Method and system for monitoring activity in monitored space

Abstract

Monitoring activity in a monitored space using a plurality of pan / tilt / zoom (PTZ) cameras each having a field of view (FOV) is disclosed herein. The method includes receiving a video stream from a first PTZ camera, identifying one or more objects in the FOV of the first PTZ camera, and classifying each of the identified objects into one or more of a plurality of object categories. The method includes determining when one or more objects classified into a first object category of the plurality of object categories obstruct a specified area of the monitored space in the FOV of the first PTZ camera for at least a threshold period of time, and when obstructed, determining that one or more objects classified into the first object category of the plurality of object categories obstruct the specified area of the monitored space in the FOV of the first PTZ camera. A second PTZ camera is caused to adjust its pan, tilt, and / or zoom settings to capture the designated area of the monitored space.

Description

Technical Field

[0001] The present disclosure relates generally to video surveillance systems, and more particularly to using video surveillance systems to monitor activity in a monitored space. Background Art

[0002] Many video surveillance systems employ a large number of cameras in use. Video surveillance systems are configured to provide video coverage of many areas of interest within a monitored space. Many times, a particular space may be covered by more than one camera in order to provide more complete coverage. Each camera has a field of view (FOV), and the FOV of each camera may be considered when designing a video surveillance system. Over time, the FOV of a camera may change due to poor adjustment, wear, etc. Sometimes, the FOV of a camera may be partially or completely obstructed due to unexpected events, such as, for example, someone moving a large indoor plant, or stacking several boxes in the wrong place. Sometimes, for more nefarious purposes, the FOV of a camera may be partially or even completely blocked, such as someone trying to avoid detection of a particular camera by intentionally placing something that blocks at least a portion of the FOV of the camera. What is desired is a system and method for automatically detecting when the FOV of a camera is obstructed or partially obstructed and making appropriate adjustments to other cameras to take into account the obstruction. Summary of the invention

[0003] The present disclosure relates generally to video surveillance systems, and more particularly to using video surveillance systems to monitor activity in a monitored space. An example may be found in a method for monitoring activity in a monitored space using multiple pan / tilt / zoom (PTZ) cameras, each having a field of view (FOV). The illustrative method includes receiving a first video stream from a first PTZ camera of a plurality of PTZ cameras, identifying one or more objects in the FOV of the first PTZ camera of the plurality of PTZ cameras, and classifying each of the one or more identified objects into one or more object categories of a plurality of object categories. The method includes determining when one or more objects classified into a first object category among the plurality of object categories obstruct a designated area of ​​a monitored space in a FOV of a first PTZ camera among the plurality of PTZ cameras for at least a threshold period of time, and when obstructed, causing a second PTZ camera among the plurality of pan / tilt / zoom (PTZ) cameras to adjust a pan, tilt, and / or zoom setting of the second PTZ camera among the plurality of pan / tilt / zoom (PTZ) cameras to capture the designated area of ​​the monitored space in the FOV of the second PTZ camera among the plurality of pan / tilt / zoom (PTZ) cameras.

[0004] Another example can be found in a video surveillance system for monitoring activities in a monitored space. The video surveillance system includes a plurality of pan / tilt / zoom (PTZ) cameras, each having a field of view (FOV). Each PTZ camera in the plurality of pan / tilt / zoom (PTZ) cameras is operably coupled via a peer-to-peer network. A first PTZ camera among the multiple PTZ cameras is configured to receive a first video stream from the first PTZ camera among the multiple PTZ cameras, identify one or more objects in a FOV of the first PTZ camera among the multiple PTZ cameras, classify each of the one or more identified objects into one or more object categories among a plurality of object categories, and determine when one or more objects classified into a first object category among the plurality of object categories obstruct a designated area of ​​a monitored space in the FOV of the first PTZ camera among the multiple PTZ cameras for at least a threshold time period, and when obstructed, send one or more messages to a second PTZ camera among the multiple pan / tilt / zoom (PTZ) cameras via a peer-to-peer network to adjust the pan, tilt, and / or zoom settings of the second PTZ camera among the multiple pan / tilt / zoom (PTZ) cameras to capture the designated area of ​​the monitored space in the FOV of the second PTZ camera among the multiple pan / tilt / zoom (PTZ) cameras.

[0005] Another example may be found in a non-transitory computer-readable medium storing instructions executable by one or more processors of a first PTZ camera that, when executed, cause the one or more processors of the first PTZ camera to receive a video stream from a first PTZ camera, identify one or more objects in a field of view (FOV) of the first PTZ camera, classify each of the one or more identified objects into one or more object categories of a plurality of object categories, and determine when one or more objects classified into a first object category of the plurality of object categories obstruct a designated area of ​​a monitored space in the FOV of the first PTZ camera for at least a threshold period of time, and when obstructed, send one or more messages to a second PTZ camera via a peer-to-peer network connection to adjust the pan, tilt, and / or zoom settings of the second PTZ camera to capture the designated area of ​​the monitored space in the FOV of the second PTZ camera.

[0006] The above summary is provided to facilitate understanding of some innovative features unique to the present disclosure, but is not intended to be a complete description. A comprehensive understanding of the present disclosure can be obtained by viewing the entire specification, claims, drawings and abstract as a whole. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] The present disclosure may be more fully understood by considering the following description of various examples in conjunction with the accompanying drawings, in which:

[0008] Figure 1 is a schematic block diagram showing an illustrative video surveillance system;

[0009] Figure 2A and Figure 2B are flow charts that collectively illustrate illustrative methods for monitoring activity in a monitored space;

[0010] Figure 3 is a flow chart showing a series of illustrative steps performed by a processor of a PTZ camera when executing executable instructions;

[0011] Figure 4 is a schematic diagram illustrating how one or more PTZ cameras can compensate for a partially or fully blocked FOV of a PTZ camera; and

[0012] Figure 5 is a flow chart showing an illustrative method.

[0013] Although the present disclosure is subject to various modifications and alternative forms, the details thereof have been shown by way of example in the accompanying drawings and will be described in detail. However, it should be understood that it is not intended to limit the present disclosure to the specific examples described. On the contrary, it is intended to cover all modifications, equivalents and alternatives that fall within the essence and scope of the present disclosure. DETAILED DESCRIPTION

[0014] The following description should be read with reference to the accompanying drawings, in which similar elements in different drawings are numbered in the same manner. The accompanying drawings are not necessarily drawn to scale, and they depict examples that are not intended to limit the scope of the present disclosure. Although examples of various elements are shown, those skilled in the art will recognize that many of the examples provided have suitable alternatives that can be utilized.

[0015] It is assumed herein that all numbers are modified by the term "about" unless the content clearly dictates otherwise. The recitation of numerical ranges by endpoints includes all numbers subsumed within that range (eg, 1 to 5 includes 1, 1.5, 2, 2.75, 3, 3.80, 4, and 5).

[0016] As used in this specification and the appended claims, the singular forms "a," "an," and "the" include plural referents unless the content clearly dictates otherwise. As used in this specification and the appended claims, the term "or" is generally employed in its sense including "and / or" unless the content clearly dictates otherwise.

[0017] It should be noted that references to "one embodiment", "some embodiments", "other embodiments", etc. in the specification indicate that the described embodiments may include a particular feature, structure, or characteristic, but every embodiment may not necessarily include the particular feature, structure, or characteristic. Moreover, these phrases do not necessarily refer to the same embodiment. In addition, when a particular feature, structure, or characteristic is described in conjunction with one embodiment, it is contemplated that the feature, structure, or characteristic is described in conjunction with one embodiment, and it is contemplated that the feature, structure, or characteristic may be applied to other embodiments regardless of whether explicitly described, unless otherwise clearly stated.

[0018] Figure 1 1 is a schematic block diagram showing an illustrative video surveillance system 10 for monitoring activities in a monitored space. The illustrative surveillance system 10 includes a plurality of pan / tilt / zoom (PTZ) cameras 12, which are individually labeled 12a, 12b, 12c, and 12d. Although a total of four PTZ cameras 12 are shown, this is merely illustrative, as the video surveillance system 10 may include any number of PTZ cameras 12, and in some instances may include far more than four PTZ cameras 12. Each of the PTZ cameras 12 has a field of view (FOV) 14, which is individually labeled 14a, 14b, 14c, and 14d. Each of the PTZ cameras 12 is configured to be able to adjust any of its pan setting, tilt setting, and zoom setting in order to change its FOV 14. In some cases, the PTZ cameras 12 are operably coupled to a networked video recorder (NVR) via a wired and / or wireless network. In some cases, the PTZ cameras 12 are operably coupled via a peer-to-peer network 16 that allows any of the PTZ cameras 12 to communicate with the other PTZ cameras 12. In some cases, the peer-to-peer network 16 can be, for example, a mesh network. In some cases, a networked video recorder (NVR) can be operably coupled to the peer-to-peer network. In some cases, the PTZ cameras 12 can be operably coupled to a monitoring station 22.

[0019] In some cases, each of the PTZ cameras 12 may include a control circuit system 18 that controls the operation of the PTZ camera 12, but for clarity, only the PTZ camera 12a is shown as including the control circuit system 18. In some cases, the control circuit system 18 may be configured to execute a video analysis algorithm to analyze the video stream generated by the corresponding PTZ camera 12. In some cases, each of the PTZ cameras 12 may include a transceiver 20, or may include a separate transmitter and / or a separate receiver. The transceiver 20 allows the PTZ camera 12 to communicate with other PTZ cameras 12, such as through a peer-to-peer network 16. It should be understood that each PTZ camera 12 may include additional components not shown, including a power supply, memory, a gyroscope and / or accelerometer for identifying the current PTZ setting, a visual alarm, and / or an audible alarm.

[0020] In some cases, each of the plurality of PTZ cameras 12 is configured to receive a video stream from a corresponding PTZ camera 12 and identify one or more objects in the FOV 14 of the PTZ camera 12. Each PTZ camera 12 is configured to classify each of the one or more identified objects into one or more object categories of a plurality of object categories, and determine when one or more objects classified into a first object category of the plurality of object categories obstruct a designated area of ​​the monitored space in the FOV 14 of the PTZ camera 12 for at least a threshold period of time, and when obstructed, send one or more messages to a second PTZ camera 12 via the peer-to-peer network 16 to adjust the pan, tilt, and / or zoom settings of the second PTZ camera 12 to capture the designated area of ​​the monitored space in the FOV 14 of the second PTZ camera 12.

[0021] In some cases, the designated area of ​​the monitored space may be a predefined critical area defined during commissioning of the video surveillance system 10. In some cases, identifying one or more objects in the FOV 14 of the PTZ camera 12 includes comparing one or more frames of the first video stream to a background reference frame associated with the PTZ camera 12. In some cases, classifying each of the one or more identified objects into one or more object classes of a plurality of object classes includes using artificial intelligence (AI) to classify each of the one or more identified objects into one or more object classes of a plurality of object classes. Each object class of the plurality of object classes may include one or more of an object size class and an object type class.

[0022] In some cases, when in a particular pan, tilt, and zoom setting, the PTZ camera 12 may see a particular object at a particular location. If the PTZ camera 12 changes its pan, tilt, or zoom, the location of the particular object will similarly change. As an example, assume that the reference point one of the PTZ camera 1 is located at (100, 100) pixels with pan=0 and tilt=0. If the camera 1 changes its position to pan=50 and tilt=0, the same reference point may now be at a new translated position, such as (500, 100). As will be appreciated, multiple common reference points may be identified in the FOV of each PTZ camera of the PTZ cameras 12 during commissioning of the video surveillance system 10, sometimes together with the corresponding PTZ settings. These common reference points may be used to map a physical location captured in the FOV of a first PTZ camera in the PTZ cameras 12 to the same physical location in the FOV of a second PTZ camera in the PTZ cameras 12. If two PTX cameras do not share any common reference points, the FOVs of the two cameras do not overlap.

[0023] When an object is identified as blocking a particular position in the FOV of a first PTZ camera, the coordinates of the blocked position in the FOV of the first PTZ camera are shared with an adjacent PTZ camera 12 (sometimes via a peer-to-peer network). Using the previously established common reference point, the adjacent second PTZ camera 12 maps the coordinates of the blocked position to corresponding coordinates in the FOV of the adjacent second PTZ camera. The adjacent second PTZ camera 12 then adjusts the pan, tilt, and / or zoom settings of the adjacent second PTZ camera 12 to capture the blocked position. In some cases, two or more of the adjacent PTZ cameras 12 may map the coordinates of the blocked position to corresponding coordinates in the FOV of the corresponding adjacent PTZ camera, and each of the adjacent PTZ cameras 12 may adjust their pan, tilt, and / or zoom settings to capture the blocked position. In some cases, the two or more adjacent PTZ cameras 12 may coordinate the adjustment of their pan, tilt, and / or zoom settings to capture the blocked position while minimizing the impact on the overall coverage of the monitored space by the video surveillance system 10.

[0024] Figure 2A and 2B2 is a flowchart that together illustrates an illustrative method 24 for monitoring activity in a monitored space using a plurality of PTZ cameras, such as the PTZ camera 12, each having a field of view (FOV). The illustrative method 24 includes receiving a first video stream from a first PTZ camera of the plurality of PTZ cameras, as indicated at block 26. One or more objects are identified in the FOV of the first PTZ camera of the plurality of PTZ cameras, as indicated at block 28. In some cases, recognizing the one or more objects in the FOV of the first PTZ camera of the plurality of PTZ cameras includes comparing one or more frames of the first video stream to a background reference frame associated with the first PTZ camera of the plurality of PTZ cameras. Each of the one or more recognized objects is classified into one or more object categories of a plurality of object categories, as indicated at block 30. In some cases, classifying each of the one or more recognized objects into one or more object categories of a plurality of object categories may include using artificial intelligence (AI) to classify each of the one or more recognized objects into one or more object categories of a plurality of object categories. As an example, each object category in the plurality of object categories may include one or more of an object size category and an object type category. In some cases, an object may be classified as a person, a vehicle, a pet, a bag, a box, a balloon, a hand, and / or any other object type.

[0025] Determine when one or more objects classified into a first object category in the plurality of object categories obstruct a designated area of ​​the monitored space in the FOV of the first PTZ camera in the plurality of PTZ cameras for at least a threshold period of time, as indicated at block 32. When this occurs, the method 24 includes causing a second PTZ camera in the plurality of PTZ cameras to adjust a pan, tilt, and / or zoom setting of the second PTZ camera in the plurality of PTZ cameras to capture the designated area of ​​the monitored space in the FOV of the second PTZ camera in the plurality of PTZ cameras, as indicated at block 32a. As an example, the designated area of ​​the monitored space may be a predefined key area (e.g., a gaming table) defined during commissioning.

[0026] In some cases, method 24 may include sending one or more instructions from the first PTZ camera in the plurality of PTZ cameras to a second PTZ camera in the plurality of PTZ cameras, wherein the one or more instructions cause the second PTZ camera in the plurality of PTZ cameras to adjust the pan, tilt, and / or zoom settings of the second PTZ camera in the plurality of PTZ cameras to capture a designated area of ​​the monitored space in the FOV of the second PTZ camera in the plurality of PTZ cameras, as indicated at block 34. As an example, the one or more instructions may be sent over a peer-to-peer network. In some cases, the first PTZ camera in the plurality of PTZ cameras may send the current pan, tilt, and zoom position and IP address of the first PTZ camera in the plurality of PTZ cameras, as well as object details about one or more objects that are obstructing the designated area of ​​the monitored space in the FOV of the first PTZ camera in the plurality of PTZ cameras. The object details may include, for example, coordinates of an object location, an object classification, a time since the designated area was initially obstructed, one or more colors of an object, a size and / or shape of an object, and / or any other suitable object details.

[0027] continue Figure 2B , the method 24 may include verifying that the FOV of the second one of the plurality of PTZ cameras is not obstructed from viewing the designated area of ​​the monitored space before causing the second one of the plurality of PTZ cameras to adjust the pan, tilt, and / or zoom settings of the second one of the plurality of PTZ cameras to capture the designated area of ​​the monitored space in the FOV of the second one of the plurality of PTZ cameras, as indicated at block 36. In some cases, the method 24 may include storing one or more shared reference points corresponding to a common physical location in the monitored space in two or more of the plurality of PTZ cameras, wherein the designated area of ​​the monitored space is identified relative to the one or more shared reference points, as indicated at block 38. The method 24 may include storing calibration data in the second one of the plurality of PTZ cameras, the calibration data associating one or more of the pan, tilt, and / or zoom settings of the second one of the plurality of PTZ cameras with the one or more shared reference points, as indicated at block 40. Method 24 may include adjusting the pan, tilt, and / or zoom settings of the second PTZ camera among the multiple PTZ cameras based at least in part on the one or more shared reference points and the calibration data to capture a specified area of ​​the monitored space in the FOV of the second PTZ camera among the multiple PTZ cameras, as indicated at box 42.

[0028] In some cases, a first PTZ camera of the plurality of PTZ cameras includes a control circuit system configured to receive a first video stream from the first PTZ camera of the plurality of PTZ cameras, identify one or more objects in a FOV of the first PTZ camera of the plurality of PTZ cameras, classify each of the one or more identified objects into one or more object categories of a plurality of object categories, and determine when one or more objects classified into a first object category of the plurality of object categories obstruct a designated area of ​​a monitored space in the FOV of the first PTZ camera of the plurality of PTZ cameras for at least a threshold period of time. When so determined, the first PTZ camera of the plurality of PTZ cameras may be configured to send one or more instructions to a second PTZ camera of the plurality of PTZ cameras via a peer-to-peer network to adjust the pan, tilt, and / or zoom settings of the second PTZ camera of the plurality of PTZ cameras to capture the designated area of ​​the monitored space in the FOV of the second PTZ camera of the plurality of PTZ cameras.

[0029] Figure 3 4 is a flow chart showing a series of illustrative steps 44 that may be performed by one or more processors of a first PTZ camera, such as PTZ camera 12a, when executing executable instructions. The executable instructions may cause the one or more processors of the first PTZ camera to receive a video stream from the first PTZ camera, as indicated at block 46. The executable instructions may cause the one or more processors of the first PTZ camera to recognize one or more objects in a field of view (FOV) of the first PTZ camera, as indicated at block 48. In some cases, recognizing the one or more objects in the FOV of the first PTZ camera may include comparing one or more frames of the first video stream to a background reference frame associated with the first PTZ camera to reveal the one or more objects. The executable instructions may cause the one or more processors of the first PTZ camera to classify each of the one or more recognized objects into one or more object categories of a plurality of object categories, as indicated at block 50. As an example, each of the plurality of object categories may include one or more of an object size category and an object type category.

[0030] The executable instructions may cause the one or more processors of the first PTZ camera to determine when one or more objects classified into a first object category in the plurality of object categories obstruct a designated area of ​​the monitored space in the FOV of the first PTZ camera for at least a threshold period of time, as indicated at block 52. When so determined, the executable instructions may cause the one or more processors of the first PTZ camera to send one or more messages to a second PTZ camera via a peer-to-peer network connection to adjust the pan, tilt, and / or zoom settings of the second PTZ camera to capture the designated area of ​​the monitored space in the FOV of the second PTZ camera, as indicated at block 54. In some cases, the designated area of ​​the monitored space may be a predefined key area (e.g., a gaming table) defined during commissioning.

[0031] Figure 4 1 is a schematic diagram showing how one or more PTZ cameras 12 compensate for a partially or fully obstructed FOV 14 of the PTZ camera 12. A total of four PTZ cameras 12 are shown, labeled 12a, 12b, 12c, and 12d. Each of the PTZ cameras 12 has a FOV 14, individually labeled 14a, 14b, 14c, and 14d, and shown in solid lines. As configured, the FOV 14 can be considered to be the raw FOV 14 of each of the PTZ cameras 12. The bucket 56 represents a designated area of ​​the monitored space and is of interest. As shown, the raw FOV 14 of each of the PTZ cameras 12 includes a barrel 56.

[0032] For example, assume that the FOV 14c of PTZ camera 12c is blocked by blocking element 58, which means that PTZ camera 12c no longer includes barrel 56 in its FOV 14c. In response, the PTZ cameras 12 can communicate with each other so that one or more of the other PTZ cameras 12 can adjust their FOV 14 to compensate for the PTZ camera 12c having its FOV 14c at least partially blocked. As can be seen, camera 12b has adjusted its FOV 14b, such as by adjusting its translation and / or its tilt, and now has a modified FOV 60 as indicated by the dashed line. This modified FOV 60 covers more of the ground in front of barrel 56, partially compensating for the loss of what PTZ camera 12c can see. PTZ camera 12d has also adjusted its FOV 14d, such as by adjusting its translation and / or its tilt, and now has a modified FOV 62 as indicated by the dashed line. This modified FOV 62 covers more of the space in front of the barrel 56, partially compensating for the loss of what the PTZ camera 12c can see.

[0033] During the initial calibration of each of the PTZ cameras 12, a number of parameters may be configured or set. As an example, each of the PTZ cameras 12 may be used to capture 360 ​​degree images during calibration. From this, an operator or user determines and marks a critical FOV for each of the PTZ cameras 12. The operator or user configures the object size. In some cases, the operator or user may configure a threshold for the occlusion time. As an example, momentary occlusions, such as those less than one minute, may be ignored, while longer occlusions may be considered critical.

[0034] Figure 5 is a flow chart showing an illustrative method 64 for operating an illustrative video surveillance system 10. When powered on, each of the PTZ cameras calculates their current camera position, as indicated at box 66. Each of the PTZ cameras determines or otherwise receives relevant information from adjacent PTZ cameras, as indicated at box 68. This information is shared, as indicated at box 70. Artificial intelligence is used to detect blind spots, as indicated at box 72. A detected blind spot will generate an alarm and notify nearby PTZ cameras, as indicated at box 74. Nearby PTZ cameras will adjust their pan, tilt and / or zoom settings to compensate, as indicated at box 76. These changes may be notified to a monitoring station, as indicated at box 78. In some cases, after the detected blind spot is captured by one or more of the other PTZ cameras, the system may automatically acknowledge the blind spot alarm so that the operator does not need to take any action.

[0035] Although several exemplary embodiments of the present disclosure have been described in this manner, it will be readily understood by those skilled in the art that other embodiments may be made and used within the scope of the claims appended hereto. However, it should be understood that the present disclosure is in many respects merely illustrative. Details (especially details related to shape, size, arrangement of parts, and exclusion and order of steps) may be changed without exceeding the scope of the present disclosure. Of course, the scope of the present disclosure is defined in the language of the appended claims.

Claims

1. A method for monitoring activity in a monitored space using a plurality of pan / tilt / zoom (PTZ) cameras each having a field of view (FOV), the method comprising: receiving a first video stream from a first PTZ camera of the plurality of PTZ cameras; identifying one or more objects in the FOV of a first PTZ camera of the plurality of PTZ cameras; classifying each of the one or more recognized objects into one or more object categories of a plurality of object categories; as well as determining when one or more objects classified into a first object category of the plurality of object categories obstruct a designated area of ​​the monitored space in the FOV of the first PTZ camera of the plurality of PTZ cameras for at least a threshold period of time, and when obstructed: causing a second pan / tilt / zoom (PTZ) camera among the plurality of PTZ cameras to adjust the pan, tilt and / or zoom settings of the second PTZ camera among the plurality of PTZ cameras to capture the designated area of ​​the monitored space within the FOV of the second PTZ camera among the plurality of PTZ cameras.

2. The method of claim 1 , wherein identifying one or more objects in the FOV of the first PTZ camera of the plurality of PTZ cameras comprises comparing one or more frames of the first video stream to a background reference frame associated with the first PTZ camera of the plurality of PTZ cameras.

3. The method of claim 1 , wherein classifying each of the one or more recognized objects into one or more object categories among a plurality of object categories comprises using artificial intelligence (AI) to classify each of the one or more recognized objects into one or more object categories among a plurality of object categories.

4. The method of claim 1 , comprising sending one or more instructions from the first PTZ camera among the multiple pan / tilt / zoom (PTZ) cameras to the second PTZ camera among the multiple pan / tilt / zoom (PTZ) cameras, wherein the one or more instructions cause the second PTZ camera among the multiple pan / tilt / zoom (PTZ) cameras to adjust the pan, tilt and / or zoom settings of the second PTZ camera among the multiple pan / tilt / zoom (PTZ) cameras to capture the designated area of ​​the monitored space in the FOV of the second PTZ camera among the multiple pan / tilt / zoom (PTZ) cameras.

5. The method of claim 4, wherein the one or more instructions are sent from the first of the plurality of pan / tilt / zoom (PTZ) cameras to the second of the plurality of pan / tilt / zoom (PTZ) cameras via a peer-to-peer network.

6. The method of claim 1 , wherein the first PTZ camera of the plurality of PTZ cameras comprises control circuitry configured to: receiving the first video stream from the first PTZ camera of the plurality of PTZ cameras; identifying one or more objects in the FOV of a first PTZ camera of the plurality of PTZ cameras; classifying each of the one or more recognized objects into one or more object categories of a plurality of object categories; as well as determining when one or more objects classified into the first one of the plurality of object categories obstruct a designated area of ​​the monitored space in the FOV of the first one of the plurality of PTZ cameras for at least a threshold period of time, and when so: sending one or more instructions to a second pan / tilt / zoom (PTZ) camera among the plurality of pan / tilt / zoom (PTZ) cameras via a peer-to-peer network to adjust the pan, tilt and / or zoom settings of the second PTZ camera among the plurality of pan / tilt / zoom (PTZ) cameras to capture the designated area of ​​the monitored space in the FOV of the second PTZ camera among the plurality of pan / tilt / zoom (PTZ) cameras.

7. The method according to claim 1, comprising: Prior to causing the second one of the multiple pan / tilt / zoom (PTZ) cameras to adjust the pan, tilt and / or zoom settings of the second one of the multiple pan / tilt / zoom (PTZ) cameras to capture the designated area of ​​the monitored space in the FOV of the second one of the multiple pan / tilt / zoom (PTZ) cameras, verify that the FOV of the second one of the multiple pan / tilt / zoom (PTZ) cameras is not obstructed from viewing the designated area of ​​the monitored space.

8. The method of claim 1, wherein the plurality of object categories include one or more of object size categories and object type categories.

9. The method according to claim 1, comprising: storing one or more shared reference points corresponding to common physical locations in the monitored space in two or more of the plurality of pan / tilt / zoom (PTZ) cameras, wherein the designated area of ​​the monitored space is identified relative to the one or more shared reference points; storing calibration data in the second one of the plurality of pan / tilt / zoom (PTZ) cameras, the calibration data associating one or more of the pan, tilt, and / or zoom settings of the second one of the plurality of PTZ cameras with the one or more shared reference points; and The pan, tilt and / or zoom settings of the second pan / tilt / zoom (PTZ) camera among the multiple PTZ cameras are adjusted based at least in part on the one or more shared reference points and the calibration data to capture the designated area of ​​the monitored space in the FOV of the second PTZ camera among the multiple pan / tilt / zoom (PTZ) cameras.

10. A video surveillance system for monitoring activities in a monitored space, the video surveillance system comprising: a plurality of pan / tilt / zoom (PTZ) cameras each having a field of view (FOV), each PTZ camera of the plurality of pan / tilt / zoom (PTZ) cameras being operably coupled via a peer-to-peer network; A first PTZ camera of the plurality of PTZ cameras is configured as: receiving a first video stream from the first PTZ camera of the plurality of PTZ cameras; identifying one or more objects in the FOV of a first PTZ camera of the plurality of PTZ cameras; classifying each of the one or more recognized objects into one or more object categories of a plurality of object categories; as well as determining when one or more objects classified into a first object category among the plurality of object categories obstruct a designated area of ​​the monitored space in the FOV of a first PTZ camera among the plurality of PTZ cameras for at least a threshold period of time, and when obstructed, sending one or more messages to a second PTZ camera among the plurality of pan / tilt / zoom (PTZ) cameras via the peer-to-peer network to adjust the pan, tilt and / or zoom settings of the second PTZ camera among the plurality of pan / tilt / zoom (PTZ) cameras to capture the designated area of ​​the monitored space in the FOV of the second PTZ camera among the plurality of pan / tilt / zoom (PTZ) cameras.

Images