Methods, systems, and apparatus, including computer programs encoded on a storage device, for preventing false alarms due to display images. In one aspect, a monitoring system is disclosed that includes a processor and a computer storage media storing instructions that, when executed by the processor, cause the processor to perform operations. The operations can include obtaining, by the monitoring system, image data that depicts a portion of a property, determining, by the monitoring system, that the image data depicts an object, based on determining, by the monitoring system, that the image data depicts an object, determining, by the monitoring system, whether the depicted object is located within an exclusionary region of the property, and based on determining, by the monitoring system, that the depicted object is not located within an exclusionary region of the property, triggering, by the monitoring system, an event based on the image data.

An automated electronic video surveillance system enables a high-resolution mega-pixel camera to capture high quality, detailed, magnified images at multiple locations, simultaneously with an overview of the whole scene. A preferred embodiment requiring no moving parts provides full 360-degree continuous viewing with up to 5 all-digital zoom capability. The system performs continuous surveillance and active resolution allocation in the form of a feedback control subsystem that dynamically allocates resources so that important details within a scene receive appropriate scrutiny, while uninteresting areas are imaged at a lower resolution.

A security system can use video analytics and/or other input parameters to identify a theft event. Optionally, the security system can take remedial action in response. For example, the security system can use video analytics to determine that a person has reached into a shelf multiple times at a rate above a threshold, which can indicate that a thief is quickly removing items from the shelf. The security system can also use video analytics to determine that a person has reached into a shelf via a sweeping action, which can indicate that a thief is gathering and removing a large quantity of items from the shelf in one motion. In response, the security system can alert security personnel, cause a speaker to output an audible message in the target area, flag portions of the video relating to the theft event, activate or ready other sensors or systems, and/or the like.

A system for monitoring shopping baskets (e.g., baskets on human-propelled carts, motorized carts, or hand-carried baskets) can include a computer vision unit that can image a surveillance region (e.g., an exit to a store), determine whether a basket is empty or loaded with merchandise, and assess a potential for theft of the merchandise. The computer vision unit can include a camera and an image processor programmed to execute a computer vision algorithm to identify shopping baskets and determine a load status of the basket. The computer vision algorithm can comprise a neural network. The system can identify an at least partially loaded shopping basket that is exiting the store, without indicia of having paid for the merchandise, and execute an anti-theft action, e.g., actuating an alarm, notifying store personnel, activating a store surveillance system, activating an anti-theft device associated with the basket (e.g., a locking shopping cart wheel), etc.

A novel method and system for constantly monitoring security-monitoring assets (SMAs) and automatically determining whether security alerts are related to the same security event. The invention improves on existing technology by automatically assessing the geospatial location data of any SMAs responsible for initiating a security alert. The system automatically determines if any of the security alerts are related based on their proximity and the elapsed time between security alerts. If the security alerts occur within the defined proximity (relational zone) and/or relational timeframe, they are automatically grouped together to be processed as a single security event. Depending on the type of security alert, the system may rely solely on proximity or elapsed time. The system is constantly updating to ensure that proper associations are maintained at all times.

A video surveillance system is set up, calibrated, tasked, and operated. The system extracts video primitives and extracts even occurrences from the video primitives using event discriminators. The extracted video primitives and event occurrences may be used to create and define additional video analytic rules. The system can undertake a response, such as an alarm, based on extracted event occurrences.

A method for security and/or automation systems is described. In one embodiment, the method includes identifying image data from a signal, analyzing the image data based at least in part on a first parameter, identifying a presence of an object based at least in part on the analyzing, and detecting an object event based at least in part on the identifying.

A system for monitoring shopping baskets (e.g., baskets on human-propelled carts, motorized carts, or hand-carried baskets) can include a computer vision unit that can image a surveillance region (e.g., an exit to a store), determine whether a basket is empty or loaded with merchandise, and assess a potential for theft of the merchandise. The computer vision unit can include a camera and an image processor programmed to execute a computer vision algorithm to identify shopping baskets and determine a load status of the basket. The computer vision algorithm can comprise a neural network. The system can identify an at least partially loaded shopping basket that is exiting the store, without indicia of having paid for the merchandise, and execute an anti-theft action, e.g., actuating an alarm, notifying store personnel, activating a store surveillance system, activating an anti-theft device associated with the basket (e.g., a locking shopping cart wheel), etc.

Techniques are described for selecting an alarm state based at least in part on determining a security event related to security and automation systems. One method includes receiving, from a sensor, a first indication of a security event at the first location, determining a first threat level based on the security event, and activating a first alarm state based at least in part on the first threat level.

In a general aspect, an offline system detects new motion zones for a motion detection system. In some examples, observed channel response data is obtained from a motion detection system. The observed channel response data is associated with a plurality of subcarriers for each wireless link over a period of time. Estimated channel response data is generated for each wireless link. Transitions between zones of activity are identified in the estimated channel response data for each of the plurality of subcarriers for each wireless link. A new motion zone of the motion detection system is detected based on the estimated channel response data and the identified transitions.