基于图结构的深度学习特征动态编排调优方法及系统
本发明提供基于图结构的深度学习特征动态编排调优方法及系统,涉及人工智能技术领域,包括通过获取施工场景视频数据流,提取节点特征并构建关联图,利用图扩散卷积网络动态调整传播步长更新特征,采用密度自适应采样策略重组特征,构建状态转移矩阵预测目标运动轨迹并结合目标检测结果进行修正。本发明提高了施工场景中目标跟踪的准确性和鲁棒性,降低了计算复杂度,实现了实时高效的目标跟踪。
APPLICANTS
Browse source applicant names and unchanged name fields from imported patent records.
These are name-based results, not verified legal entities. Identical names may refer to different people or organizations; aliases and historical names are not merged.
This page matches the complete original name field. It may contain multiple applicants or another recorded party role. Name boundaries and legal identities have not been verified; punctuation is preserved, not split.
2 indexed patent records