.png){kind=icon}
.png){kind=icon}
Return
Reliability-Oriented evaluation of UAV-Based vehicle detection under complex visual measurement conditions
.png){kind=icon}
PRE
AI
J
Y
L
Y
G
C
DOI：10.1016/j.measurement.2026.122837.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• YOLOv26x reached 0.9065 precision, 0.7250 recall and 0.7021 mAP50-95. • Bootstrap resampling quantifies variation linked to fixed test-set composition. • Small targets, smoke and clutter remain major sources of detection failure. • A two-level taxonomy structures representative errors and visual factors. • Reliability claims are bounded to the stated image dataset and protocol.
Keywords:
UAV visual measurement
Vehicle detection
Reliability-oriented evaluation
YOLOv26x
Complex visual disturbances
Failure analysis
Journal
IF:
5.6
Papers:
1.9W
Citations:
5.4W
Organization
Cited Papers