License Plate Recognition and Vehicle tracking solution
Our Visual Recognition Software for License Plate Recognition is a specialized application in the field of Visual Recognition. Visual Recognition, as a technology in general, transforms recorded images, printed characters, numbers and letters to match with a reference database to trigger digital information for printing, duplication and data management. Our recognition engine enables reading of license plates from many image sources remarkably fast and with the highest recognition accuracy in its class. It offers country-independent recognition of various characters, as well as reflective, non-reflective, and personalized and special interest plates that are typical in many Indian states. Toll collection and congestion charging systems, traffic monitoring and security, speed measurement, bus lane and traffic light enforcement, parking or access control and many other systems can benefit from the fast, exact, automatic identification and recognition capabilities from our engine.
Navigation & Proximity Alerts: Route following using the audiovisual AR concepts were more accurate in day and night conditions as compared to the baseline. Accuracy was improved using haptic during night time only. The results showed that the workload decreased for all the AR concepts and that audio and visual AR for day and night navigation and haptic AR for night navigation were rated in the top 10% of technologies tested for system usability. Cue-in: None of the AR technologies performed better than the baseline radio call for the cueing tasks. The visual and audio AR solutions were both liked by the users, but the trial showed how the lack of angular precision had a negative impact on task performance. The audio and visual AR did provide instant cues as compared to the radio call baseline, where it took approximately 10 seconds before a target was resolved.
See-Through Vehicle: The results indicated that the system used caused an increased workload against the baseline, but scored higher on task performance and system usability. Indirect Fire Augmentation: Simulated indirect fire detonations could be used to provide appropriate AR simulation associated with the detonation. The ‘own’ position of the soldier will need to be known to determine their relative position (heading and range) to the detonation. Different combinations of visual, auditory and haptic methods could be used to provide appropriate.
Stimulations associated with the detonation effects. Entity Injection: Virtual targets, neutral or friendly forces could be provided via the use of AR. One of the greatest challenges will be the ‘registration’ of the virtual entity (i.e. does the entity appear to be in a plausible location, such as closely following the terrain for a land vehicle). Target occlusion will also be a challenge (i.e. is the entity hidden behind a physical feature or other Direct Fire ‘Crack Thump’ Augmentation: Auditory AR could be applied to simulate the sonic ‘crack’ of around passing close by. Direct fire weapon effects simulation can detect near misses. However, because there is no actual round, there is no stimulation associated with the passage of the round.
This concept could obtain information from the soldier’s tracking equipment which would detect the near miss. The critical aspect is the timing — the delay between the crack (from the round) and the thump (from the weapon fire) provides an indication of the range of the engagement.
Vehicle tracking is a technology that uses Adaptive background subtraction uses the current frame and the reference image. Difference between the current frame and the reference frame is above the threshold is considered as moving vehicle.
By using the cameras installed near the signals, on highways, etc. the flow of vehicles can be monitored and the type of vehicle passing through the camera view can be monitored.
This data gathered at each camera point can then be collated and analysed and used for multiple traffic monitoring purposes
The detection and tracking and counting of moving vehicle can be extended to real-time live video feeds. Apart from the detection and extraction, process of recognition can also be done.