System and method of identifying vehicle brand and model

A Computing system for identifying a brand and a model of a vehicle, the computing system comprises:

• a processor;
• and
• a memory communicatively coupled to the processor, wherein the memory stores a processor instructions, which, on execution, causes the processor to perform operation comprising:
• obtaining a plurality of video frames with at least one vehicle in the plurality of video frames from at least one video capturing device, wherein obtaining the plurality of video frames comprises modifying a count associated with the plurality of video frames by performing a frame interpolation when the at least one vehicle moves at a speed higher than a certain speed;
• and
• detecting one of a presence or an absence of a text associated with the at least one vehicle in the plurality of video frames;
• upon detecting the presence of the text, determining at least one of the brand and the model of the at least one vehicle in the plurality of video frames by performing at least one of:
• accumulating the text in the plurality of video frames associated with the at least one vehicle based on image processing techniques and character recognition techniques;
• and
• identifying at least one of the brand and the model of the at least one vehicle based on an accumulated text;
• upon detecting the absence of the text, performing by the computing system:
• determining the brand of the at least one vehicle in the plurality of video frames based on a logo associated with the at least vehicle, wherein the logo is identified using a first convolution neural network from the plurality of video frames.

A non-transitory computer readable medium including instructions stored thereon that when processed by at least one processor cause a device to perform operations comprising:

• obtaining, by a computing system, a plurality of video frames with at least one vehicle in the plurality of video frames from at least one video capturing device, wherein obtaining the plurality of video frames comprises modifying a count associated with the plurality of video frames by performing a frame interpolation when the at least one vehicle moves at a speed higher than a certain speed;
• and
• detecting, by the computing system, one of a presence or an absence of a text associated with the at least one vehicle in the plurality of video frames;
• upon detecting the presence of the text, determining, by the computing system, at least one of the brand and the model of the at least one vehicle in the plurality of video frames, by performing at least one of:
• accumulating the text in the plurality of video frames associated with the at least one vehicle based on image processing techniques and character recognition techniques;
• and
• identifying at least one of the brand and the model of the at least one vehicle based on an accumulated text;
• upon detecting the absence of the text, performing by the computing system:
• determining the brand of the at least one vehicle in the plurality of video frames based on a logo associated with the at least one vehicle, wherein the logo is identified using a first convolution neural network from the plurality of video frames.