Fundamentally, a stereo matching algorithm produces a disparity map or depth map. This map contains valuable information for many applications, such as range estimation, autonomous vehicle navigation and 3D surface reconstruction. The stereo matching process faces various challenges to get an accurate result for example low texture area, repetitive pattern and discontinuity regions. The proposed algorithm must be robust and viable with all of these challenges and is capable to deliver good accuracy. Hence, this article proposes a new stereo matching algorithm based on a hybrid Convolutional Neural Network (CNN) combined with directional intensity differences at the matching cost stage. The proposed algorithm contains a deep learning-based method and a handcrafted method. Then, the bilateral filter is used to aggregate the matching cost volume while preserving the object edges. The Winner-Take-All (WTA) is utilized at the optimization stage which the WTA normalizes the disparity values. At the last stage, a series of refinement processes will be applied to enhance the final disparity map. A standard benchmarking evaluation system from the Middlebury Stereo dataset is used to measure the algorithm performance. This dataset provides images with the characteristics of low texture area, repetitive pattern and discontinuity regions. The average error produced for all pixel regions is 8.51%, while the nonoccluded region is 5.77%. Based on the experimental results, the proposed algorithm produces good accuracy and robustness against the stereo matching challenges. It is also competitive with other published methods and can be used as a complete algorithm
Computing the stereo matching cost with a convolutional neural network
