AI & ML

Deploy high-performance AI-enabled edge devices equipped with specialized hardware accelerators at the checkpoint. These devices should be capable of processing video streams from multiple cameras in real-time.

Utilize edge-based computer vision algorithms and deep learning models to detect vehicles within the camera's field of view. Extract the number plates from the detected vehicles using ANPR technology, which can accurately read and interpret alphanumeric characters on the plates. Perform this processing at the edge devices to minimize latency.

Train a machine learning model using a labelled dataset to classify the detected vehicles as commercial freight carriers or non-commercial vehicles. The model should be optimized for edge deployment and capable of running efficiently on the edge devices.

Perform real-time verification of the extracted number plate by comparing it against a local database stored within the edge devices. The local database should contain registered vehicle information to process.

Utilize the edge computing capabilities to query the central Eway bill database. Check if an Eway bill has been raised against the identified vehicle number and validate its authenticity in real-time.

If both the number plate authenticity and Eway bill verification yield positive results, consider the vehicle as a legitimate commercial freight carrier. In case of any discrepancies or negative results from either verification step, generate alerts to the relevant departments, such as the GST department or law enforcement agencies, to take appropriate action.

Aggregate the collected data at the edge devices and periodically transmit it to a central server for analysis and reporting. Perform data analytics on the centralized data to identify patterns, trends, or anomalies related to commercial freight carriers passing through the checkpoint. Generate comprehensive reports summarizing the results for better insights and decision-making.