相机运动误差补偿的无人机视觉位移测量方法

Unmanned aerial vehicle vision-based displacement measurement method using camera motion error compensation

针对无人机悬停测量过程中是一个非稳定平台,使得位移测量结果中包含了目标本身的真实位移和相机运动所引起的测量误差问题。为削弱其影响,该文对相机运动所引起的位移测量误差进行分析,并提出一种对监测目标和固定参考目标没有强位置依赖、适用性更好的相机运动改正方法。在室内4 m距离测试中,相机运动误差改正率可达87.8%,位移测量精度可达0.5 mm;室外15 m距离测试中,相机运动误差改正率可达90.18%,位移测量精度可达2.2 mm。基于室内、室外实验结果表明:该方法能有效改正无人机运动所引起的相机运动误差,验证了无人机视觉位移测量技术的有效性和可靠性。

The hover measurement process for unmanned aerial vehicle(UAV)is a non-stable platform,so that the displacement measurement results include the true displacement of the target itself and the measurement error caused by the camera movement.In order to weaken its impact,this paper analyzes the displacement measurement error caused by camera motion,and proposes a camera motion correction method that has no strong relative positional relationship on the monitoring target and fixed reference target and is more applicable.In the indoor 4-meter distance test,the camera motion error correction rate can reach 87.8%,and the displacement measurement accuracy can reach 0.5 mm;in the outdoor 15-meter distance test,the camera motion error correction rate can reach 90.18%,and the displacement measurement accuracy can reach 2.2 mm.Based on indoor and outdoor experimental results,the proposed method can effectively correct the camera movement error caused by UAV movement,and verify the effectiveness and reliability of UAV visual displacement measurement technology.