Abstract: Multiple input feeds are used to make a pathway determination in systems using artificial intelligence engines in connection with video cameras, associated video streams, and other sensors. The system obtains a video stream and information specifying a location of the video stream. An event is detected in the video stream, such as movement of an individual, movement of an automobile, criminal activity, an emergency situation, etc. The system also obtains a detection signal and location thereof, such as information from a sensor in a heat detecting device, a sound detecting device, or a camera. Based on the foregoing information, the system identifies a possible future location for an event, such as the movement of the detected individual, automobile, etc.

Abstract: Segments are generated with respect to images and rules are correlated to the segments. The images may be associated with the field of view of a camera that is used in systems having artificial intelligence engines in connection with video cameras and associated video data streams. A video processor identifies element in a video stream, examples of which include various regions in a view, such as sky, vegetation, buildings, etc. The elements may be identified based on elements that were previously identified for other cameras and can be updated in response to the view changing. Segments are created around the different identified elements. Rules are assigned to the segments. The rules and segments may be stored for later reference when analyzing events within the view of the video camera.

Abstract: Artificial intelligence (AI) models are switched, tuned and retrained. This process may be performed with respect to systems having artificial intelligence engines in connection with video cameras and associated video data streams. An AI model is obtained for a video camera based on, for example, historic video streams from the camera for the past day, week, month, year, or any other time period. The AI model is then modified for the camera after the system obtains, for example, data internal to the video camera, data external to the video camera and data related to objects of interest for the video camera. As the AI model is modified, a processor associated with the system may adopt linear regression algorithms to regress conditions to the modified model and other available models.

Abstract: Changes in sizes of objects over long periods of time are detected. The objects may be detected in the field of view of a camera that is used in systems having artificial intelligence engines in connection with video cameras and associated video data streams. A video processor identifies different elements in the video stream. Segments are created around the different elements identified. The video processor identifies an algorithm for each segment. An object is identified in the video stream. The video processor uses the created segments and the identified algorithms to detect changes in the object over time.

Abstract: An object size model filters false positive results in systems using artificial intelligence engines in connection with video cameras and associated video data streams. The system obtains a video data stream and accesses an object size model that has been previously computed for the camera from which the video data stream is obtained. An object is detected in the video stream and a preliminary identification thereof is made. A size range for the identified object is calculated using the object size model. The object size range is compared to an observed size of the object. If observed size of the object is not within the size range for the identified object, the object is deemed to be a false positive.

Abstract: Signal-to-noise ratios are calculated for cellphones in a process that may be implemented in processing elements of the cellphones or in a SIM card. A signal for a cellular device is obtained, such as a voice stream, a message, or a data stream. The voice stream, for example, may be received as a part of a telephone call, as part of a voicemail message, as part of a VoIP call, or as part of a video messaging service, etc. The noise data is determined in the signal using a machine learning algorithm. The cellphone may include a model based on the identification of signals as desired signals or as noise. The model on the cellphone may be learned and updated incrementally, based on the identification of new signals as desired signals or as noise and based on the identification of signals by other systems.

Abstract: A computer-implemented method to train a video annotation machine learning process is disclosed. The method may include obtaining a video and determining that a predetermined event occurs in the video. The method may include identifying a first set of object attribute data associated with the event in the video based on a machine learning process and machine learning data. The method may include receiving a second set of object attribute data of the event in the video from a user or external source. The method may also include comparing the first set of object attribute data with the second set of object attribute data. The method may include validating the quality of the first set of object attribute data when the first set of object attribute data is determined to be sufficiently similar to the second set of object attribute data.

Abstract: A computer-implemented method to identify an object in a video is disclosed. The method may include obtaining a video and receiving an indication of one or more foreground regions in the video from a user module based on a user selection within the user module. The method may also include receiving an indication of one or more regions of interest in the foreground regions from the user module based on a user selection within the user module. The method may include determining a human potential size in a plurality of locations in the one or more regions of interest. The method may include generating a background model based on a plurality of frames of the video. The method may also include tracking an object in the one or more regions of interest based on the background model. The method may include identifying the object as a predicted human based on the human potential size.

Abstract: A computer-implemented method to compare events from videos including monitoring two or more videos and identifying a first event in a first video, determining a first feature description of the first event, a first location of the first event, and a first time stamp of the first event, identifying a second event in a second video of the two or more videos, determining a second feature description of the second event, a second location of the second event, and a second time stamp of the second event, comparing the first and second feature description, the first and second location, and the first and second time stamp. The method may include classifying the first event and the second event as correlated events determined to be sufficiently similar and classifying the first event and the second event as not correlated events when determined not to be sufficiently similar.

Abstract: A computer-implemented method to train a video annotation machine learning process is disclosed. The method may include obtaining a video and determining that a predetermined event occurs in the video. The method may include identifying a first set of object attribute data associated with the event in the video based on a machine learning process and machine learning data. The method may include receiving a second set of object attribute data of the event in the video from a user or external source. The method may also include comparing the first set of object attribute data with the second set of object attribute data. The method may include validating the quality of the first set of object attribute data when the first set of object attribute data is determined to be sufficiently similar to the second set of object attribute data.

Abstract: A computer-implemented method to identify an object in a video is disclosed. The method may include obtaining a video and receiving an indication of one or more foreground regions in the video from a user module based on a user selection within the user module. The method may also include receiving an indication of one or more regions of interest in the foreground regions from the user module based on a user selection within the user module. The method may include determining a human potential size in a plurality of locations in the one or more regions of interest. The method may include generating a background model based on a plurality of frames of the video. The method may also include tracking an object in the one or more regions of interest based on the background model. The method may include identifying the object as a predicted human based on the human potential size.

Abstract: A computer-implemented method to compare events from videos is disclosed. The method may include monitoring two or more videos and identifying a first event in a first video of the two or more videos. The method may include determining a first feature description of the first event, a first location of the first event, and a first time stamp of the first event. The method may also include identifying a second event in a second video of the two or more videos. The method may include determining a second feature description of the second event, a second location of the second event, and a second time stamp of the second event. The method may include comparing the first feature description with the second feature description, the first location with the second location, and the first time stamp with the second time stamp.

Abstract: A computer-implemented method to train a video annotation machine learning process is disclosed. The method may include obtaining a video and determining that a predetermined event occurs in the video. The method may include identifying a first set of object attribute data associated with the event in the video based on a machine learning process and machine learning data. The method may include receiving a second set of object attribute data of the event in the video from a user or external source. The method may also include comparing the first set of object attribute data with the second set of object attribute data. The method may include validating the quality of the first set of object attribute data when the first set of object attribute data is determined to be sufficiently similar to the second set of object attribute data.

Abstract: A computer-implemented method to notify a user about an event is disclosed. The method may include monitoring a video and determining that an event occurs in the video and identifying one or more event data related to the event. The method may include comparing the one or more event data with one or more event data previously stored in a false alarm database. The method may include classifying the event as a false alarm event when the one or more event data is determined to be sufficiently similar to the event data previously stored in the false alarm database and classifying the event as not a false alarm event when the one or more event data is determined not to be sufficiently similar to event data previously stored in the false alarm database. The method may include notifying the user about the event when the event is classified as not a false alarm event.