Abstract
In this paper, a portable assistance system is designed to help the visually impaired to detect the traffic light. The designed system is realized on the basis of the AdaBoost algorithm, which is fast and robust in object detections. In order to accelerate the AdaBoost-based approach, a flexible parallel architecture is implemented on the field-programmable gate array (FPGA) platform. The architecture is designed utilizing the parallelism of computations in the AdaBoost-based detection. The computations of the window integral image are implemented in parallel, and the confidences of the weak classifiers are calculated in parallel. The parameters of the weak classifiers are trained by the AdaBoost algorithm with multi-layer features in the MATLAB software, and then are configured on the FPGA platform via the Vivado design suite before the detection process. The parallelism optimized architecture is implemented on an Artix-7 FPGA at 200 MHZ. Experiments show that it can detect the traffic light in videos with a rate of 30 frames per second (fps).
Highlights
Many people in the world suffer from impaired vision
We propose a parallelism optimized architecture on field-programmable gate array (FPGA) to detect the traffic light
The hardware architecture is implemented on an FPGA platform for experiments
Summary
Many people in the world suffer from impaired vision. The visually impaired are limited in the independent mobility in urban roads, which is mainly because they cannot catch the information for safety in the heavy traffic [1]. The model is implemented on a mobile phone for test with videos about 5 to 10 fps Another approach on the phone is presented in [7], in which a filtering scheme is designed to detect the traffic light with a robust image acquisition method under particular exposure conditions. In [8], the AdaBoost algorithm with the aggregate channel features is adopted to detect the traffic light. The remaining of this paper is organized as follows: In Section II, concepts of the AdaBoost-based traffic light detection with multi-layer features is introduced. The concepts of the AdaBoost-based traffic light detection with multi-layer features are shown in Fig.. Based on the easy-use features, the AdaBoost algorithm is adopted to train the parameters of weak classifiers in iterations. Based on three integral images, the confidences of weak classifiers are evaluated in order to calculate the detection result.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have