Fig. 1. Overall architecture of proposed binocular stereo matching method

Fig. 2. Construction of positive and negative samples

Fig. 3. Image features convoluted by Log-Gabor filter with different scales and directions

Fig. 4. Rotation invariant uniform LBP image features

Fig. 5. Fusion module of multi-scale feature image blocks

Fig. 6. Fast network architecture based on MC-CNN

Fig. 7. Loss curves of training process on two datasets. (a) KITTI2012 dataset; (b) KITTI2015 dataset

Fig. 8. Average error rate for different margins on KITTI2012 and KITTI2015 datasets

Fig. 9. Average error rate for different image patch sizes on KITTI2012 and KITTI2015 datasets

Fig. 10. Average error rate under different noise tolerances on KITTI2012 and KITTI2015 datasets

Fig. 11. Training loss curves under different sample construction methods on two datasets. (a) KITTI2012; (b) KITTI2015

Fig. 12. Disparity results obtained by various methods. (a) Original input image; (b) SGM; (c) MC-CNN-fast; (d) LG-LBP CNN; (e) noise CNN; (f) our method

Fig. 13. Disparity maps of stereo matching obtained by proposed method on KITTI2012 dataset. (a) Original left input image; (b) original right input image; (c) ground truth; (d) disparity map; (e) error graph

Fig. 14. Disparity maps of stereo matching obtained by proposed method on KITTI2015 dataset. (a) Original left input image; (b) original right input image; (c) ground truth; (d) disparity map; (e) error graph