Optics

• Industrial grade, high stability, high-end luxury appearance
• Deep learning algorithm model based on UNV independent intellectual property rights, face recognition accuracy rate > 99%, false rate < 1%
• Built-in deep learning dedicated chip, supports local offline recognition, 20,000 face capacity, face white list (1∶ N)
• Fastest recognition time 0.2 seconds, various model merge mode are used to reduce false rate and increase pass rate
• Built-in 16G EMMC front end storage, stable and reliable, up to 100.000 event capacity 2MP low illumination wide-angle camera, WDR and F1.6 large aperture lens for capturing high quality image with various complex lighting scenes
• Built-in mic and speaker for ensuring audio input and output
• Suggested height for face recognition: between 0.8m and 2.2m
• Face recognition distance: 0.5m to 1.5m
• Support live detection based on deep learning algorithm, effective against fraud such as photo and video
• Support face metering and human metering for fast adapting to ambient light
• Support screen sleep mode, keep the minimum brightness to prevent glare at night
• Support adding up to 6 photos per person of the bottom library, greatly improve face recognition speed and pass rate
• Support video capture, support ONVIF
• Dual network ports in series, reuse original network, support escape when power outage Support face authentication, password authentication to control door open
• Two-way audio with indoor monitor
• Support direct control door lock, exit button, door contact detection to implement access control management
• Support tamper protection, door open timeout and time exceed alarm function to keep door opening during fire alarm active