Unverified50% confidenceDecision RuleExact time
为每个传感器独立建模测量协方差矩阵R是多传感器融合区别于单传感器扩展的本质，R设置过小会导致过度信任该传感器测量值
1
Sources
50%
Confidence
Long-term
Relevance
7/14/2026
First Seen
Sources
多传感器卡尔曼融合实战：Shahed无人机追踪系统完整解析
Related Claims
Unverified测量协方差矩阵 R 越大滤波器越不信任该传感器读数，越小则越快响应观测变化78% similarUnverifiedQuantization error has a non-uniform distribution characteristic; the Q/K/V matrices of the attention mechanism and the last few layers are more sensitive to quantization.64% similarUnverifiedTwo-stage detectors (such as R-CNN and Faster R-CNN) first generate candidate boxes via a Region Proposal Network (RPN) and then classify them one by one, with typical inference speeds of only around 5–10 FPS64% similarUnverified当标注不一致存在时，增加更多数据只会成倍放大混乱，向模型提供自相矛盾的监督信号63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/503454API
curl https://kongchang.com/api/v1/knowledge/claims/503454MCP
get_claim(id=503454)