With embedded deep learning based algorithms, the camera is able to give the best shot of a target face through detecting, capturing, grading and selecting. The camera uses face exposure function to dynamically adjust face area exposure of captures and ensures high face picture quality.

Perimeter Protection

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 filter out the mistaken alarm caused by the interference of leafs, lights, animal, flag, etc.

Multi-Target-Type Detection

With the embedded deep learning algorithms, the camera detects and captures the face, human body, vehicle in the specified region.

Queue Management

With embedded deep learning based algorithms, the camera detects queuing-up people number and waiting time of each person. It can generate reports to compare the efficiency of different queuing-ups and display the changing status of one queue, and supports raw data export for further analysis.

Regional People Counting

With the embedded deep learning algorithms, the camera supports people density detection and will upload detection data through scheduled uploading, number of people change uploading and congestion level uploading. It also supports number of people exception detection and waiting time exception detection.

On/Off Duty Detection

With the embedded deep learning algorithms, the camera supports absence detection and on/off duty detection. It can detect the on/off duty status and people number changes in a predefined area.

Heat Map

The camera can generate a graphic description of visits (by calculating amount of people or amount of dwell time) in a configured area.

Multi-Dimension People Counting

With the embedded deep learning algorithms, the camera integrates multiple intelligences. It counts persons and compares them with the built-in face picture library to remove duplicates. It counts persons and reports an alarm simultaneously to achieve both the entrance control and people counting.

Hard Hat Detection

With the embedded deep learning algorithms, the camera detects the persons in the specified region. It detects whether the person is wearing a hard hat, and reports an alarm if not.

Blue glass module to reduce ghost phenomenon

Focal Length ＆ FOV

8 to 32 mm, horizontal FOV: 42.5° to 15.1°, vertical FOV: 23.3° to 8.64°, diagonal FOV:

49.6° to 17.3°

8 to 32 mm: F1.7 to F1.73

DORI

2.8 to 12 mm: D (Detect): 45 m, O (Observe): 17.9 m, R (Recognize): 9 m, I (Identify):

4.5 m

8 to 32 mm: D (Detect): 112.7 m, O (Observe): 44.8 m, R (Recognize): 22.6 m, I (Identify): 11.3 m

Tele:

2.8 to 12 mm: D (Detect): 111.8 m, O (Observe): 44.3 m, R (Recognize): 22.4 m, I (Identify): 11.2 m

8 to 32 mm: D (Detect): 300 m, O (Observe): 119.0 m, R (Recognize): 60 m, I (Identify):

30 m

8 to 32 mm: 50 m

Model Specification

Model type: detection model, classification model, mixed model (detection model and classification model)

60 Hz: 60 fps (1920 × 1080, 1280 × 960, 1280 × 720)

60 Hz: 30 fps (704 × 480, 640 × 480)

60 Hz: 30 fps (1920 × 1080, 1280 × 720, 704 × 480, 640 × 480)