ID 原文 译文
1093 且大都是在已有目标检测算法基础上进行改进，以提高小目标检测的检测精度。 Furthermore, most of the methods proposed are based on the traditional object detection algorithms with certainmodifications so as to improve the accuracy of small object detection.
1094 小目标像素点少，本身携带的特征少，多次下采样后就更难进行特征提取，因而小目标检测面临极大挑战。 Small object contains fewer pixels and has less fea-tures, and it is even harder to extract object features after down sampling. Hence, small object detection is a challenging task.
1095 小目标检测在自动驾驶、遥感图像检测、刑侦等领域都有广泛应用需求， Small object detection has a wide range of application requirements in the fields of automatic driving, remote sensing image detection, and criminal investigation.
1096 对于小目标检测技术的研究有重要的实用价值。 It has important practical value for the research of small object detection technology.
1097 本文对小目标检测的现有研究成果进行了详细综述。 In this paper, the existing research results of small object detection are summarized.
1098 首先，将现有算法按照检测需要的阶段数分为一阶段、二阶段、多阶段，描述了RetinaNet、CornerNet-Lite、特征金字塔网络( Feature Pyramid Network，FPN) 等算法的原理并进行了对比分析。 Firstly, the existing algorithms are classified into one stage, two stages and multi-stages according to the number of stages for detection. The principles of RetinaNet、Cor-nerNet-Lite、feature pyramid network( FPN) and other algorithms are described and compared.
1099 其次，本文描述了小目标检测技术在不同领域的应用情况，并汇总了 MS COCO、PASCAL VOC、DOTA、KITTI 等数据集及算法性能评价指标。 Secondly, this paper describes the application of small object detection technology in different fields, and summarizes the data sets such as MS COCO、PASCAL VOC、DOTA、KITTI and algorithm performance evaluation indicators.
1100 最后，总结了小目标检测面临的挑战，并展望了未来的研究方向。 Finally, the challenges faced by small object detection are concluded, and the future research directions are prospected.
1101 针对低信噪比条件下，复杂多类雷达辐射源信号识别存在特征提取困难，识别正确率低的问题，本文提出了一种基于时频分析和扩张残差网络的辐射源信号自动识别方法。 This paper proposes a radar emitter signal recognition method based on time-frequency analysis and dilatedresidual network ( DRN) to solve the problem of difficulty in feature extraction and low accuracy in recognition of complexmultiple radar emitter signals under low signal-to-noise ratio ( SNR) .
1102 首先通过时频分析将信号时域波形转换成二维时频图像以反映信号本质特征; Firstly, the signal time-domain wave form is trans-formed into a two-dimensional time-frequency image by time-frequency analysis to reflect the essential characteristics of sig-nal.