Obstacles Stiffness And Flexibility Discriminant Method By Computer Vision

In order to reduce the complexity of the robot obstacle avoidance algorithm and improve the efficiency of obstacle avoidance, propose a method of distinguishing the stiffness and flexibility of obstacles before obstacle avoidance, and removing flexible objects which needn’t obstacle avoidance.Green bristlegrass was taken as the object of study.The specific method is to take the video image of the obstacles which occur deformation, extract the video image frame sequence, after the process of image binarization and denoising, overlay the extracted video image frame sequence, using the Canny edge detection algorithm to extract the edge and then extract the feature points of the superimposed image outer edge, after transforming the coordinate system, re-import feature points, fit the curve, considering the evaluation coefficient of the curve fitting and select the best curve fit model, get the equation of the characteristic curve and calculate the obstacle’s flexibility in accordance with it.Take green bristlegrass of different heights as the object of experiment to find the relationship between the flexibility and the corresponding height of the object. Definite the object weighed flexibility and its formulas. According to the equation of the characteristic curve and the formulas of the object weighed flexibility, calculate the obstacle’s weighted flexibility, then take the obstacle’s weighted flexibility and flexibility threshold for comparison; When the weighted flexibility of the obstacle is greater than or equal to the flexibility threshold, the obstacle is flexible; when the weighted flexibility of the obstacle is lower than the flexibility threshold, the obstacle is stiff.Take a cylindrical stick and a period of wicker as the object of experiment to verify the validity of the object stiffness and flexibility discrimination regulation. The result of the experiment proves that the object stiffness and flexibility discrimination regulation can discriminate the object stiffness and flexibility well.When the shape of a rigid object is similarity to the overlaid effect of the flexible object which has deformation, it will produce the misjudgment of object’s stiffness and flexibility. In order to solve the misjudgment, process a corresponding solution.In no wind or breeze environment, using the method in the paper to distinguish the stiffness and flexibility of the object, the correctness may be affected to some degree. To solve the limitation, propose two solutions to be in-depth study in future.