Localized edge computing Box (ZS-AIBOX-HIS3559A)

Localized edge computing Box (ZS-AIBOX-HIS3559A)It integrates a variety of edge computing intelligent algorithms such as panoramic stitching, target detection, target tracking, target recognition, alarm linkage, and information tagging, which can be applied to different combat scenarios such as air, ground, and water, and has the ability to detect, recognize, and track multiple targets such as people/vehicles/animals/aircraft/ships/UAVs.

Localized edge computing Box (ZS-AIBOX-HIS3559A)Enable the security system to haveObserving the Six PathsThe practical effect of listening to all directions and being able to make good decisions effectively enhances the practicality of the system, eliminates false alarms, reduces false alarms, and improves monitoring efficiency,Smooth upgrade from traditional security to intelligent security.

Automatic recognition of target types, filtering out false alarms caused by wind and grass movements as well as various interference factors in the external environment (such as trees, rocks, buildings, flags, railings, flying insects, rainwater, etc.), accurately detecting targets such as personnel/vehicles/animals/aircraft/ships and drones, and automatically overlaying and storing target types in videos.

Call the tracking algorithm to continuously track the target, lock the target in a certain area of the central screen, automatically correct the tracking frame throughout the tracking process, and automatically reselect the target when tracking errors occur. At the same time, the lens adapts to zoom to ensure good tracking performance.

Support setting detection conditions according to specific requirements, including target wandering, retention, retrograde movement, gathering, intrusion, crossing boundaries, etc. It can mark targets in real time and upload alarm information.

Communication with various external devices is achieved through interfaces, enabling access to various alarm sources and coordinated handling of alarms. When an external device detects an alarm, based on the location information of the alarm, it can guide the photoelectric device to automatically jump, confirm the event twice, automatically identify and track the target, and record the entire process of the event.

▲ Ship type identification

▲ Identification of crop growth period

Using deep residual convolutional neural network as the basic model, through target recognition and feature extraction/comparison, the multi-dimensional matching degree of the target is calculated based on the Euclidean distance calculation method, and the target attributes are judged. For example, facial/license plate recognition, vehicle/ship classification, and plant growth period recognition.

▼

Support real-time splicing and output of multiple 4K video frames, with frame synchronization between each video frame, and no ghosting, misalignment, or missing content at the splicing point. Front end splicing greatly reduces the bandwidth pressure on network transmission.

Support integration with external business systems on site (such as ADS-B, AIS, GPS, etc.) to obtain multi-dimensional information about targets and display them in videos.