Absolute Depth Measurement of Objects Based on Monocular Vision

Abstract

With the continuous development of computer vision technology and the continuous upgrading of digital imaging equipment, image depth measurement method is widely used in the fields of intelligent robotics, traffic assistance, three-dimensional modeling and three dimensional video production. The following are the drawbacks of the traditional depth information measurement method: the operation is complex, the cost is high, and the measuring equipment occupies a large space and the load. In this paper, based on the Harris-SIFT corner detection algorithm, a technique is proposed to measure the absolute depth information of the object in the image using monocular vision. First of all, after the monocular camera is used to obtain the image of the target object, the image segmentation algorithm based on the LBF model is used to preprocess the image. Then, Harris algorithm in multi-scale space and SFIT algorithm to reconstruct feature descriptors are used to extract feature information in the image. Finally, by comparing the feature information between image groups, the depth information of target object is calculated by using the formula of convex hull principle and camera imaging principle. The test platform is applied to carry out measurement tests for different depth measurement methods, and the actual depth data and measurement data of the target object are compared, so as to evaluate the accuracy of the measurement method. The comparison results show that the error rate between the actual distance and the measured distance is less than 3.5%, which can accurately measure the absolute depth of the object in static and short distance, and is superior to other measurement methods.