下载全文  

ObjectiveThe application of mixed reality （MR） in training environments, particularly in the field of aviation, marks a remarkable leap from… …   相似文献

《中国图象图形学报》2024,29(10):3008-3021

下载全文  

ObjectiveThree-dimensional human pose estimation has always been a research hotspot in computer vision. Currently, most methods directly reg… …   相似文献

《中国图象图形学报》2024,29(10):3116-3129

下载全文  

ObjectiveThis study introduces a novel method that aims to address the shortcomings of current no-reference point cloud quality assessment m… …   相似文献

《中国图象图形学报》2024,29(10):2979-2991

  

To improve the decoding performance of the simplified sequence repetition node-based fast successive cancellation (SSRFSC) decoding algorithm, a decoding algorithm (CSS-SSR-Flip) based on critical simplified set (CSS) and simplified sequence repetition (SSR) nodes was designed. Firstly, the information bit of the longest repetition (REP) node in SSR was selected as candidate bit (CB), thus constructing a CSS based on SSR. Corresponding flip metrics and flip criterion were designed according to the decoding characteristics of SSR nodes. Secondly, the CB reliability was measured by considering the influence of repetition sequences and the source of SSR nodes on decoding, and suboptimal repetition sequences were selected to complete SSR node flip operations during specific CB flips. Experimental data shows that at frame error rates of , CSS-SSR-Flip decoding algorithm is able to obtain more than 0.1 dB performance gain compared to the traditional fast simplified successive cancellation filp (Fast-SSC-Flip) decoding algorithm, and has the same decoding performance as the new Fast-SSC-Flip (New-Fast-SSC-Flip) decoding algorithm. However, compared to the traditional flip set size K, the CSS size of the proposed algorithm is reduced by up to 79.5%, and compared to the critical set (CS), the set size can be reduced by up to 23.1%.… …   相似文献

《通信学报》2024,45(10):95-106

  

To solve the problem of low efficiency of entanglement distribution caused by quantum information easily lost in quantum channels, quantum s… …   相似文献

《通信学报》2024,45(10):69-80

  

Aiming at the problems of quantum computing attacks, high authentication overhead and long interaction time in satellite network access auth… …   相似文献

《通信学报》2024,45(10):17-30

  

Although the computing power network (CPN) can connect via the Internet and flexibly schedule computing resources, it still lacks intelligen… …   相似文献

《通信学报》2024,45(10):191-206

  

To address the significant issue of hidden terminal interference that severely impacted resource management in ultra-dense Internet of thing… …   相似文献

《通信学报》2024,45(10):243-252

  

  相似文献

《通信学报》2024,45(10):225-242

SAR目标增量识别中基于最大化非重合体积的样例挑选方法

下载全文  

为了确保合成孔径雷达(SAR)自动目标识别(ATR)系统能够迅速适应新的应用环境,其必须具备快速学习新类的能力。目前的SAR ATR系统在学习新类时需要不断重复训练所有旧类样本,这会造成大量存储资源的浪费,同时识别模型无法快速更新。保留少量的旧类样例进行后续的增量训练是模型增量识… …   相似文献

李斌  崔宗勇  汪浩瀚  周正  田宇  曹宗杰 《电子与信息学报》2024,46(10):3918-3927