# US 2019/0244364 A1 · System and Method for Detecting the Object Panic Trajectories

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0244364 A1
- Document ID: US20190244364A1
- Status: Published application
- Kind: A1
- Application number: 16/167,535
- Filed: 2018-10-23
- Published: 2019-08-08
- Earliest claimed: 2018-02-06
- Assignees: OOO ITV Group
- Applicants: OOO ITV Group
- Inventors: Murat K. Altuev; Viacheslav V. Bratishchev
- Web page: https://patentgrep.com/patent/US20190244364A1

## CPC

- G06V 10/764: using classification, e.g. of video objects
- G06T 7/20: Analysis of motion (motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51)
- G06T 11/23: using straight lines or curves
- G08B 3/10: using electric transmission; using electromagnetic transmission
- G08B 5/22: using electric transmission; using electromagnetic transmission
- G08B 13/19613: {Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion}
- G06T 2200/24: involving graphical user interfaces [GUIs]
- G06T 2207/20096: Interactive definition of curve of interest
- G06T 2207/30241: Trajectory
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS

## Abstract

The invention relates to the area of safety and monitoring systems, and more particularly to the technologies aimed to detect the alarming object trajectories afield while using the specified graphics primitives. The computer system detecting the alarming object trajectories consists of the processor, memory, data capture device and graphical user interface. The data input means include the graphics primitives setting unit configured to set the graphics primitive by choosing several points in the coordinates system of original data. The set of specified graphics primitives internally forms the tracing area, the classification rules setting unit and object trajectory classification unit. The object trajectory classification unit is additionally designed with the possibility to set the notifications to user. The enlargement of hardware range relating to the alarming object trajectories detection is achieved.

## Claims

### Claim 1

A computer system for detecting the alarming object trajectories that includes:
at least one processor;
a memory unit configured to store original data;
at data capture device configured to collect and output data including object metadata,
wherein the metadata comprise, for specific times, object coordinates;
a graphical user interface configured to process the object metadata;
a data input unit; and
a data output unit;
wherein the data input unit comprises:
a graphics primitives setting unit configured for a user to choose at least one graphics primitive by choosing points in coordinates of the original data output by the data capture device,
wherein the at least one graphics primitive forms a tracing area;
a classification rules setting unit configured to define rules for determining whether an object trajectory is alarming with respect to the tracing area;
an object trajectory classification unit configured to detect alarming object trajectories according to the rules defined in the classification rules setting unit;
wherein the object trajectory classification unit is further configured to send a notification to the user if an alarming object trajectory is detected.

### Claim 2 (depends on 1)

The computer system of claim 1, wherein the original data comprise a location map output by the data capture device or image data output by the data capture device.

### Claim 3 (depends on 2)

The computer system of claim 2, wherein the graphical user interface is further configured to display object coordinates in the original data.

### Claim 4 (depends on 3)

The computer system of claim 3, wherein object trajectory coordinates are two-dimensional or three-dimensional.

### Claim 5 (depends on 1)

The computer system of claim 1, wherein the output data is a video or an object metadata stream.

### Claim 6 (depends on 1)

The computer system of claim 1, wherein the at least one graphics primitive is a two- dimensional surface or a three-dimensional surface.

### Claim 7 (depends on 6)

The computer system of claim 6, wherein the two-dimensional surface is one of: a segment, a straight line, a curved line, a broken line, a polyline, and an arc.

### Claim 8 (depends on 6)

The computer system of claim 6, wherein the three-dimensional surface is one of: a plane, a broken surface, a smooth curved surface, and a multi-segment surface.

### Claim 9 (depends on 1)

The computer system of claim 1, wherein the at least one graphics primitive is located arbitrarily, in parallel or at selected angle relative to each other.

### Claim 10 (depends on 1)

The computer system of claim 1, wherein the tracing area is a corridor constrained by the specified graphics primitives.

### Claim 11 (depends on 10)

The computer system of claim 10, wherein the fact of object complete passing through the corridor due to the set trajectory fully located inside the corridor is related to the classification rule.

### Claim 12 (depends on 10)

The computer system of claim 10, wherein the fact of object complete passing through several specified corridors in succession due to the trajectories which are set for every corridor and fully located inside every of several mentioned corridors is related to the classification rule.

### Claim 13 (depends on 1)

The computer system of claim 1, wherein the following object parameters are minimally set by the classification rules setting unit in the course of classification rules setting: trajectory, type, color, minimum allowed speed, maximum allowed speed, minimum permissible dimension, maximum permissible dimension.

### Claim 14 (depends on 13)

The computer system of claim 13, wherein the type of object relates to: person, group of people or transport.

### Claim 15 (depends on 13)

The computer system of claim 13, wherein it is possible to minimally set the object's sex or possession of one of the things (bag, umbrella, headwear, moustaches, beard) as additional characteristics.

### Claim 16 (depends on 1)

The computer system of claim 1, wherein the classification rules additionally depend on the type of data capture device that provides the metadata.

### Claim 17 (depends on 16)

The computer system of claim 16, wherein one of the following may represent the data capture device: video surveillance camera, GPS sensor, GLONASS sensor, objects detector.

### Claim 18 (depends on 16)

The computer system of claim 16, wherein the data capture device is a security system bracelet providing GPS or GLONASS coordinates. At the same time, this device alerts the bracelet's possessor identifier and due to the type of this identifier determines if it is necessary to alert.

### Claim 19 (depends on 1)

The computer system of claim 1, wherein the user notification may be at least visual, acoustic, textual or combined.

### Claim 20 (depends on 1)

The computer system of claim 1, wherein the memory unit is additionally designed with the possibility to record and store the data archive received from, at least, one data capture device, and the computer system is additionally configured to detect the alarming trajectories using the archive data.

### Claim 21

A method for detecting alarming object trajectories is realized by the computer system and includes the stages during which:
the output data including objects metadata are collected and introduced and metadata involve, at least, the information about number of object locations at the certain points;
at least one graphics primitive is set by means of choosing several points in the coordinates system of original data connected with the output data coming from the data capture device. Moreover, the set of specified graphics primitives internally forms the tracing area;
the classification rules defining which object trajectories are alarming in regards to the tracing area are set;
every trajectory is checked according to the specified classification rules to detect the alarming object trajectories; and
the notification is sent to the user if the trajectory is turned to be or became alarming during the specified time.

### Claim 22 (depends on 21)

The method of claim 21, wherein the original data may be the location map or image received from the data capture device, and the location map may be bound to the output data.

### Claim 23 (depends on 21)

The method of claim 21, wherein it is additionally designed with the possibility to induce the user interface to display the object coordinates on the original data.

### Claim 24 (depends on 23)

The method of claim 23, wherein the object coordinates may be two- or three-dimensional ones.

### Claim 25 (depends on 21)

The method of claim 21, wherein the output data is represented by the video or object metadata stream.

### Claim 26 (depends on 23)

The method of claim 23, wherein the graphics primitive may be the virtual two- or three-dimensional surface.

### Claim 27 (depends on 26)

The method of claim 26, wherein two-dimensional surface is at least one of the following: segment, straight line, curve line, broken line, polyline, arc.

### Claim 28 (depends on 26)

The method of claim 26, wherein three-dimensional surface is at least one of the following: plane, broken surface, smoothly spun surface, multi-segment surface.

### Claim 29 (depends on 26)

The method of claim 26, wherein the graphics primitives taken from the set of graphics primitives may be located arbitrary, in parallel or at selected angle relative to each other.

### Claim 30 (depends on 21)

The method of claim 21, wherein the tracing area is a corridor constrained by the specified graphics primitives.

### Claim 31 (depends on 30)

The method of claim 30, wherein the fact of complete object passing through the corridor due to the set trajectory fully located inside the corridor is related to the classification rule.

### Claim 32 (depends on 30)

The method of claim 30, wherein the fact of complete object passing through several specified corridors in succession due to the trajectories which are set for every corridor and fully located inside every of several mentioned corridors is related to the classification rule.

### Claim 33 (depends on 21)

The method of claim 21, wherein the following object parameters are minimally set in the course of classification rules setting: trajectory, type, color, minimum allowed speed, maximum allowed speed, minimum permissible dimension, maximum permissible dimension.

### Claim 34 (depends on 33)

The method of claim 33, wherein the person, group of people or transport belongs to the types of object.

### Claim 35 (depends on 33)

The method of claim 33, wherein it is possible to minimally set the object's sex or possession of one of the things (bag, umbrella, headwear, moustaches, beard) as additional characteristics.

### Claim 36 (depends on 21)

The method of claim 21, wherein the classification rules additionally depend on the type of data capture device that provides the metadata.

### Claim 37 (depends on 36)

The method of claim 36, wherein one of the following things may represent the data capture device: video camera, GPS sensor, GLONASS sensor, objects detector.

### Claim 38 (depends on 36)

The method of claim 36, wherein the data capture device is a security system bracelet providing GPS or GLONASS coordinates. At the same time, this device alerts the bracelet's possessor identifier and due to the type of this identifier determines if it is necessary to alert.

### Claim 39 (depends on 21)

The method of claim 21, wherein the user notification may be at least visual, acoustic, textual or combined.

### Claim 40 (depends on 21)

The method of claim 21, wherein it is additionally designed with the possibility to record and store the data archive received from at least one data capture device, and computer system is additionally configured to detect the alarming trajectories using the archive data.

### Claim 41 (depends on 21)

The storage medium read by the computer contains the instructions performed by the processor to implement the methods of claim 21.
