1. Finish paper "Corn plant phenotypic parameters extraction algorithm based on keypoint detection and stereo images"
2. Change my paper "FCOS_Stereo"

{{unknown}}

The first draft of the paper has been completed, and it is expected to be completed in one week

1. detect key points based on yolo-pose
2. use mpdiou and focal mechanism to improve accuracy
3. Use GSCONV and pruning framework to reduce the parameters of the model

I am writing my paper and expect to finish the first draft within a week.

1.update my flow

2.As what i do in the last work,using internal parameters to project the key point to make data.

3.Adding the stereo -> depth netwotk to obtain the depth map

The pruning frame has a BUG in the library, hard to make progress.

Ⅰ.learn the different varities of the IoU:

1.GIoU：https://openaccess.thecvf.com/content_CVPR_2019/html/Rezatofighi_Generalized_Intersection_Over_Union_A_Metric_and_a_Loss_for_CVPR_2019_paper.html

2.DIoU:

https://ojs.aaai.org/index.php/AAAI/article/view/6999

3.CIoU：

https://ieeexplore.ieee.org/abstract/document/9520717

4.MPDIoU：

1.revise my SNPD paper

2. The characteristic values of corn key points were calculated

1. revise my SNPD paper to BOOK
2. Take more photos of the corn

1.Keypoint_POSE

2D_POSE based on yolov7

2.Use the RGB-D data to get the 3D Keypoint

1):Root point

2):Top point

3)： leaf root point

4)： … Continue Reading ››