Systems and methods for preserving data and human confidentiality during feature identification by robotic devices
Systems and methods for data and confidentiality preservation for feature identification by robotic devices are disclosed herein. According to at least one non-limiting exemplary embodiment, a method for determining if an image depicts a human is disclosed. The determination may be utilized to either (i) censor the face of the human, or (ii) identify features within the image. The determination enhances feature identification by ensuring only uncensored and unobscured images are provided to one or more models for the identification to preserve human confidentiality.
1 . A method, comprising:
receiving an image from a first sensor of a robotic device during navigation along a route;
determining if one or more dynamic objects is detected in the image within a field of view of the first sensor based on data from a second sensor;
determining if the one or more dynamic objects is either a human being or an inanimate object;
determining if a portion of the one or more dynamic objects comprises a human face;
blurring the portion of the image with the human being, wherein the blurring corresponds to digitally altering the image to censor the portion of the image;
determining that one or more human faces is not on the human being;
communicating, to a server, the image without the blurring of the one or more human faces that are within the one or more dynamic objects, and wherein the blurring of the one or more human faces comprises at least one of pixilation and blacking-out the one or more human faces in order to maintain confidentiality of the one or more human faces; and
identifying features depicted in the image if one or more dynamic objects is not detected within the field of view of the first sensor based on data from the second sensor,
wherein the one or more dynamic objects comprises either one or more objects moving in the field of view of the first sensor or one or more objects not localized onto a computer-readable reference map of the robotic device prior to the navigation along the route.
2 . The method of claim 1 , further comprising:
determining if the one or more dynamic objects does not comprise a human face.
3 . The method of claim 1 , wherein the second sensor includes a LIDAR sensor, a motion sensor, a thermal imaging camera, an ultrasonic sensor, or depth camera.
4 . The method of claim 1 , wherein the identifying of features further comprises communicating the image to a server external to the robotic device if the one or more dynamic objects is not detected in the image, the server including at least one processor configured to embody one or more models to identify the features within the image.
5 . The method of claim 4 , further comprising:
producing a computer readable map different from the computer-readable reference map, the computer readable map includes the identified features localized thereon, the localization being based on a position of the robotic device during acquisition of the image, the localization being performed by either a processor of the robotic device or the at least one processor of the server.
6 . The method of claim 1 , further comprising disabling or dimming at least one light configurable to illuminate a visual scene of the image upon determining the dynamic object comprises a human depicted within the image, wherein the robotic device includes the at least one light.
7 . The method of claim 1 , wherein, the second sensor comprises a field of view which overlaps at least in part with the field of view of the first sensor.
8 . The method of claim 7 , wherein, the second sensor includes two or more sensors, the two or more sensors comprise a combined field of view which overlaps at least in part with the field of view of the first sensor.
9 . A system, comprising:
one or more processing devices configured to execute computer readable instructions stored on one or more non-transitory computer readable storage mediums to:
receive an image from a first sensor of a robotic device;
determine if a dynamic object is present within a field of view of the first sensor based on data from a second sensor, the second sensor including at least one of a LIDAR sensor, a motion sensor, a thermal imaging camera, an ultrasonic sensor, or depth camera;
determine if the dynamic object is a human or inanimate object;
determine if a portion of a human in the image comprises a human face;
blur, in the image, the portion of the image comprising the human face to maintain confidentiality of the human face, wherein the blurring of the portion of the image corresponds to digitally altering the image to censor the portion of the image;
determine that one or more human faces is not on a human being;
communicate, to a server, the image without blurring of the one or more human faces that are within the one or more dynamic objects, and wherein the blurring the portion of the dynamic object comprising the human face comprises at least one of pixilation and blacking-out the one or more human faces in order to maintain the confidentiality of the one or more human faces;
identify features depicted in the image if no dynamic objects are detected within the field of view; and
produce a computer readable map, the computer readable map includes the identified features localized thereon, the localization being based on a position of the robot during acquisition of the image if no dynamic objects are detected within the field of view;
wherein,
the dynamic object includes one or more objects which are moving or objects not previously localized onto a computer readable reference map; and
the robotic device includes at least one light configurable to illuminate a visual scene of the image, the at least one light being disabled or dimmed upon determining the dynamic object comprises a human depicted within the image.
10 . A non-transitory computer readable storage medium comprising a plurality of computer readable instructions embodied thereon, the instructions, when executed by at least one processor, configure the at least one processor to:
receive an image from a first sensor of a robotic device during navigation along a route; and
identify features depicted in the image if one or more dynamic objects are not detected within a field of view of the first sensor based on data from a second sensor,
wherein the one or more dynamic objects comprises either one or more objects moving in the field of view of the first sensor or one or more objects not localized onto a computer-readable reference map of the robotic device prior to the navigation along the route;
determine if the one or more dynamic objects is either a human being or an inanimate object;
determine if a portion of the one or more dynamic objects comprises a human face; and
blur the portion of the one or more dynamic objects comprising the human face, wherein the blurring of the portion corresponds to digitally altering the image to censor the portion of the image,
determine that one or more human faces is not on the human being; and
communicate, to a server, the image without blurring of the one or more human faces that are within the one or more dynamic objects, and wherein the blurring of the one or more human faces comprises at least one of pixilation and blacking-out the one or more human faces in order to maintain confidentiality of the one or more human faces.
11 . The non-transitory computer readable storage medium of claim 10 , further comprising instructions which, when executed, configure the at least one processor to:
determine if the one or more dynamic objects does not comprise a human face.
12 . The non-transitory computer readable storage medium of claim 10 , wherein,
the second sensor includes a LIDAR sensor, a motion sensor, a thermal imaging camera, an ultrasonic sensor, or depth camera.
13 . The non-transitory computer readable storage medium of claim 10 , wherein,
the identifying of features further comprises communicating the image if the one or more dynamic objects is not detected in the image to a server external to the robotic device, the
server comprising at least one processor configured to embody one or more models to identify the features within the image.
14 . The non-transitory computer readable storage medium of claim 13 , further comprising instructions which, when executed, configure the at least one processor to:
produce a computer readable map different from the computer-readable reference map, the computer readable map includes the identified features localized thereon, the localization being based on a position of the robotic device during acquisition of the image, the localization being performed by either a processor of the robotic device or the at least one processor of the server.
15 . The non-transitory computer readable storage medium of claim 10 , further comprising instructions which, when executed, configure the at least one processor to:
disable or dim at least one light configurable to illuminate a visual scene of the image upon determining the dynamic object comprises a human depicted within the image; wherein the robotic device includes the at least one light.
16 . The non-transitory computer readable storage medium of claim 10 , wherein,
the second sensor comprises a field of view which overlaps at least in part with the field of view of the first sensor.
17 . The non-transitory computer readable storage medium of claim 16 , wherein,
the second sensor includes two or more sensors, the two or more sensors comprise a combined field of view which overlaps at least in part with the field of view of the first sensor.