I had a series of pictures of some flower species that I bought in the shop. I obtained a series of pictures by programming an android phone to take a picture every hour. After the plant had died, I annotated all the pictures and separated the states in (bud, growing, flower and dying). This annotation was done very quickly and I did not pay much attention to detail.
After I finished the annotation, I calculated the Principal Component Analysis (PCA) figure with the HOG features from each annotation. As you can see the features are all over the place, except the red ones that are grouped towards one side of the figure. I also observed this in the PCA that I did for the Zackenberg pictures (previous posts). I believe that this happens because of the shape of the buds. They are usually round and fit nicely inside the annotation window.
This might be something that we can use to detect the position of the flower. Assuming that every flower is a bud in the beginning of its life, we can scan images for buds and pinpoint their position. Then we can keep doing an analysis of that position once the bud has changed into a female of male flower. This could potentially give a very accurate count of the amount of flowers in the plot (without differentiating between sex). Remember that one of the assumptions of this project is that we are going to have a static camera taking pictures of the plot. This means that a coordinate in the picture will always be related to the same place in the plot. There is still hope:)