 ₹12,000
9th Renewed 23 Nov 2021 Period 06 Dec 2021 – 06 Dec 2022 · CBR 26853 · Certificate 31746 ₹12,000
10th Renewed 01 Dec 2022 Period 06 Dec 2022 – 06 Dec 2023 · CBR 31642 · Certificate 34393 ₹12,000
11th Renewed 01 Dec 2023 Period 06 Dec 2023 – 06 Dec 2024 · CBR 48160 · Certificate 51812 ₹24,000
12th Renewed 04 Dec 2024 Period 06 Dec 2024 – 06 Dec 2025 · CBR 55153 · Certificate 95797 ₹24,000
13th Renewed 01 Dec 2025 Period 06 Dec 2025 – 06 Dec 2026 · CBR 48551 · Certificate 44772 ₹24,000