Systems and methods for predicting and preventing collisions
A method for preventing a collision between a first object and a second object using a camera. The method includes capturing images of the first object and the second object using the camera, accessing a database of point clouds, and identify a first point cloud corresponding to the first object and a second point cloud corresponding to the second object within the database of point clouds, where the first point cloud corresponds to the first object being a person. The method further includes calculating a distance between the first object and the second object and comparing the distance to a threshold. The method further includes generating a notification when the distance is below the threshold.
1. A method for preventing an unintended collision between a person and a separate object using a camera, the method comprising:
capturing images of the person and the separate object using the camera, wherein the separate object and the person are non-coupled to each other;
accessing a database of point clouds;
identify a first point cloud corresponding to the person and a second point cloud corresponding to the separate object within the database of point clouds;
calculating a closest distance between the person and the separate object;
comparing the closest distance to a threshold; and
generating a notification when the closest distance is below the threshold to prevent the person and the separate object from unintentionally colliding and thus prevent the separate object from injuring the person.
2. The method according to claim 1 , wherein the first point cloud for the person is based on a first mask identified as corresponding to the person and the second point cloud for the separate object is based on a second mask identified as corresponding to the separate object, wherein the closest distance between the person and the separate object is calculated between the first point cloud and the second point cloud.
3. The method according to claim 2 , wherein nearest points between the first point cloud and the second point cloud are used to calculate the closest distance between the first point cloud and the second point cloud.
4. The method according to claim 1 , wherein the person is a patient, further comprising identifying that the patient is within a bed, wherein the separate object is other than the bed.
5. The method according to claim 4 , wherein the person is identified as being the patient based on identifying that the patient was within the bed, further comprising maintaining the identification of the person being the patient after the patient has left the bed.
6. The method according to claim 1 , wherein a third object is captured in the images from the camera, further comprising identifying a third point cloud within the database of point clouds that corresponds to the third object and identifying the third object as being a caregiver.
7. The method according to claim 6 , wherein the third object is identified as being the caregiver based on the patient being identified as being within a bed.
8. The method according to claim 7 , further comprising excluding notifications based on the third object when the third object is identified as being the caregiver.
9. The method according to claim 1 , further comprising determining a collision probability based on comparing the closest distance to the threshold.
10. The method according to claim 9 , wherein the person is a patient in a bed, further comprising determining an orientation of the patient, and wherein the collision probability varies based on the orientation of the patient.
11. The method according to claim 10 , wherein the orientation is classified as being one of supine, prone, and lateral.
12. The method according to claim 10 , further comprising counting a number of times the orientation changes for the patient, wherein the collision probability varies based on the number of times the orientation changes for the patient.
13. The method according to claim 1 , wherein the person is identified as being a patient, wherein the patient has body parts, and wherein the closest distance between the person and the separate object is calculated each of the body parts, further comprising determining when the closest distance for each of the body parts to the separate object is less than the threshold.
14. The method according to claim 13 , wherein the notification includes an image of the patient and the body parts thereof, further comprising displaying a given body part within the body parts differently within the image when the closest distance corresponding thereto is less than the threshold.
15. The method according to claim 14 , where the given body part is shown in a given color only when the closest distance corresponding thereto is less than the threshold.
16. The method according to claim 1 , wherein the person and the separate object are inside a patient room, wherein the camera is within the patient room, and wherein the notification is an audible alarm within the patient room.
17. The method according to claim 1 , wherein calculating the closest distance between the person and the separate object and comparing the closest distance to the threshold are performed in real-time.
18. A non-transitory medium having instructions thereon that, when executed by a processing system, causes a system for preventing unintended collisions between a person and a separate object using a camera to:
capture images of the person and the separate object using the camera, wherein the separate object is spaced apart from the person;
access a database of point clouds;
identify a first point cloud corresponding to the person and a second point cloud corresponding to the separate object within the database of point clouds;
calculate a closest distance between the person and the separate object;
compare the closest distance to a threshold; and
generate a notification when the closest distance is below the threshold to prevent the person and the separate object from unintentionally colliding and thus prevent the separate object from injuring the person.
19. The non-transitory medium according to claim 18 , wherein the person is identified as being a patient, wherein the patient has body parts, and wherein the closest distance between the person and the separate object to prevent the person and the separate object from unintentionally colliding and thus prevent the separate object from injuring the person is calculated for each of the body parts, wherein the system is further caused to determine when the closest distance for each of the body parts to the separate object is less than the threshold, wherein the notification includes an image of the patient and the body parts thereof, wherein the system is further caused to display a given body part within the body parts differently within the image when the closest distance corresponding thereto is less than the threshold.
20. A method for preventing an unintended collision between a patient and a separate object using a 3D camera, the method comprising:
capturing images of the patient and the separate object using the 3D camera, wherein the separate object is spaced apart from the patient;
accessing a database of masks;
identify a first mask corresponding to the patient and a second mask corresponding to the separate object within the database of masks;
generating a first point cloud for the patient based on the first mask and a second point cloud for the separate object based on the second mask;
calculating a closest distance between nearest points within the first point cloud and the second point cloud;
determining an orientation of the patient;
determining a collision probability based on closest distance calculated between the nearest points within the first point cloud and the second point cloud and based on the orientation determined for the patient; and
generating a notification when the collision probability exceeds a threshold to prevent the patient and the separate object from unintentionally colliding and thus prevent the separate object from injuring the patient.