Depth Estimation Based on Stereo Image Using Passive Sensor

摘要

Abstract This article presents an algorithm for depth estimation using a pair of passive sensors which involves two cameras. These cameras did not produce any energy to collect the depth information. However, the depth information obtained from a camera can be produced by a matching process between two images at the same viewpoints. These images are captured from two cameras, which are also known as stereo cameras. The matching process consists of several stages, which will produce depth map. The most challenging problem for the matching process is to get an accurate corresponding point between two images. Hence, this article proposes an algorithm for stereo matching using Weighted Sum of Absolute Differences (WSAD), Median Filter (MF), and Bilateral Filter (BF) to surge up the accuracy. The WSAD will be implemented at the first stage to get the preliminary corresponding result, then the BF works as an edge-preserving filter to remove the noise from the first stage. The MF is used at the last stage to improve final depth map. A standard benchmarking dataset from the Middlebury has been used for the experimental analysis and validation. The proposed work in this article achieves good accuracy. The comparison is also conducted with some established methods where the proposed framework performs much better.