Updated GSoC_2018 (markdown)

Gary Bradski 2018-01-29 12:12:21 -08:00
parent 4c87f97709
commit 357cacdd2a

@ -206,7 +206,8 @@ Improving [DNN module](https://github.com/opencv/opencv_contrib/tree/master/modu
#### 2c. Reading ONNX
- Implement ONNX format parser. We already support Caffe 1 (with various extensions), TF, Torch and part of Darknet. Adding yet another parser is time-consuming but quite straight-forward thing.
We have found a good reference [starting point for this project here](https://github.com/lcskrishna/onnx-parser). Basically, we need to parse this network structure and fill out the DNN data structures that come with a download of OpenCV. There are several people working on DNN right now, so one of them will mentor this through to finish.
- We have found a good reference [starting point for this project here](https://github.com/lcskrishna/onnx-parser).
- Basically, we need to parse this network structure and fill out the DNN data structures that come with a download of OpenCV. There are several people working on DNN right now, so one of them will mentor this through to finish.
### 3a. Add April Tags to OpenCV, show examples of calibration using them
[April Tags](http://people.csail.mit.edu/kaess/apriltags/)