针对景区手写诗词存在背景纹理复杂、字体尺寸及风格多样等特点导致景区游客难以识别手写诗词的问题,首先,分析研究景区手写诗词的识别场景,设计景区诗词检测网络(detection of poetry in scenic areas-network,DPSA-Net)以提取景区手...针对景区手写诗词存在背景纹理复杂、字体尺寸及风格多样等特点导致景区游客难以识别手写诗词的问题,首先,分析研究景区手写诗词的识别场景,设计景区诗词检测网络(detection of poetry in scenic areas-network,DPSA-Net)以提取景区手写诗词不同尺度的特征,并结合手写诗词字符间的链接依赖关系实现景区手写诗词检测;其次,设计了卷积循环聚合网络(convolution recurrent aggregation network,CRA-Net)以对景区手写诗词进行识别,结合卷积神经网络(convolutional neural networks,CNN)和双向长短期记忆网络提取手写诗词图像的序列特征,并通过聚合交叉熵(aggregation cross-entropy,ACE)实现特征向文本的转换;最后,结合景区知识图谱对CRA-Net的输出进行校正,进而提高景区手写诗词的识别准确率。实验结果表明,通过景区手写诗词矫正技术对CRA-Net的识别结果矫正后,识别准确率达到了79.04%,同时,该技术具有较好的抗干扰能力和良好的应用前景。展开更多
Founded in Yuan Dynasty,formed and perfected from Ming and Qing Dynasties to modern times,the Central Axis of Beijing has a history of more than 750 years.It is the longest and best be-preserved traditional capital ax...Founded in Yuan Dynasty,formed and perfected from Ming and Qing Dynasties to modern times,the Central Axis of Beijing has a history of more than 750 years.It is the longest and best be-preserved traditional capital axis in China.It is composed of a series of buildings,historical landmarks,historical roads,bridges and ruins,forming an orderly urban space complex.展开更多
在基于到达相位差(Phase Differences Of Arrival,PDOA)的着靶点参数估计问题中,估计精度受到阵列结构的影响。与一般的单点目标定位问题相比,着靶点参数估计需要同时估计目标的速度和角度参数,情况更加复杂。为了选择合适的阵列结构以...在基于到达相位差(Phase Differences Of Arrival,PDOA)的着靶点参数估计问题中,估计精度受到阵列结构的影响。与一般的单点目标定位问题相比,着靶点参数估计需要同时估计目标的速度和角度参数,情况更加复杂。为了选择合适的阵列结构以对定位结果带来有利影响,该文从灵敏度的角度分析了不同阵列结构下靶点参数估计精度各有差异的原因,为判断不同情况下接收阵列定位性能的优劣提供了理论方法。最后,对3种常见阵列结构进行了计算机仿真对比,仿真结果验证了利用灵敏度指标对阵列布放结构进行评估的可行性。展开更多
文摘Founded in Yuan Dynasty,formed and perfected from Ming and Qing Dynasties to modern times,the Central Axis of Beijing has a history of more than 750 years.It is the longest and best be-preserved traditional capital axis in China.It is composed of a series of buildings,historical landmarks,historical roads,bridges and ruins,forming an orderly urban space complex.
文摘在基于到达相位差(Phase Differences Of Arrival,PDOA)的着靶点参数估计问题中,估计精度受到阵列结构的影响。与一般的单点目标定位问题相比,着靶点参数估计需要同时估计目标的速度和角度参数,情况更加复杂。为了选择合适的阵列结构以对定位结果带来有利影响,该文从灵敏度的角度分析了不同阵列结构下靶点参数估计精度各有差异的原因,为判断不同情况下接收阵列定位性能的优劣提供了理论方法。最后,对3种常见阵列结构进行了计算机仿真对比,仿真结果验证了利用灵敏度指标对阵列布放结构进行评估的可行性。