Controlled-environment facility video communications monitoring system
Video communications of residents of a controlled-environment facility are monitored to detect instances of non-verbal communications within the video, such as the display of written messages and hand signals. Residents may participate in live video visitation sessions with non-residents. Video recordings are generated for each video feed of the live video visitation. During the live video visitation, indications of non-verbal communications displayed in the live video are detected. If indications of non-verbal communications are detected in the live video, the recorded video is annotated to specify the locations of the detected indications in the recording. Upon completion of the video visitation session, post-processing of the recorded video detects additional indications of displayed non-verbal communication. The additional indications may be detected at proximal locations to the annotations and may be detected based on sampling frames of the recording to detect changes in the color balance indicating the display of a message surface.
1. A system for monitoring video communications provided to a resident of a controlled-environment facility, the system comprising:
a communication system configured to:
host a live video visitation between the resident and one or more non-residents, wherein the video visitation comprises a plurality of live video feeds; and
a video feed recording system configured to:
generate a plurality of video recordings, each video recording corresponding to a live video feed of the plurality of live video feeds; and
a live video processing system configured to:
concurrent with the live video visitation, sample a plurality of frames of a first live video feed of the plurality of video feeds to detect indications of a non-verbal communication displayed in the first live video feed, wherein a color balance is determined for each of the frames sampled from the first live video feed; and
annotate a first video recording corresponding to the first live video feed, wherein the annotations specify the locations of the detected indications of the non-verbal communication displayed in the first video recording; and
a video post-processing system configured to:
upon completion of the live video visitation, detect additional indications of the non-verbal communication displayed in the first video recording.
2. The system of claim 1 , wherein the additional indications of the non-verbal communication are detected at proximal locations to the locations specified in the annotations of the first video recording.
3. The system of claim 1 , wherein the live video processing system is further configured to detect the display of a message surface in the first live video feed based on changes in the color balance within a sequence of successive frames of the plurality of sampled frames.
4. The system of claim 1 , wherein the live video processing system is further configured to detect indications of the non-verbal communication in the first live video feed by detecting movement by a participant in the first live video feed.
5. The system of claim 4 , wherein the movement is detected based on a frame rate of the first live video feed.
6. The system of claim 4 , wherein the movement is detected based on a compression efficiency associated with the first live video feed.
7. A method for monitoring video communications of a resident of a controlled-environment facility, the method comprising:
hosting a live video visitation between the resident and one or more non-residents, wherein the video visitation comprises a plurality of live video feeds;
generating a plurality of video recordings, each video recording corresponding to a live video feed of the plurality of live video feeds;
sampling a plurality of frames of a first live video feed of the plurality of video feeds to detect, concurrent with the live video visitation, indications of a non-verbal communication displayed in the first live video feed, wherein a color balance is determined for each of the frames sampled from the first live video feed;
annotating a first video recording corresponding to the first live video feed, wherein the annotations specify the locations of the detected indications of the non-verbal communication displayed in the first video recording; and
detecting, upon completion of the live video visitation, additional indications of the non-verbal communication displayed in the first video recording.
8. The method of claim 7 , wherein the additional indications of the non-verbal communication are detected at proximal locations to the locations specified in the annotations of the first video recording.
9. The method of claim 7 , further comprising detecting the display of a message surface in the first live video feed based on changes in the color balance within a sequence of successive frames of the plurality of sampled frames.
10. The method of claim 7 , wherein the indications of the non-verbal communication in the first live video feed are detected by detecting movement by a participant in the first live video feed.
11. The method of claim 10 , wherein the movement is detected based on a frame rate of the first live video feed.
12. The method of claim 10 , wherein the movement is detected based on a compression efficiency associated with the first live video feed.
13. A computer-readable storage device having program instructions stored thereon for monitoring video communications of a resident of a controlled-environment facility, upon execution by one or more processors, the program instructions cause the one or more processors to:
host a live video visitation between the resident and one or more non-residents, wherein the video visitation comprises a plurality of live video feeds;
generate a plurality of video recordings, each video recording corresponding to a live video feed of the plurality of live video feeds;
sample a plurality of frames of a first live video feed of the plurality of video feeds to detect, concurrent with the live video visitation, indications of a non-verbal communication displayed in the first live video feed, wherein a color balance is determined for each of the frames sampled from the first live video feed;
annotate a first video recording corresponding to the first live video feed, wherein the annotations specify the locations of the detected indications of the non-verbal communication displayed in the first video recording; and
detect, upon completion of the live video visitation, additional indications of the non-verbal communication displayed in the first video recording.
14. The computer-readable storage device of claim 13 , the program instructions further causing the one or more processors to detect the additional indications of the non-verbal communication in the first live video feed by sampling a plurality of frames from the first live video feed at proximal locations to the locations specified in the annotations of the first video recording.
15. The computer-readable storage device of claim 14 , the program instructions further causing the one or more processors to detect the display of a message surface in the first live video feed based on changes in the color balance within a sequence of successive frames of the plurality of sampled frames.
16. The computer-readable storage device of claim 13 , the program instructions further causing the one or more processors to detect indications of the non-verbal communication in the first live video feed by detecting movement by a participant in the first live video feed, wherein the movement is detected based on a frame rate of the first live video feed.