• With UNV deep learning algorithm model,accuracy rate > 99%, false rate < 1%, fast recognition speed (up to 0.2s)

• Built in deep learning chip allows local offline recognition, smart recognition capacity: 10,000

• Fastest recognition time 0.2 seconds, various model merge mode are used to reduce false rate and increase pass rate

• Support screen sleep mode, keep the minimum brightness to prevent glare at night

• Support card, password authentication to control door open

• Built in 4G EMMC front end storage, stable and reliable, up to30,000 events capacity (with images)

• Support direct control door lock, exit button, door contact detection to implement access control management

• Supports real time visitor viewing via the indoor station or APP, and enables remote door unlocking and video intercom communication

• Support tamper protection, support door opening timeout, support time exceeding alarm, support keeping door opening while fire alarm active.