ID 原文 译文
39066 针对上述问题，采用NOMA技术提升数据链频谱利用率并分析干扰条件下基于非正交多址接入(NOMA)技术的数据链系统性能。 In response to the above problems, the NOMA technology is used to improve the data link spectrum utilization and analyze the performance of the data link system based on the NOMA technology under interference conditions.
39067 首先针对航空集群作战场景特点，建立了基于NOMA技术的航空数据链系统模型，推导了系统可获得最大速率表达式。 Firstly, an aviation data link system model based on NOMA technology was established based on the characteristics of the aviation cluster combat scenario, and the expression that the system can obtain the maximum rate was derived.
39068 其次考虑路径损耗与莱斯衰落的影响，推导出系统中断概率的闭合表达式，为估算系统性能提供了快速有效的方法。 Secondly, considering the effects of path loss and Rice fading, a closed expression for the probability of system outage is derived, which provides a fast and effective method for estimating system performance.
39069 仿真结果验证了理论推导公式的准确性，并进一步分析了信号发射功率、传输距离、敌方干扰以及数据速率等因素对系统性能的影响。 Simulation results verify the accuracy of the theoretical derivation formula, and further analyze the effects of factors such as signal transmission power, transmission distance, enemy interference, and data rate on system performance.
39070 基于运动信息与肤色特征相结合的手势分割是目前最主流的手势分割方法， Hand gesture segmentation based on the combination of motion information and skin color features is the most popular method of hand gesture segmentation at present.
39071 该类方法易受光照变化、背景变化、运动轨迹重合等因素的影响，并且所采用的肤色模型对不同肤色的手势不具有适应性。 This kind of method is easily affected by light changes, background changes, motion trajectory overlap and other factors, and the adopted skin color model has no adaption for different skin color gestures.
39072 针对以上问题，提出了一种先检测手势再自适应分割手势的方法。 So, this paper proposes a method to roughly detect hand gesture first and then segment hand adaptively.
39073 首先设计了一种基于空洞卷积的主干网络和一套Anchor方案将SSD(single shot multi-box detector)改进为手势检测模型，通过该模型初步分割出手势ROI(region of interest)以避免类肤色背景的影响。 SSD(Single Shot Multi-Box Detector) is improved into a hand gesture detection model, where a backbone network based on dilated convolution and a set of Anchor setting scheme are designed, which can preliminarily segment the gesture ROI(Region Of Interest) to avoid the influence of skin color background on the gesture segmentation.
39074 然后根据手势ROI建立YCrCb高斯肤色模型，以使肤色模型对不同的手势肤色具有很好的适应能力。 Then, the YCrCb gaussian skin color model was built according to the gesture ROI, so that the skin color model could adapt well to different skin colors of gestures.
39075 实验结果表明，在多种复杂场景下，本文的手势分割算法能够避免类肤色背景的影响并且对不同肤色的手势都取得了非常好的分割效果。 The experimental results demonstrate the robustness and effectiveness of proposed method for gestures with different skin color in a variety of complex scenarios.