Method and system to track and monitor human using an array of radars
This disclosure relates generally to method and system to track and monitor human using an array of radars. Human tracking is necessarily important in security, especially with the growth of threats and incidents. Conventional systems and method lack in tracking target subject being authenticated to move around the monitoring environment. The present invention provides a method of detect human continually based on radar signals from an array of radars to track the presence of one or more target subjects associated within the monitoring environment. Further, a height surface plot of each target subject present in a radar range is constructed for identification. Then, each target subject present in the radar range of the monitoring environment based on mapping the height surface plot with a predefined height map. The characteristics of each target subject helps in detecting the target subject accurately.
1. A processor implemented method to track and monitor target subject using an array of radars, the method comprising:
receiving, via one or more hardware processors, a radar signal from an array of radars configured to a monitoring environment, wherein the radar signal continually tracks the presence of one or more target subjects associated within the monitoring environment
authenticating each target subject present in the monitoring environment, via the one or more hardware processors, based on comparing a device ID associated with each target subject with a list of preregistered subject's device IDs;
constructing, via the one or more hardware processors, a height surface plot of each target subject present in a radar range for identification based on (i) the authenticated device ID of each target subject, and a 3D cloud point of the radar signal exhibiting the monitoring environment;
recognizing, via the one or more hardware processors, each target subject present in the radar range of the monitoring environment based on mapping the height surface plot with a predefined height map associated with the data source; and
tracking, via the one or more hardware processors, each target subject present in the radar range of the monitoring environment based on a closest mapped height surface plot and the device ID of each target subject.
2. The method as claimed in claim 1 , constructing the height surface plot of each target subject present in the radar range by,
plotting, the 3D point cloud comprising three co-ordinates (X,Y,Z) with the surface height of each target subject present within the radar range obtained from the radar signal, wherein the surface height of each target subject is computed using the Z coordinate;
forming, a plurality of grids for the 3D point cloud to obtain a field of view (FOV) of the moving target subject within its present radar range in the monitoring environment;
removing, outliers detected from the plurality of grids based on a threshold computed using a mean and a standard deviation, wherein the outliers are detected from each grid using a distance-based k nearest neighbor outlier detection technique; and
performing, interpolation to fill missing spots in the FOV to smoothen height surface plots at a predefined granularity to construct the height surface plot.
3. The method as claimed in claim 2 , wherein each grid of the 3D point cloud is formed by segmenting the monitoring environment into the plurality of grids having concentric circular area with a pre-defined area and a width, and wherein the plurality of grids are divided into patches.
4. The method as claimed in claim 2 , wherein the threshold is the sum of mean and the standard deviation with corresponding neighbors distant average of grids.
5. The method as claimed in claim 1 , wherein the height surface plot of each target subject is mapped based on the closest match with the height map having spatial distribution of height points over X and Y coordinates using standard classifiers.
6. The method as claimed in claim 1 , wherein the height surface plot represents target subjects' motion observed in the radar range of the monitoring environment.
7. The method as claimed in claim 1 , wherein a time spent by each target subject in the radar range of the monitoring environment is computed using the height surface plot and the device ID of corresponding target subject.
8. A system to track and monitor target subject using an array of radars comprises:
a memory ( 102 ) storing instructions;
one or more communication interfaces ( 106 ); and
one or more hardware processors ( 104 ) coupled to the memory ( 102 ) via the one or more communication interfaces ( 106 ), wherein the one or more hardware processors ( 104 ) are configured by the instructions to:
receive, a radar signal from an array of radars configured to a monitoring environment, wherein the radar signal continually tracks the presence of one or more target subjects associated within the monitoring environment;
authenticate, each target subject present in the monitoring environment, based on comparing a device ID associated with each target subject with a list of preregistered subject's device IDs;
construct, a height surface plot of each target subject present in a radar range for identification based on (i) the authenticated device ID of each target subject, and a 3D cloud point of the radar signal exhibiting the monitoring environment;
recognize, each target subject present in the radar range of the monitoring environment based on mapping the height surface plot with a predefined height map associated with the data source; and
track, each target subject present in the radar range of the monitoring environment based on a closest mapped height surface plot and the device ID of each target subject.
9. The system as claimed in claim 8 , constructing the height surface plot of each target subject present in the radar range by,
plotting, the 3D point cloud comprising three co-ordinates (X,Y,Z) with the surface height of each target subject present within the radar range obtained from the radar signal, wherein the surface height of each target subject is computed using the Z coordinate;
forming, a plurality of grids for the 3D point cloud to obtain a field of view (FOV) of the moving target subject within its present radar range in the monitoring environment;
removing, outliers detected from the plurality of grids based on a threshold computed using a mean and a standard deviation, wherein the outliers are detected from each grid using a distance based k nearest neighbor outlier detection technique; and
performing, interpolation to fill missing spots in the FOV to smoothen height surface plots at a predefined granularity to construct the height surface plot.
10. The system as claimed in claim 9 , wherein each grid of the 3D point cloud is formed by segmenting the monitoring environment into the plurality of grids having concentric circular area with a pre-defined area and a width, and wherein the plurality of grids are divided into patches.
11. The system as claimed in claim 9 , wherein the threshold is the sum of mean and the standard deviation with corresponding neighbors distant average of grids.
12. The system as claimed in claim 8 , wherein the height surface plot of each target subject is mapped based on the closest match with the height map having spatial distribution of height points over X and Y coordinates using standard classifiers.
13. The system as claimed in claim 8 , wherein the height surface plot represents target subjects' motion observed in the radar range of the monitoring environment.
14. The system as claimed in claim 8 , wherein a time spent by each target subject in the radar range of the monitoring environment is computed using the height surface plot and the device ID of corresponding target subject.
15. One or more non-transitory machine-readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors perform actions comprising:
receiving, a radar signal from an array of radars configured to a monitoring environment, wherein the radar signal continually tracks the presence of one or more target subjects associated within the monitoring environment
authenticating, each target subject present in the monitoring environment, based on comparing a device ID associated with each target subject with a list of preregistered subject's device IDs;
constructing, a height surface plot of each target subject present in a radar range for identification based on (i) the authenticated device ID of each target subject, and a 3D cloud point of the radar signal exhibiting the monitoring environment;
recognizing, each target subject present in the radar range of the monitoring environment based on mapping the height surface plot with a predefined height map associated with the data source; and
tracking, each target subject present in the radar range of the monitoring environment based on a closest mapped height surface plot and the device ID of each target subject.
16. The one or more non-transitory machine-readable information storage mediums of claim method as claimed in claim 15 , constructing the height surface plot of each target subject present in the radar range by,
plotting, the 3D point cloud comprising three co-ordinates (X,Y,Z) with the surface height of each target subject present within the radar range obtained from the radar signal, wherein the surface height of each target subject is computed using the Z coordinate;
forming, a plurality of grids for the 3D point cloud to obtain a field of view (FOV) of the moving target subject within its present radar range in the monitoring environment;
removing, outliers detected from the plurality of grids based on a threshold computed using a mean and a standard deviation, wherein the outliers are detected from each grid using a distance-based k nearest neighbor outlier detection technique; and
performing, interpolation to fill missing spots in the FOV to smoothen height surface plots at a predefined granularity to construct the height surface plot.
17. The one or more non-transitory machine-readable information storage mediums of claim 16 , wherein each grid of the 3D point cloud is formed by segmenting the monitoring environment into the plurality of grids having concentric circular area with a pre-defined area and a width, and wherein the plurality of grids are divided into patches.
18. The one or more non-transitory machine-readable information storage mediums of claim 16 , wherein the threshold is the sum of mean and the standard deviation with corresponding neighbors distant average of grids.
19. The one or more non-transitory machine-readable information storage mediums of claim 15 , wherein the height surface plot of each target subject is mapped based on the closest match with the height map having spatial distribution of height points over X and Y coordinates using standard classifiers.
20. The one or more non-transitory machine-readable information storage mediums of claim 15 , wherein a time spent by each target subject in the radar range of the monitoring environment is computed using the height surface plot and the device ID of corresponding target subject.