Visual cues can be used alongside GPS positioning and digital maps to improve understanding of vehicle environment in fleet management systems. Such systems are limited both in terms of bandwidth and storage space, so minimizing the size of transmitted and stored visual data is a priority. In this article, the authors present efficient strategies for computing very short image representations suitable for classifying various types of traffic scenes in fleet management systems. They anticipate that the set of interesting classes will change over time, so they consider image representations that can be trained without knowing the labels of the target data set. They empirically evaluate and compare the presented methods on a contributed data set of 11447 labeled traffic scenes. Their results indicate that excellent classification results can be achieved with very short image representations and that fine-tuning on the target data set image data is not mandatory. Image descriptors can be as short as 128 components while still offering good performance, even in the presence of adverse weather or illumination conditions. This article proposes a new personal-based hierarchical driver monitoring system (HDMS). During driving, the first layer of the proposed HDMS detects normal and abnor-mal driving behavior based on normal personal driving models represented by sparse representations. When abnor-mal driving behavior is detected, the second layer of the HDMS further determines whether the behavior is drowsy driving behavior or distracted driving behavior. The experimental results obtained for three data sets show that the proposed HDMS outperforms existing state-of-the-art DMS methods.