Movement monitoring system
A monitoring system or tracking system may include an input port and a controller in communication with the input port. The input port may receive video from an image capturing device. The image capturing device is optionally part of the monitoring system and in some cases includes at least part of the controller. The controller may be configured to receive video via the input port and identify a subject within frames of the video relative to a background within the frames. Further, the controller may be configured to identify dimensions, posture, hand location, feet location, and/or other parameters of the identified subject in frames of the video and determine when the subject is performing a task. Based on the dimensions and/or other parameters identified or extracted from the video during the predetermined task, the controller may output via the output port assessment information.
1. A marker-less subject tracking system comprising:
an input port for receiving a digital video of a subject;
a controller in communication with the input port, the controller is configured to:
determine a height of the subject in a frame from the digital video;
determine a width of the subject in the frame;
determine a posture of the subject in the frame based on a normalized height value of the subject in the frame and a normalized width value of the subject in the frame; and
wherein the height of the subject in the frame and the width of the subject in the frame are normalized based on a normalizer to determine the normalized height value of the subject in the frame and the normalized width value of the subject in the frame.
2. The system of claim 1 , wherein the controller is configured to automatically determine postures of the subject in real time during playback of the digital video.
3. The system of claim 1 , wherein the normalizer is a standing height of the subject.
4. The system of claim 1 , wherein the controller is configured to use a decision tree model to determine the posture of the subject in the digital video based on the normalized height value of the subject and the normalized width value of the subject determined from the digital video.
5. The system of claim 1 , wherein the determined posture is selected from a group consisting of a standing posture, a stooping posture, and a squatting posture.
6. The system of claim 1 , wherein to determine the posture of the subject in the frame, the controller is configured to:
compare a value based on the height of the subject in the frame to one or both of a first height threshold value and a second height threshold value; and
compare a value based on the width of the subject in the frame to one or both of a first width threshold value and a second width threshold value.
7. The system of claim 1 , wherein the controller is configured to determine the height of the subject and the width of the subject in the digital video using pixel information in the digital video.
8. The system of claim 1 , wherein the controller is configured to:
apply a bounding box around the subject in the digital video;
assign a height of the bounding box as the height of the subject; and
assign a width of the bounding box as the width of the subject.
9. The system of claim 8 , wherein the controller is configured to:
determine extreme-most pixels in two dimensions of the subject; and
the bounding box intersects the determined extreme-most pixels in the two dimensions of the subject.
10. The system of claim 1 , wherein the controller is configured to:
determine extreme-most pixels in a first dimension of the subject and assign a distance between the extreme-most pixels in the first dimension as the height of the subject; and
determine extreme-most pixels in a second dimension of the subject and assign a distance between the extreme-most pixels in the second dimension as the width of the subject.
11. A computer readable medium having stored thereon in a non-transitory state a program code for use by a computing device, the program code causing the computing device to execute a method for determining a posture of a subject in video comprising:
identifying a subject within a frame of video;
determining a height of the subject within the frame of the video;
determining a width of the subject within the frame of the video;
determining a first value based on the height of the subject in the frame by normalizing the height of the subject in the frame with a normalizer;
determining a second value based on the width of the subject in the frame by normalizing the width of the subject in the frame with the normalizer;
comparing the first value based on the height of the subject to at least a first threshold value and comparing the second value based on a width of the subject to at least a second threshold value; and
determining a posture of the subject within the frame of the video based on one or both of the comparing the first value based on the height of the subject to the first threshold value and the comparing the second value based on a width of the subject to the second threshold value.
12. The computer readable medium of claim 11 ,
wherein the normalizer is a standing height of the subject.
13. The computer readable medium of claim 11 , wherein the determined posture is selected from a group consisting of a standing posture, a stooping posture, and a squatting posture.
14. The computer readable medium of claim 11 , wherein:
comparing the first value based on the height of the subject to at least a first threshold value includes comparing the first value based on the height of the subject to a first height threshold value; and
determining the posture of the subject within the frame of the video includes when the first value based on the height of the subject has reached or gone beyond the first height threshold value, determining the subject is in a standing posture.
15. The computer readable medium of claim 14 , wherein:
comparing the first value based on the height of the subject to at least a first threshold value includes comparing the first value based on the height of the subject to a second height threshold value; and
determining the posture of the subject within the frame of the video includes when the first value based on the height of the subject has not reached or gone beyond the first height threshold value and when the first value based on the height of the subject has not reached or gone beyond the second height threshold value,
determining the subject is in a squatting posture.
16. The computer readable medium of claim 15 , wherein:
comparing the second value based on the width of the subject to at least a second threshold value includes comparing the second value based on the width of the subject to a first width threshold value; and
determining the posture of the subject within the frame of the video includes when the first value based on the height of the subject has not reached or gone beyond the first height threshold value and has reached or gone beyond the second height threshold value and when the second value based on the width of the subject has reached or gone beyond the first width threshold value, determining the subject is in a stooping posture.
17. The computer readable medium of claim 16 , wherein:
comparing the second value based on the width of the subject to at least a second threshold value includes comparing the second value based on the width of the subject to a second width threshold value;
determining the posture of the subject within the frame of the video further comprises wherein when the first value based on the height of the subject has not reached or gone beyond the first height threshold value and has reached or gone beyond the second height threshold value and the second value based on the width of the subject has not reached or gone beyond the first width threshold and:
when the second value based on the width of the subject has reached or gone beyond the second width threshold value, determining the subject is in a standing posture; and
when the second value based on the width of the subject has not reached or gone beyond the second width threshold value, determining the subject is in a squatting posture.
18. The computer readable medium of claim 11 , further comprising:
applying a bounding box around the subject within the frame of the video;
determining the height of the subject within the frame of the video based on a height of the applied bounding box; and
determining the width of the subject with the frame of the video based on a width of the applied bounding box.
19. A tracking system comprising:
a processor;
memory in communication with the processor, the memory includes instructions executable by the processor to:
analyze pixel information in a video;
determine a first value based on a height of a subject in the video by normalizing the height of the subject in the video with a normalizer;
determine a second value based on a width of the subject in the video by normalizing the width of the subject in the video with the normalizer;
compare the first value to one or more height threshold values;
compare the second value to one or more width threshold values; and
determine a parameter of the subject in the video using the comparison of the first value to the one or more height threshold values and the comparison of the second value to the one or more width threshold values.
20. The tracking system of claim 19 , wherein to analyze pixel information in the video, the processor and memory are configured to:
determine extreme-most pixels in a first dimensions of the subject and assign a distance between the extreme-most pixels in the first dimension as a height of the subject; and
determine extreme-most pixels in a second dimension of the subject and assign a distance between the extreme-most pixels in the second dimension as a width of the subject.
21. A marker-less subject tracking system comprising:
an input port for receiving a digital video of a subject;
a controller in communication with the input port, the controller is configured to:
determine a height of the subject in a frame from the digital video by determining extreme-most pixels in a first dimension of the subject and assigning a distance between the extreme-most pixels in the first dimension as the height of the subject;
determine a width of the subject in the frame by determining extreme-most pixels in a second dimension of the subject and assigning a distance between the extreme-most pixels in the second dimension as the width of the subject;
determine a posture of the subject in the frame based on the height of the subject in the frame and the width of the subject in the frame.
22. A tracking system comprising:
a processor;
memory in communication with the processor, the memory includes instructions executable by the processor to:
analyze pixel information in a video;
compare a value based on a height of a subject in the video to one or more height threshold values;
compare a value based on a width of a subject in the video to one or more width threshold values; and
determine a parameter of the subject in the video using the comparison of the value based on the height of the subject in the video to one or more height threshold values and the comparison of the value based on the width of the subject in the video to one or more width threshold values; and
wherein to analyze pixel information in the video, the processor and memory are configured to:
determine extreme-most pixels in a first dimensions of the subject and assign a distance between the extreme-most pixels in the first dimension as the height of the subject; and
determine extreme-most pixels in a second dimension of the subject and assign a distance between the extreme-most pixels in the second dimension as the width of the subject.