With the rising ownership of new energy vehicles (NEVs), accurate road traffic emission estimations are crucial. This study combined mixed traffic flow and license plate recognition (LPR) using improved 3D convolutional neural network (3D-CNN) and Transformer models. The 3D-CNN model is designed for vehicle localization and traffic flow data acquisition, while the Transformer-based LPR model accurately recognizes license plates, distinguishing NEVs from conventional vehicles. The overall model is validated by the training and test datasets, and then with field application along a primary arterial segment in the South 2nd Ring Road, Xi’an, China. The results demonstrate capability for the traffic emission approximation of the mixed traffic flow including new energy vehicles, revealing that mixed traffic flow identification plays an important role in road emission approximation. Results and procedures of the study may provide benchmark for the subsequent research and the verification of related transportation policies.