Research on Classifiers Used to Identify Dangerous Goods Transportation Vehicles

With the continuous development of the national economy, the domestic demand for dangerous goods has also increased year by year. Once a traffic accident occurs, it will have a huge impact on the natural environment, road safety, and the safety of people’s lives and property. In addition, Advanced Driver Assistance Systems (ADAS) based on sensor technology and advanced control technology provide a good solution for car driving safety. Sensors play a very important role in advanced driver assistance systems. Commonly used sensors mainly include cameras, millimeter wave radars, lidars, etc., which can be used to obtain vehicle internal and external information. This information can help the driver complete the driving task more safely. Therefore, this paper summarizes the current research status of relevant aspects at home and abroad, and compares various vehicle identification and detection algorithms, and uses Haar-features and AdaBoost cascade classifier algorithm to identify dangerous goods transportation vehicles. A total of four classifiers are trained, and the number of positive samples of each classifier is 800, 1200, 1600 and 2000 respectively. Through comparative analysis, it is found that the classifier trained from 1600 positive samples has the best effect.