Kernel extreme learning machine based quick traffic sign detecting method

Abstract

The invention discloses a kernel extreme learning machine based quick traffic sign detecting method and belongs to a field of image signal processing and mode recognition. The method includes reading an original sample image; utilizing a BING based objectness method for producing an area that may contain traffic signs; extracting HOG features of the candidate area and sending the features to a kernel extreme learning machine classifier; and obtaining a final detection result. According to the invention, a traditional slide window scanning method is abandoned. The BING algorithm is used for reducing search space and improving detection speed. A traditional ELM algorithm has a single hidden layer structure and has huge boundedness in complicated signal analysis. The invention adopts KELM (Kernel Extreme Learning Machine) for classification detection. The kernel extreme learning machine improves the stability of a learning model and enhances the generalization performance, improves the detection performance and keeps an advantage of low time consumption of ELM (Extreme Learning Machine).

Description

technical field [0001] The invention belongs to the field of image signal processing and pattern recognition, and relates to a method for fast traffic sign detection by using a binarization normative gradient (BING) and a nuclear ultra-limit learning machine. Background technique [0002] In today's society, with the development of the economy, people's living standards are improving day by day, and the number of private cars is increasing day by day. At the same time, the problem of urban road traffic safety is becoming more and more serious, so the intelligent transportation system emerges as the times require and develops rapidly. Intelligent transportation systems include car navigation systems, collision warning systems, traffic sign recognition systems (Traffic SignRecognition System, TSR) and other intelligent systems. The first two systems have been widely used, but TSR has not yet reached the level of practical application. Regardless of actual driving or unmanned...

AI Technical Summary

Problems solved by technology

However, the training cost of such algorithms based on machine learning and classifiers is very high, and it is difficult to meet the requirements of real-time traffic sign detection under natural conditions.

Moreover, this kind of method adopts the traditional exhaustive sliding window scanning method, which has a larger search space and a larger amount of computer, which greatly slows down the detection speed.

Images