● 1/1.8” Progressive Scan CMOS
● 1920 × 1080 @ 60fps
● MJPEG up to 1920 × 1080 @ 30fps
● 2.8 to 12 mm/8 to 32 mm motorized lens
● Color: 0.002 Lux @ (F1.2, AGC ON), 0.004 Lux @ (F1.6,AGC ON), 0 Lux with IR
● H.265, H.265+, H.264, H.264+
● 140dB WDR
● IR range: up to 30 m
● Alarm 1 input/1 output, audio 1 input/1 output, RS 485
● 5 streams and up to 5 custom streams
● 6 behavior analyses, 3 exception detection, and face detection
● Built-in microSD/SDHC/SDXC card slot, up to 256 GB
● Metadata of intrusion detection, line crossing detection, region entrance detection, region exiting detection, unattended baggage detection, object removal, face capture and queue management are supported.
Smooth streaming offers solutions to improve the video quality in different network conditions. For example, in poor network conditions, adapting to the detected real-time network condition, streaming bit rate and resolution are automatically adjusted to avoid mosaic and lower latency in live view; in multiplayer network conditions, the camera transmits the redundant data for the self-error correcting in back-end device, so that to solve the mosaic problem because of the packet loss and error rate.
Metadata uses individual instances of application data or the data content. Metadata can be used for third-party application development.
With embedded deep learning based algorithms, the camera is able to give the best shot of a target face through detecting, tracking, capturing, grading and selecting. The procedure reduces the happening of mistaken capture, and thus gets the best face shot, improving the accuracy rate of face comparison by the back-end devices. The camera uses face exposure function to dynamically adjusts face area exposure of captures and ensure high face picture quality.
With embedded deep learning based target detection and classification algorithms, the camera carries out the duty of perimeter protection, monitoring the actions of line crossing, intrusion, region entrance and region exiting. The algorithms greatly reduce the mistaken alarm caused by the interference of leafs, lights and etc.
The camera supports a wide voltage range of 10 VDC to 48 VDC. If the voltage instability occurs, the camera still works properly. The camera supports reverse polarity protection which can avoid the camera malfunction caused by false operation.
With embedded deep learning based algorithms, the camera detects queuing-up people number and waiting time of each person. The body feature detection algorithm helps filter out wrong targets and increase the accuracy of detection.