Big Data AI Analysis Software

With the booming trend of video surveillance cameras in last decade, high-definition networking video surveillance systems have been widely used for auxiliary management and anti-terrorism security over the world. In case of incidence, however,  the monitoring process of the surveillance video is time-consuming and labor-intensive, whether it is event precaution, real-time monitoring in the matter, or security analysis in hindsight. Furthermore, large amount of video data are lost without effective information extraction, resulting in the inefficiency of the existing video surveillance systems.

Due to the urgent need of an automatic video analysis system, our company have developed “GTAI-VIWE”, which is a video content structuring and analysis system as intelligent as the human vision system. As the core system of government supervision, enterprise management and social security, it can extract the useful information during the whole surveillance process without losing any clue for event analysis. This system is an important information module for the infrastructure of smart city, smart transportation and smart security.

After the simply configuration of multiple video source access, GTAI-VIEW can do lots of miracles. First, it can accurately detect and recognize various types of objects, and segment the object boundary in pixel-level as well. Second, a number of detailed attributes of objects are displayed, including human gender, age, dressing style, as well as color and texture of handbag and other accessories.  Third, with the cutting-edge technologies of object tracking and clustering algorithms, the object retrieval process is fast yet accurate. Fourth, with the novel cross-view person re-identification technology, any objects can be steadily tracked in the whole smart city. Last but not least, all the structured data are stored in a distributed big-data platform, which enables fast playback of the target object and alarm of suspicious incidents according to  preset rules.

In the field of smart transportation, GTAI-VIEW has advantage to manual monitoring as it is able to recognize and count motor vehicles, non-motor vehicles and pedestrians on all existing roads at an overall accuracy of above 90%, on a 24 hours by 7 days basis. By extracting the information from the video content of all roads and blocks, a group of census data can be acquired, such as traffic directions of all vehicle types, motion trajectory, and congestion level. All these data are beneficial to effective decision of a smart transportation system.

GTAI-VIEW can be utilized to reconstruct the information flow and business flow of video surveillance and analysis, and is not limited to accurate video content structuring and analysis for smart transportation. It can be extended to other applications such as social security, anti-terrorism, property management, and targeted advertising according to user profiles. GTAI-VIEW, the smart choice to promote video surveillance system from “information” level to “intelligence” level! GTAI-VIEW, the foundation to realize the database management of forensics video data!

* Faceless discrimination

The system can support faceless discrimination even suspect covers face or other factor which cause unable to get the face detail at scene. It can still precisionly locate to target base on overall charactertics.

* Human detection accuracy

Recall and accuracy rate of more than 90% for human targets in the video.

* Human Trajectory Tracking

Track and restore cross- camera trajectory according to the overall characteristics of object in video. Support real-time export of target character trajectory video and support simultaneous tracking of multiple objects.

* Cross-camera trajectory tracking

The system can automatically splicing the object across the multi-camera trajectory video. It can also restore all the behavior of the object during the trajectory of video. The system would not effected by suspect changed clothes or bag .

* Video Searching Function

Support Search base on a picture which suspect picture or screenshot in video for intellegent searching.  It would automatic matching similar target at different camera.

* human Hot-spot diagnosis

System provide human hot-spot diagnosis and traffic statitic function

* Restricted area intrusion detection

system supports visual fens setting. It would auto alart while human break in

* Vehicle Traffic Statistic

The system supports the vehicle traffic statistics function. It can record the traffic flow information. Through the statistics of the traffic flow, end user can review  the “real-time vehicle quantity” and “historical vehicle quantity” information in a certain period of time.

* Vehicle characteristics identified

The system can identify the vehicle models (buses, trucks, cars, non-motor vehicles) in the monitored area,structure the past vehicle information in the video and classify the statistics to facilitate the search and investigation of suspect vehicles after the incident for police.

* Vehicle behavior analysis and statistics

Support behavior analysis and statistics for real-time or historical vehicles, including behavior analysis and quantitative statistics of straight-through vehicles, left-turn vehicles, and right-turn vehicles, and provide data reference for future traffic light optimization and viaduct construction.

* Cross Camera vehicle trajectory analysis.

Supporting cross-camera vehicle trajectory tracking under the condition that the vehicle's detailed feature information is relatively clear, supporting the display of motion trajectories from GIS maps, and supporting viewing of videos from GIS maps.

* Camera Extending Ability

The system support no less than 1000 PCS of camera for extending.