Method for adaptively detecting remote obstacle

Abstract

The invention discloses a method for adaptively detecting a remote obstacle in the technical field of robots. The method comprises the following steps of: acquiring an image and preprocessing the image; dividing area and performing super-pixel division processing; performing high-dimensional external feature extraction; obtaining topographic types of each super-pixel of a close scene area; obtaining low-dimensional leading features of the super-pixels of a close scene; obtaining the low-dimensional leading features of the super-pixels of a remote scene; performing Adaboost classifier training; and inputting the low-dimensional leading features of the super-pixels of the remote scene area into an Adaboost classifier, determining a current scene is the obstacle if the output of the Adaboost classifier is 1, and determining the current scene is the ground if the output of the Adaboost classifier is not 1. The method has the advantages of realizing the adaptive extraction of detection features of the obstacle, simplifying a classifier model, simultaneously reducing the influence of the multimode distribution of the obstacle and type ambiguity caused by random feature superposition on detection results, and improving obstacle detection accuracy and stability.

Description

technical field The invention relates to a detection method in the technical field of robots, in particular to an adaptive detection method for long-distance obstacles. Background technique Obstacle detection is a key problem to be solved in the visual navigation of mobile robots in outdoor unstructured environments, and it is a prerequisite for subsequent path planning and action execution. At present, due to the lack of low-cost and long-distance obstacle detection methods, most obstacle detection methods are short-distance obstacle detection methods based on stereo vision or lidar. However, the myopic nature of this obstacle perception will directly or indirectly cause the robot to produce inefficient path planning results and even fail in navigation tasks. In recent years, with the development of artificial intelligence and other disciplines and the self-learning ability of robots has received greater attention in the field of robotics, the long-distance obstacle detec...

AI Technical Summary

Problems solved by technology

However, this method relies on a large amount of sample data. The selection of sample data will have a significant impact on the classification effect, and the extracted feature dimension is too high, which increases the computational complexity and lacks the discussion of feature contribution.

In addition, this method does not study how the system adaptively selects the optimal features for obstacle detection in the current scene, so it is difficult to meet the following requirements for visual navigation of mobile robots in outdoor unstructured environments:

Images