ID 原文 译文
24905 为满足电网电能质量要求,减少畸变的影响，导通角调制区间定义为 0.91π~π 之间。 In consideration of the power quality standard of power grid, the conduction angle modulation interval is from 0.91 π to π.
24906 经验证测试,该设计可实现调光控制,总谐波畸变率小于 5%,电压闪变幅度小于 4%,功率因数大于0。90。 Based on the practical testing results, the design can realize dimming control, the total harmonic distortion rate is less than 5%, the voltage flicker amplitude is less than 4%, and the power factor is greater than 0.90.
24907 该设计可广泛应用在智慧照明领域。 This design has a wide application prospect in the field of intelligent lighting.
24908 目标检测是计算机视觉领域中最基础且最重要的任务之一，是行为识别与人机交互等高层视觉任务的基础。 Object detection is one of the most fundamental and important tasks in the field of computer vision, which is the basis of high-level vision tasks such as behavior recognition and human-computer interaction.
24909 随着深度学习技术的发展，目标检测模型的准确率和效率得到了大幅提升。 With the development of deep learning technology, the accuracy and efficiency of object detectors have been greatly improved.
24910 与传统的目标检测算法相比，深度学习利用强大的分层特征提取和学习能力使得目标检测算法性能取得了突破性进展。 Compared with traditional object detection algorithms, deep learning utilizes powerful hierarchical feature extraction and learning capabilities to make breakthroughs in the performance of object detectors.
24911 与此同时，大规模数据集的出现及显卡计算能力的极大提高也促成了这一领域的蓬勃发展。 Meanwhile, the large-scale data-sets and the tremendous improvement in computing power have also contributed to the vigorous development in this field.
24912 本文对基于深度学习的目标检测现有研究成果进行了详细综述。 In this paper, the existing research of object detectors based on deep learning are reviewed in detail.
24913 首先回顾传统目标检测算法及其存在的问题，其次总结深度学习下区域提案和单阶段基准检测模型。 First, we review the traditional object detection algorithms and its problems. Then, object detectors based on deep learning are in-troduced, and the region-based and single-stage benchmark detectors are summarized.
24914 之后从特征图、上下文模型、边框优化、区域提案、类别不平衡处理、训练策略、弱监督学习和无监督学习这八个角度分类总结当前主流的目标检测模型，最后对目标检测算法中待解决的问题和未来研究方向做出展望。 After that, the current mainstream object detectors are concluded from eight perspectives of feature maps, context information, bounding box optimization, regional proposal, category imbalance processing, training strategy, weakly supervised learning and unsupervised learning. Finally, the problems to be solved in the object detectors are proposed and future research directions are prospected.