LISA Vehicle Lights Dataset
收藏资源简介:
LISA Vehicle Lights Dataset是由加州大学圣地亚哥分校创建的一个专门用于自动驾驶领域中车辆灯光检测的数据集。该数据集包含44,784张图像,每张图像都标注了车辆灯光的中心坐标和四个角点的坐标,适用于车辆检测、意图和轨迹预测以及安全路径规划等下游应用。数据集的创建过程涉及从ApolloCar3D数据集中筛选出包含可见灯光的车辆实例,并进行详细的标注。该数据集的应用领域主要集中在自动驾驶技术中,旨在通过精确的灯光检测提高夜间车辆检测、3D车辆方向估计和动态轨迹提示的准确性。
The LISA Vehicle Lights Dataset is a specialized dataset designed for vehicle light detection in the autonomous driving domain, developed by the University of California, San Diego. It consists of 44,784 images, with each image annotated with the central coordinates and the coordinates of the four corner points of vehicle lights, making it suitable for downstream applications including vehicle detection, intent prediction, trajectory prediction and safe path planning. The dataset was created by screening vehicle instances with visible lights from the ApolloCar3D dataset and conducting detailed annotations. Its application is primarily concentrated in autonomous driving technology, with the goal of enhancing the accuracy of nighttime vehicle detection, 3D vehicle orientation estimation and dynamic trajectory prompting via precise light detection.

- 1Patterns of Vehicle Lights: Addressing Complexities in Curation and Annotation of Camera-Based Vehicle Light Datasets and Metrics加州大学圣地亚哥分校 · 2023年



