System and method for detecting, tracking and counting human objects of interest with an improved height calculation
Techniques for evaluating height data are disclosed herein. Height values for a tracked object are obtained over a specified period of time. Clusters including at least one of the height values are generated. The cluster having the largest amount of height values is identified. A height of the tracked object is estimated from the identified cluster.
1. A computer-implemented method for evaluating height data, the method comprising:
obtaining multiple height maps, wherein each height map of the multiple height maps corresponds to an image of a scene including an object over a specified duration;
detecting, in each height map of the multiple height maps, a blob corresponding to an object;
obtaining, by execution of one or more processors and from the multiple height maps, a plurality of height values for the object, wherein each height value of the plurality of height values corresponds to the height value of the blob tracked in one of the multiple height maps;
generating, from the plurality of height values, a plurality of clusters by height value, each cluster including at least one of the plurality of height values, at least one cluster including a plurality of height values;
identifying one of the plurality of clusters having a largest amount of the plurality of height values relative to one or more remaining clusters of the plurality of clusters; and
estimating a height of the object from the identified one of the plurality of clusters.
2. The computer-implemented method of claim 1 , further comprising:
determining whether the estimated height of the tracked object exceeds a specified threshold.
3. The computer-implemented method of claim 2 , further comprising:
upon determining that the estimated height of the object exceeds a specified threshold, classifying the object as an adult individual.
4. The computer-implemented method of claim 2 , further comprising:
upon determining that the estimated height of the object does not exceed a specified threshold, classifying the object as a child individual.
5. The computer-implemented method of claim 1 , wherein estimating the height of the object comprises calculating a mean height value of a portion of the plurality of height values that are included in the identified one of the plurality of clusters.
6. The computer-implemented method of claim 1 , wherein the object corresponds to an individual, and further comprising:
detecting the individual entering a predefined area;
capturing, via one or more sensors, a plurality of images of the individual; and
for each image, generating an associated height map of the multiple height maps and identifying local maxima.
7. The computer-implemented method of claim 1 , wherein generating the plurality of clusters comprises applying a k-means clustering algorithm to the plurality of height values of the object.
8. The computer-implemented method of claim 7 , further comprising:
iterating the k-means clustering algorithm until each of the plurality of clusters is stable.
9. The computer-implemented method of claim 1 , wherein generating the plurality of clusters comprises applying a k-means clustering algorithm to the plurality of height values of the object to create three clusters, the three clusters corresponding to the plurality of clusters.
10. A system comprising:
one or more processors; and
a memory storing program code, which, when executed on the one or more processors, causes the system to:
obtain multiple height maps, wherein each height map of the multiple height maps corresponds to an image of a scene including an object over a specified duration;
detect, in each height map of the multiple height maps, a blob corresponding to an object;
obtain, from the multiple height maps, a plurality of height values for the object, wherein each height value of the plurality of height values corresponds to the height value of the blob tracked in one of the multiple height maps;
generate, from the plurality of height values, a plurality of clusters by height value, each cluster including at least one of the plurality of height values, at least one cluster including a plurality of height values;
identify one of the plurality of clusters having a largest amount of the plurality of height values relative to one or more remaining clusters of the plurality of clusters; and
estimate a height of the object from the identified one of the plurality of clusters.
11. The system of claim 10 , wherein the program code further causes the system to:
determine whether the estimated height of the object exceeds a specified threshold.
12. The system of claim 11 , wherein the program code further causes the system to, upon a determination that the estimated height of the tracked object exceeds a specified threshold:
classify the object as an adult individual.
13. The system of claim 11 , wherein the program code further causes the system to, upon a determination that the estimated height of the object does not exceed a specified threshold:
classify the object as a child individual.
14. The system of claim 10 , wherein the program code causes the system to estimate the height of the object at least in part by calculating a mean height value of the identified one of the plurality of clusters.
15. The system of claim 10 , wherein the program code causes the system to generate the plurality of clusters at least in part by applying a k-means clustering algorithm to the plurality of height values of the object to create three clusters, the three clusters corresponding to the plurality of clusters.