In autonomous driving vehicles, the emergency braking system uses lidar or radar sensors to recognize the surrounding environment and prevent accidents. The conventional classifiers based on radar data using deep learning are single input structures using range–Doppler maps or micro-Doppler. Deep learning with a single input structure has limitations in improving classification performance. In this paper, we propose a multi-input classifier based on convolutional neural network (CNN) to reduce the amount of computation and improve the classification performance using the frequency modulated continuous wave (FMCW) radar. The proposed multi-input deep learning structure is a CNN-based structure using a distance Doppler map and a point cloud map as multiple inputs. The classification accuracy with the range–Doppler map or the point cloud map is 85% and 92%, respectively. It has been improved to 96% with both maps.
In this paper, a text region extraction system with high contrasting text images for self-driving cars is proposed. The maximally stable extremal regions (MSER) method is usually used to extract text regions. Images must be converted to grayscale to process with the MSER method. However, the performance of MSER by using grayscale images has a poor ability of capturing regions of interest in bad conditions such as high-contrast, low-luminance, much light reflection, and so on. An MSER system with a contrast-limited adaptive histogram equalization (CLAHE) instead of conventional MSER is therefore proposed. CLAHE is utilized as a pre-processing method in MSER to detect text regions. The proposed method achieves a precision of 81% and a recall of 82%. However, those for the MSER with grayscale are 63% and 55%, respectively.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.