The present disclosure generally pertains to image sensor control circuitry for event-based controlling of an image sensor, the image sensor control circuitry being configured to: obtain events from a plurality of event-based vision elements of an event-based vision sensor; determine event groups based on an event-detection property; and generate an imaging control signal for controlling the imaging elements of the image sensor based on the event groups, for imaging with imaging element groups corresponding to the event groups.

System and method for detection of pre-drowning and drowning events based on underwater images are disclosed.

A process mining system performs process mining using visual logs generated from video streams of worker devices. Specifically, for a given worker device, the process mining system obtains a series of images capturing a screen of a worker device while the worker device processes one or more tasks related to an operation process. The process mining system determines activity labels for a plurality of images. An activity label for an image may indicate an activity performed on the worker device when the image was captured. The activity label is determined by extracting information from pixels of the image and inferring the activity of the worker device from the extracted information. The process mining system generates event logs from the visual logs of worker devices and uses the event logs for process mining.

The disclosure relates improving correctional officer safety. A system can include a first camera facing a region of a correctional facility including monitored objects, the first camera configured to generate first pixel data including first pixels corresponding to the objects, a second camera in the correctional facility and facing away from the region, the second camera configured to generate second pixel data including second pixels corresponding to a person that approaches the region, and a server configured to receive the first and second pixel data through a network connection, transmit the received data to a recognition service through the network, and receive an alert from the alert service that indicates a monitoring rule associated with an object of the objects is violated, an identification associated with the person, a last known location of the person or the object, and an indication of the monitoring rule violated.

A method may include capturing, by a camera, video data that relates to operation of the automobile. The method may include storing the video data using a first data storage device that includes a first storage capacity in which older video data included in the first data storage device is overwritten by newer video data upon exceeding the first storage capacity. The method may include determining whether an event has occurred at a given time point, and responsive to determining that the event has occurred, identifying a video segment included in the first data storage device that corresponds to the event. The method may include storing the video segment using a second data storage device. The method may include identifying a reviewing entity to which the video segment may be sent based on video content of the video segment and sending the video segment to the identified reviewing entity.

In some examples, a system processes event data and video frames produced by a program during execution of the program, the event data representing user actions with respect to a graphical user interface (GUI) of the program. The system identifies an area of the GUI that corresponds to a respective user action of the user actions, wherein identifying the area of the GUI uses a first video frame before an event corresponding to the respective user action, and a second video frame after the event corresponding to the respective user action. The system identifies, based on the identified area, a test object representing a user interface (UI) element, and generates a test script for testing the program, the test script including the test object.

A method of reducing false positives and identifying relevant true alerts in a video management system includes analyzing images to look for patterns indicating changes between subsequent images. When a pattern indicating changes between subsequent images is found, the video management system solicits from a user an indication of whether the pattern belongs to one of two or more predefined categories. The patterns indicating changes between subsequent images are saved for subsequent use. Subsequent images received from the video camera are analyzed to look for patterns indicating changes between subsequent images. When a pattern indicating changes between subsequent images is detected by the video management system, the video management system compares the pattern indicating changes between subsequent images to those previously categorized into one of the two or more predefined categories. Based on the comparison, the video management system may provide an alert to the user.

System and method for determining an outcome probability of an event based on videos are disclosed. The method includes receiving the videos of an event, creating a building block model, extracting one of an audio content, a video content from the videos, analysing extracted content, generating an analysis result, analysing an engagement between speaker and participant of event, generating a data lake comprising a keyword library, computing the outcome probability of the event, enabling the building block model to learn from the data lake and the outcome probability computed and representing the at least one outcome probability in a pre-defined format.

A management server receives a request to view video content; access a stream of video content corresponding to the request; access and store, in one or more databases, metadata associated with the video content, wherein the metadata includes a plurality of detections and was generated by the video gateway device based on an analysis of the video content and previously uploaded to a remote computing device; generating and causing display of a user interface that includes: the stream of the video content, a seek bar configured to be manipulated by a user so that the user can navigate through the video content, and the metadata overlaid on the seek bar such that the plurality of detections are overlaid at locations on the seek bar corresponding to when the plurality of detections were detected.

A process mining system performs process mining using visual logs generated from video streams of worker devices. Specifically, for a given worker device, the process mining system obtains a series of images capturing a screen of a worker device while the worker device processes one or more tasks related to an operation process. The process mining system determines activity labels for a plurality of images. An activity label for an image may indicate an activity performed on the worker device when the image was captured. The activity label is determined by extracting information from pixels of the image and inferring the activity of the worker device from the extracted information. The process mining system generates event logs from the visual logs of worker devices and uses the event logs for process mining.