# US 10,121,080 B2 · Systems and methods for controlling the recording, storing and transmitting of video surveillance content > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,121,080 B2 - Document ID: US10121080B2 - Status: Granted - Kind: B2 - Application number: 14/996,302 - Filed: 2016-01-15 - Published: 2016-07-21 - Granted: 2018-11-06 - Earliest claimed: 2015-01-15 - Assignees: Vclick3D, Inc. - Applicants: vClick3d, Inc. - Inventors: Michael Script; Daniel Moodie - Web page: https://patentgrep.com/patent/US10121080B2 ## CPC - G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) - G08B 13/19665: {Details related to the storage of video surveillance data (television signal recording H04N5/76)} - H04N 5/77: between a recording apparatus and a television camera - H04N 5/783: Adaptations for reproducing at a rate different from the recording rate - H04N 13/204: using stereoscopic image cameras (stereoscopic photography G03B35/00) - H04N 13/239: using two two-dimensional [2D] image sensors having a relative position equal to or related to the interocular distance (H04N13/243 takes precedence) - H04N 13/271: wherein the generated image signals comprise depth maps or disparity maps - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract Embodiments of the present invention relate to systems and methods for controlling the recording, storing and transmitting of video content captured by security cameras in order to drastically reduce the overall bandwidth required to remotely monitor a physical space. More specifically, embodiments of the present invention relate to a method of triggering or activating a video camera to record and/or transmit images of a physical environment over a network only when measurements taken by a separate structural sensor camera or depth-sensing device indicate that sufficient physical changes have occurred in the environment to warrant video recording. Embodiments of the invention pair video cameras with structural depth sensors, along with enhanced on-board processing techniques, to increase the recording and transmitting efficiency of video cameras by recording and/or transmitting video streams only when something in the physical environment monitored by a depth sensor is determined to have changed or moved, or is determined by processing algorithms to be important or significant. A security function and a library of image processing analytics are also disclosed for processing static and dynamic image states within the measured physical space. ## Claims ### Claim 1 A video surveillance system comprising: a video camera configured to monitor a physical space; a three-dimensional (3D) depth sensor configured to measure the physical space; a control system in communication with the video camera and the 3D depth sensor, the control system comprising a software application executable on a computing system, the control system configured receive real-time video images of the physical space from the video camera, the control system further configured to record the real-time video images, the control system further configured to capture a 3D baseline measurement of the physical space from the 3D depth sensor and to capture 3D subsequent measurements of the physical space from the 3D depth sensor at predetermined time intervals; and an analyte module operable with the control system, the analytic module configured to compare each 3D subsequent measurement to the 3D baseline measurement, each said 3D subsequent measurement comprising data model indicative of new 3D objects in the physical space that were not present in the 3D baseline measurement, the analytic module further configured to trigger the control system to record the real-time video images at a user-configurable active frame rate whenever a statistical confidence measure associated with the data model exceeds a predetermined threshold value. ### Claim 2 (depends on 1) The video surveillance system of claim 1, wherein the active frame rate is approximately 30 frames per second. ### Claim 3 (depends on 1) The video surveillance system of claim 1, wherein the analytic module is further configured to trigger the control system to record the real-time video images at a user-configurable default frame rate whenever no statistical confidence measure associated with the data model exceeds a predetermined threshold value. ### Claim 4 (depends on 3) The video surveillance system of claim 3, wherein the default frame rate is approximately 1 frame per minute. ### Claim 5 (depends on 1) The video surveillance system of claim 1, further comprising: a storage device within the control system, wherein the recording of real-time video images comprises storing the real-time video images in the storage device. ### Claim 6 (depends on 1) The video surveillance system of claim 1, wherein the recording of real-time video images comprises transmitting the real-time video images over a network to an external location. ### Claim 7 (depends on 6) The video surveillance system of claim 6, wherein the recording of real-time video images further comprises encoding the real-time video images using an image compression algorithm before transmitting the real-time video images over the network to the external location. ### Claim 8 (depends on 1) The video surveillance system of claim 1, wherein the 3D depth sensor comprises a stereo vision camera. ### Claim 9 (depends on 1) The video surveillance system of claim 1, wherein the 3D depth sensor comprises a LIDAR depth camera. ### Claim 10 (depends on 1) The video surveillance system of claim 1, wherein the 3D depth sensor comprises a LIDAR camera. ### Claim 11 (depends on 1) The video surveillance system of claim 1, wherein the data model of new objects in the physical space comprises at least one dimensionally reduced and translation-rotation invariant sensor. ### Claim 12 (depends on 11) The video surveillance system of claim 11, wherein the sensor comprise a 2nd-order Hu moment value for each of the new objects, where each 2nd-order Hu moment value represents an estimated size of one of the new objects. ### Claim 13 The video surveillance system of wherein the analytic module is further configured to receive the real-time video images of the physical space. ### Claim 14 (depends on 13) The video surveillance system of claim 13, wherein the analytic module is further configured to apply a facial identification algorithm to each frame of the received real-time video images. ### Claim 15 (depends on 1) The video surveillance system of claim 1, wherein the analytic model comprises a foreground estimation module configured to process points in a point cloud to identify the new 3D objects. ### Claim 16 (depends on 15) The video surveillance system of claim 15, wherein the foreground estimation module is configured to receive default settings for determining whether a given point in a received 3D subsequent measurement is close to a corresponding point in the 3D background measurement.