Abstract: System and method for adjusting side mirrors capture, by a primary camera, a facial image of a driver; estimate a 3D eye location with respect to a 3D coordinate of the primary camera based on the captured facial image; map the estimated 3D eye location to a respective set of pitch and yaw of the side mirror based on a look up table; and rotate the side mirror to a target position in accordance with the respective set of pitch and yaw. The lookup table includes a plurality of rows, each containing a pair of a key and a set of values. The key is a set of three parameters of 3D line of locations where the driver can observe an optimal view behind the vehicle, and the set of values includes a set of pitch and yaw of the side mirror corresponding to the 3D line of locations.

Abstract: A method for adjusting a side mirror of a vehicle includes capturing, by a primary camera provided in front of a driver of the vehicle, a facial image of the driver; estimating a 3D eye location with respect to a 3D coordinate of the primary camera based on the captured facial image; mapping the estimated 3D eye location to a respective set of pitch and yaw angles of the side mirror based on a lookup table; and rotating the side mirror to a target position in accordance with the respective set of pitch and yaw angles. The lookup table includes a plurality of rows, each row containing a pair of a key and a set of values. The key is a 3D eye location, and the set of values includes a set of pitch and yaw angles of the side mirror corresponding to the 3D eye location.

Abstract: The present invention relates to a method and a system for training a machine learning model for face recognition. The method comprising generating a training dataset; providing a teacher model that comprises a teacher backbone and a teacher head; iteratively training the teacher backbone and the teacher head using the training dataset; setting the machine learning model to include a lightweight backbone and a lightweight head; copying trained parameters of the trained teacher head to the lightweight head; and iteratively training the lightweight backbone using the training dataset.

Abstract: A method of clustering using encoder-decoder model based on attention mechanism extracts image features, clusters to form image feature vector clusters, and based on the cosine similarity score between the image feature vectors to arrange each image feature vector cluster into an image feature vector sequence. The image feature vector sequence includes cosine distance encoding vectors concatenated with respective image feature vectors and is used as the input data sequence in encoder and decoder neural network models to generate an output data sequence from the input data sequence. The output data sequence is a binary sequence having values of 1 or 0 at a position denoting that the image corresponding to the position is or is not in the same cluster with respect to the center image of the cluster.

Abstract: A driver monitor system includes an image data acquiring module configured to acquire a plurality of image data from a data collection module; a training module configured to train a plurality of teacher models to obtain a plurality of feature groups using the plurality of image data, and transfer a plurality of pieces of knowledge obtained from the plurality of feature groups to a plurality of student models, respectively; and at least one edge device comprising the plurality of student models configured to use a pipeline design pattern with multiple threads to make a warning.