jmfacil / single-view-place-recognition Goto Github PK

@jmfacil Hi, your work is very amazing! However, the code that trains the model is not open source. Could you release the code that trains the model? Moreover, it is noticed that you trained the new layer with 834746 image triplets for 5 epochs. How do you construct these 834746 image triplets? Thank you very much!

Hi,

I would like to create a precision recall curve for this model and dataset but I am confused how to create true_positive, false_negative, false_positive and true_negative.

Is this a correct approach:

tp, fp, fn, tn = 0,0,0,0
for i in range(3450):
   for j in range(neighbors):
       if(query_lbl[i] >= top_5[j]-2 and query_lbl[i] <= top_5[j]+2):
	   tp += 1
       else:
	   fp += 1

top_5 corresponds to the top 5 predicted places from reference database for a given query!

The confusion comes from the fact written in the article:

It is important to note that we consider a match is correct when the closest feature vector corresponds to a place within a 5 -frame window.

Does this statement mean a match is considered true_positive if a query is predicted within a 5-frame window of the reference database? Or true_positive is still assessed based on exact label from query to reference as follows:

Query_Season ---> Reference_Season
frame_i      ---> frame_i

for example:

Query = 0: Top 5 predicted places: [ 7  5 12 11 10] --> tp = 0, fp = 5, fn = ?, tn = ?
Query = 1: Top 5 predicted places: [ 7  8  6 10  4] --> tp = 0, fp = 5, fn = ?, tn = ?
Query = 2: Top 5 predicted places: [ 8  7 12 11 10] --> tp = 0, fp = 5, fn = ?, tn = ?
Query = 3: Top 5 predicted places: [ 8  7  6  4 12] --> tp = 1, fp = 4, fn = ?, tn = ?
Query = 4: Top 5 predicted places: [ 4 12  8  7  6] --> tp = 2, fp = 3, fn = ?, tn = ?

I don't know how to get fn and tn in the above code!

Cheers,

Hi,

in your article, there's an statement about the nordland dataset in which the length of each video is about 10 hours and each frame is timestamped with the GPS coordinates.

I was wondering if there might be any ground truth for train and test for each season to visualize , maybe something similar to following:

#Frame_ID, Timestamp, x, y

I created an imaginary similarity matrix for its ground truth between summer (Query) and and winter (Reference) in testing data.

Each frame is one season corresponds to frame to another season with exact label.

Query_Season --> Ref_Season
frame_i      --> frame_i

Can that matrix be a ground truth or there's a better approach to obtain it?

cheers,

I have recurrent code of Single-View Place Recognition. It was a great work and I have got the same result as shown on your paper. However, I haven't found any code about Multi-View Place Recognition on the project website or your homepage. I wonder if it is possible for you to share the code with me. I would like to do some further research. Thanks a lot!