| 116 | |
| 117 | |
| 118 | |
| 119 | |
| 120 | === Weekly Report 4 (2014, June 13) === |
| 121 | |
| 122 | '''Week 4:''' |
| 123 | |
| 124 | WHAT I GET DONE THIS WEEK: |
| 125 | |
| 126 | I have deeply studied how to implement the epipolar rectification (goal of the mid-term). As a result of a discussion with mentors, I have evaluate alternative approaches for the epipolar rectification, such as Vertical Line Locus feature-based type approach, Vertical Line Locus based on a coarse external DSM (such as SRTM or ASTER) and integration of Disparity Map and Non-Disparity Map approaches. |
| 127 | |
| 128 | As a result of a discussion with mentors, I have discarded the idea of using OpenCV SIFT procedure for automatic TPs generation since it cannot be included or used as part of a public distribution, and I have choosen another detector (OrbFeatureDetector). Therefore I have wrote a procedure for the automatic Tps detection with OrbFeatureDetector implemented in the OpenCV library and I have tested it on an Ortho Ready GeoEye stereo-pair: these are very good images since they are basically epipolar as already projected by provider on a constant ellipsoidical height. |
| 129 | |
| 130 | [[Image()]] |
| 131 | |
| 132 | |
| 133 | I have wrote a procedure for the implementation of the Semi Global Matching algorithm and the Disparity Map generation; I have tested it on the above-mentioned images and I have calculated the x and y parallax errors. |
| 134 | |
| 135 | [[Image()]] |
| 136 | |
| 137 | I have upload the code produced on Git repository (https://github.com/martidi/OSSIM-GSoC-2014). |
| 138 | |
| 139 | [[BR]] |
| 140 | WHAT I PLAN ON DOING NEXT WEEK: |
| 141 | |
| 142 | To solve the problem on which I am stuck. |
| 143 | |
| 144 | To continue working on epipolar images generation and Disparity Map creation. |
| 145 | |
| 146 | To test and control implementation efficacy – discuss results with mentors. |
| 147 | |
| 148 | [[BR]] |
| 149 | SOMETHING ON WHICH I AM BLOCKED: |
| 150 | |
| 151 | I am having some issues in the integration between OpenCV algorithms and OSSIM Apps. |