Neural network object detector
Identifies and classifies objects
A neural network object detector offers clear identification of the following object types on image: person, car, bus, motorcycle, bicycle, dog, train, and aircraft. Detector operation algorithm includes a unique neural network ensuring high reliability of identification of such objects. The identification accuracy cannot be affected by weather conditions, day/night, illumination and etc.
The unique feature of the neural network detector is that it can work with PTZ-cameras during Guard Tour
This detector can be used to prevent parking violations, detect person in a hazardous area and other applications where object type identification reliability plays an essential role. Neural network training capability allows company's engineers to create systems that can identify any user-defined objects types.
A neural network object detector refers to the category of detectors that use object identification algorithm based on high-accuracy neural networks. The object detector can quickly and with minimal error determine objects of specific types within camera's field of view.
Neural networks can deliver great advantages for video surveillance applications: from retail shops to «Safe City» solutions. For security systems market transition from assumptions based on mathematical analysis of the geometry and color characteristics of a set of pixels to pattern recognition can be considered as a serious step in the situational analysis development. Analysis results clearly show people crowd, or person on the rails, or truck near the gate. Neural network technology can be effectively used for searching and analyzing data during accident investigations. Also, you can sort objects by classes to save time and obtain more clear results.
Neural network objects detector operation and configuration
When system detects an object of specific type on the live video from camera, this object image on the screen will be marked with rectangular frame with its type and number in the queue.
You can configure automatic response to the event, for example, system can activate recording of video and audio signal from the camera, send SMS-message or email, add record to video archive, launch application, produce audio alarm, generate report, send command to the actuating device or assign other event-based actions.
The VideoNet system allows to configure parameters individually for each of the detection zones of the object detector, including entire image or selected image area.
You can configure detector for a specific camera and select type of object to be detected. The detector provides clear identification of the following object types in image: person, car, bus, motorcycle, bicycle, dog, train, and aircraft.