基于深度强化学习的移动机器人视觉图像分级匹配算法

Hierarchical Matching Algorithm of Visual Image for Mobile Robots Based on Deep Reinforcement Learning

针对传统移动机器人视觉图像分级匹配算法只能完成粗匹配,导致最终匹配精度较低、匹配时间较长等问题,提出一种基于深度强化学习的移动机器人视觉图像分级匹配算法.首先,利用深度强化学习网络结构中的策略网络和价值网络,共同指导浮动图像按正确方向移至参考图像;其次,在粗匹配过程中通过设计奖赏函数,实现颜色特征粗匹配;最后,在粗匹配基础上,利用改进尺度不变特征变换算法提取待匹配的图像局部特征,按相似度进行移动机器人视觉图像分级匹配.实验结果表明,该算法可有效实现图像的粗匹配与精匹配,在不同视角与尺度情况下特征检测的稳定性均较高,匹配精度高、时间短,匹配后的图像质量较好,提高了移动机器人的实际应用效果.

Aiming at the problems that the traditional hierarchical matching algorithm of visual image for mobile robot could only complete rough matching, resulting in low final matching accuracy and long matching time, we proposed a hierarchical matching algorithm of visual image for mobile robot based on deep reinforcement learning. Firstly, the strategy network and value network in the deep reinforcement learning network structure were used to guide the floating image to move to the reference image in the correct direction. Secondly, in the process of rough matching, the reward function was designed to realize the rough matching of color features. Finally, on the basis of rough matching, the improved scale invariant feature transformation algorithm was used to extract the local features of the image to be matched, and the mobile robot visual image was graded matched according to the similarity. The experimental results show that the algorithm can effectively realize the coarse matching and fine matching of images. The stability of feature detection is high under different viewing angles and scales. The matching accuracy is high, the time is short, and the matched image quality is good, which improves the actual application effect of mobile robot.