海参捕捞机器人动态定位技术研究

Research on Dynamic Positioning Technology of Sea Cucumber Fishing Robot

为提高海参的水下定位精度,提出一种基于双目视觉系统的水下海参动态定位方法。首先,建立双目立体视觉模型并利用Bouguet算法对图像进行立体校正,从而使左相机与右相机的成像平面共面、铅垂方向高度一致;然后,构建优化函数并利用改进布谷鸟算法优化双目相机的内参,削弱了多介质折射对定位精度的影响;最后,对距相机防水玻璃(300~1000)mm任意位置的水下海参进行定位测试,结果表明,参数优化后的模型在对海参进行定位时,在x、y、z方向的平均误差分别为3.09mm、2.96mm、8.21mm,可为水下机器人捕捞海参提供准确的信号输入。

In order to improve the underwater positioning accuracy of sea cucumbers,a dynamic positioning method of underwa⁃ter sea cucumbers based on binocular vision system was proposed.Firstly,a binocular stereo vision model was established and the Bouguet algorithm was used to correct the image,so that the image planes of the left and right cameras was coplanar and the plumb direction height was the same.Secondly,the optimization function was constructed and the internal parameters of the binoc⁃ular camera were optimized by the improved cuckoo algorithm to reduce the influence of multi-media refraction on positioning ac⁃curacy.Finally,the positioning test of underwater sea cucumbers at any location between(300~1000)mm away from the camera’s waterproof glass was carried out.The results show that when the parameter optimization model is used to locate the sea cucum⁃bers,the average errors in the x,y and z directions are 3.09mm,2.96mm and 8.21mm,respectively.Through this method,the accu⁃rate signal input can be provided for underwater robots to fish sea cucumbers.