STAYING SAFE.
BACK TO BUSINESS SOLUTIONS
NEW AI THERMAL DETECTOR AITD-820HT
Adopts an AI chipset, large thermal sensor array and latest algorithm which provides cutting-edge face recognition and body temperature detection, with the ability to detect even with a mask on.
FEATURES & TECHNOLOGY
Powerful AI
Chipset
With ISP technologies, images are able to avoid shadowing, shortening the detection time.
FAST DETECTION
(0.3s Temperature
+ face ID)
Auto Forehead
Identify
With best AI chipset and
algorithm in the world to detect foreheads
HIGH ACCURACY
(±.5ºF, 99.9%)
Best Algorithm
Powered by the best
Algorithm, can recognize
people with masks and can
detect people without masks
then push alerts.
Facial Recognition
With dual-lens cameras capturing, you can increase your accuracy of facial recognition.
LONG DETECTION
RANGE
(1 ft. ~ 4 ft.)
SPECIFICATION
HARDWARE SPECIFICATIONS
Sensor Type
Infrared Thermography camera
Thermal measurement distance range
Thermal measurement accuracy
Uncooled infrared focal plane array
120*90
1 FT. - 4 FT.
±0.5ºF
HARDWARE
Processer
OS
Storage
LCD
AI chipset ARM Cortex-A7 quad-core, 4 x high performance CEVA DSP
Linux
8GB EMMC+1GB DDR4
7 inch, 1024*600 resolution
CAMERA
Sensor
WDR
FoV (Diagonal/horizontal/ vertical)
Iris
Focus length
Dual 2Mp, low lux sensor
≥120dB
73°/65°/40°
F2.0
4.3mm
PERFORMANCE
Anti-spoofing
Face Detection range
Face library
Attendance Record
Face angle
Anti-electronic screen, video, mask hacker attack
1.5 ft. - 6.5 ft., lens adjustable
50,000 (default)
50,000
horizontal 30 degree, vertical 30 degree
CONNECTIVITY
Access control
Power supply
Power consumption
Ethernet
Wifi
USB
Push out
DC12V , 2A ( 9 -16V DC)
Less than 20W
1 pcs RJ45 10M / 100M Ethernet
2.4G Wi-Fi
1 pcs USB 2.0
GENERAL
Ambient Working Temperature
Dimensions
-40° F - 100° F
4.75"X 8.9" X 1.3"
ALGORITHM PARAMETERS
Face Recognition
Face recognition
Algorithm accuracy
Angle requirements
Face minimum pixels
Local recognition: 50,000 (default )
99.9%@0.01% （The accuracy rate is 99% under the 10,000th false alarm rate）
95%@0.0001% （The accuracy rate is 95% under the one-millionth false alarm rate）
Yaw ±30°，roll ±30°，pitch ±15°
Face size above 80 * 80 pixels
Anti-spoofing
Angle requirements
Face pixel requirements
Algorithm accuracy
Anti-spoofing category
Yaw ±30°，roll ±30°，pitch ±15°
Interpapillary distance 50 pixels and above
98%@0.01% （Real pass rate@Dummy pass rate）
Pictures, videos, coated paper, fake face models, etc.
Face detection and tracking
Number of people captured
Snap frame rate
Minimum face size
Adaptation angle
More than 30 people / frame
25fps
30*30
Yaw ±45°，roll ±45°，pitch ±30°
Face attribute
Item
Algorithm accuracy
Gender, age, glasses, facial expression (angry, calm, happy, sad, surprised), mask, ethnicity, beard, ethnicity, hat detection, helmet detection
Age accuracy (± 5 years old): more than 85%;
Gender accuracy: more than 96%;
Skin color accuracy: more than 97%;
Beard accuracy: more than 97%;
Glasses accuracy: more than 98%;
Mask accuracy: more than 98%;
Hat accuracy: more than 97%;
Expression accuracy: more than 88%
AVAILABLE IN:
WALL MOUNT
TABLE STAND
