Skip to content

Switched overlap to IoU. #216

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Namburger wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Switched overlap to IoU. #216

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 7 additions & 5 deletions imutils/object_detection.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
# import the necessary packages
import numpy as np

def non_max_suppression(boxes, probs=None, overlapThresh=0.3):
def non_max_suppression(boxes, probs=None, iouThresh=0.3):
# if there are no boxes, return an empty list
if len(boxes) == 0:
return []
Expand Down Expand Up @@ -53,13 +53,15 @@ def non_max_suppression(boxes, probs=None, overlapThresh=0.3):
w = np.maximum(0, xx2 - xx1 + 1)
h = np.maximum(0, yy2 - yy1 + 1)

# compute the ratio of overlap
overlap = (w * h) / area[idxs[:last]]
# compute the IoU
intersections = w * h
IoU = intersections / (area[idxs[:last]] + area[i] - intersections)

# delete all indexes from the index list that have overlap greater
# than the provided overlap threshold
idxs = np.delete(idxs, np.concatenate(([last],
np.where(overlap > overlapThresh)[0])))
np.where(IoU > iouThresh)[0])))

# return only the bounding boxes that were picked
return boxes[pick].astype("int")
return boxes[pick].astype("int")