Top Read Articles

Published in last 1 year |

In last 2 years |

In last 3 years |

All

Please wait a minute...


For Selected: Download Citations EndNote Reference Manager ProCite BibTeX RefWorks Toggle Thumbnails

Select

Key Technologies to Ensure the Safety of the Intended Functionality for Intelligent Vehicles Wenbo Shao,Jun Li,Yuxin Zhang,Hong Wang Automotive Engineering    2022, 44 (9): 1289-1304.   DOI: 10.19562/j.chinasae.qcgc.2022.09.001 Abstract （758）   HTML （76）    PDF（pc） （3585KB）（9647）       Knowledge map    The limitations on performance， insufficient specifications or reasonably foreseeable misuse lead to the issues related to the safety of the intended functionality （SOTIF） emerging one after another， seriously hindering the rapid development of intelligent vehicles. This paper focuses on the key technologies to ensure the SOTIF， and systematically summarizes the related state of art of research from system development， functional improvement， and operation three phases. Finally， the research prospect is foreseen from the perspectives of basic theory， risk prevention and update mechanism. The review can provide an important reference for the research on the safety of the intended functionality for intelligent vehicles. Table and Figures | Reference | Related Articles | Metrics

Select

Small Target Detection Method for Dual-Modal Autonomous Driving with Yolo v5 and Lite-HRNet Fusion Zilong Liu,Xiangfei Shen Automotive Engineering    2022, 44 (10): 1511-1520.   DOI: 10.19562/j.chinasae.qcgc.2022.10.005 Abstract （721）   HTML （25）    PDF（pc） （2181KB）（535）       Knowledge map    This paper proposes a Yolo v5 network fused with Lite-HRNet to solve the problem of missed detection in the current target detection algorithm for autonomous driving field when detecting small and dense targets. Firstly， in order to obtain high-resolution feature detection maps， Lite-HRNet is used as the backbone network of Yolo v5 to enhance the detection of small and dense objects. In order to improve the detection performance in dark scenes， the infrared image and the visible light image are dynamically weighted to give full play to the complementary advantages of the visible light image and the infrared image. Because of the sufficient feature fusion of the backbone network， in order to speed up the detection speed， the feature fusion structure in the detection layer is cancelled. Secondly， \alpha-EIoU is used as the bounding box loss function in order to speed up the convergence and improve the regression accuracy. At the same time， the bisecting K-means algorithm is used for clustering to select more appropriate anchor boxes for the data set， and the small target data augmentation algorithm is used for sample expansion of the dataset. Finally， a comparative test with Yolo v5 on the flir dataset is conducted. According to the experimental results， the average detection accuracy of this algorithm is 7.64% higher than Yolo v5， and the missed detection rate of small targets and dense targets is significantly reduced. Table and Figures | Reference | Related Articles | Metrics