This work aims to design and develop an efficient visual based vehicle re-identification system for International Road Dynamic. Vehicle re-identification, which is defined as: Identifying, classifying, and position-referencing a vehicle of interest through images/video streams collected via a network of camera stations, plays a key role towards developing intelligent transportation system.
Information is everywhere, especially in the commercial vehicle industry. Vehicles may be classified by number of axles/tires. There are several text- and label-based classification systems: for dangerous goods transport (HAZMAT); vehicle safety code compliance (CVSA); and general identification and tracking (license plates, USDOT numbers). Employing humans to perform simple classification and recognition tasks can be impractical. However, explicitly programming these tasks can be challenging.
A laser-optics vehicle profiling system will be designed and developed in this project. The image of a laser line projected onto the surface of a vehicle from a vantage point will be used to make metric measurements on the vehicle and to develop a 3D model of it.
It is conjectured that this setup would work superior to the existing time-of-flight laser profilers in terms of accuracy, resolution, and speed of operation.
Multiple laser-optics scanners located at optimal locations in an inspection station can provide a panoramic 3D model of the vehicle and also provide measurements.
It is very useful to build an automatic computer system to recognize the types of vehicles passing a checkpoint given some easy-to-get data about the vehicles, such as the distances between axles, the weights on each axle. Such a system has many applications, for example, in monitoring traffic volumes and identifies the type of vehicle, which will be helpful in budgeting road maintenance costs. The main goal of this project is to develop a better methodology for cluster analysis with application to the vehicle detection problem. The simplest clustering technique is the K-means clustering.
Join a thriving innovation ecosystem. Subscribe now