Mathematical models of both the ultrasonic and magnetic sensors were constructed to first understand the intrinsic characteristics of the individual sensors and also to provide a means of simulating the performance of the combined sensor system and to facilitate algorithm development. Preliminary algorithms that utilized this sensor fusion were developed to make inferences relating to vehicle proximity as well as type. It was noticed that while it helped alleviate the limitations of the individual sensors, the algorithm was affected by high occurrences of false positives. Also, since sensors carry only partial information about the surrounding environment and their measured quantities are partially corrupted with noise, probabilistic techniques were employed to extend the preliminary algorithms to include these sensor characteristics. These statistical techniques were utilized to reconstruct partial state information provided by the sensors and to also filter noisy measurement data. This probabilistic approach helped to effectively utilize the advantages of sensor fusion to further enhance the reliability of inferences made on vehicle identification.

In summary, the study investigated the enhancement of vehicle identification through the use of sensor fusion and statistical techniques. The algorithms developed showed encouraging results in alleviating the occurrences of false positive inferences. One of the several applications of this study is in the use of ultrasonic-magnetic sensor combination for advanced traffic monitoring such as smart toll booths.

This paper presents results of applying these techniques in a multi-disciplinary vehicle sensing research project involving sixteen undergraduates over a three-year period. Although individual student time on the project ranged from only three to twelve months, all students were able to contribute to the project. Student activities were grouped into individual and small group tasks, each with specific goals and timetables. Rigorous electronic documentation and data storage techniques were employed to enable new students to come up-to-speed quickly. A mix of course credits, supplemental pay, and an intercollegiate competition were used to maintain student motivation. Project successes include high student satisfaction, conference papers, a demonstration pre-crash sensing system, and participation in an international student competition.

One way to perform research with heavy undergraduate involvement is to select an appropriate topic and develop a stable undergraduate research group that builds and maintains knowledge over time. Such a research group requires tasks encompassing many skill levels, a steady funding source, and an orderly progression of short-term goals for each student. Web based communication and archiving tools can be used to share and pass on data, references and information. Selecting the research topic, obtaining funding, and initially training and organizing the student team are the major start-up tasks. The benefits for the students and the faculty member are worth these efforts.