Method by a computer of a computing system having a plurality of camera sensors and a camera sensor control system is provided. A gesture input event is identified that is detected by a camera sensor of the camera sensors. Each camera sensor routes video captured by the camera sensor to a data storage system. The first gesture input event is identified as corresponding to a defined attention-based gesture performed by a user. A time the first gesture input event was identified is determined. Video stored in the data storage system is fetched using the time that is determined as a pointer. An indication of the first gesture input event and the video that is fetched is transmitted towards an emergency call center (ECC). A trigger word or sound may be detected, and an indication of the trigger word or sound may be transmitted towards the ECC.