my detector shows multiple bounding boxes .

hi everyone,
i have problem that my trained detector show multple bounding boxes on same object as shown in attached image .Inaddition to this iit shows bounding boxes only when threshold is set to 0.1.if i set 0.2 or more it does not show anyy box or label.

回答 (1 件)

Image Analyst
Image Analyst 2023 年 9 月 19 日

0 投票

I don't know what your detector does or how it operates or even what function you called. However maybe you can run through the bounding boxes and for those that have any overlapping area, take the bounding box of all the overlapped boxes.

9 件のコメント

ahmad
ahmad 2023 年 9 月 19 日
My detector is yolov2 which detects pothole,speedbumps,pole and lane .i trained dataset on these classes.
ahmad
ahmad 2023 年 9 月 19 日
So you are saying that I have to remove bounding boxes that overlap in training dataset.
Image Analyst
Image Analyst 2023 年 9 月 19 日
I'm saying to construct the overall bounding box and get rid of the ones inside.
ahmad
ahmad 2023 年 9 月 19 日
How can I construct on this test image detect by detector?
ahmad
ahmad 2023 年 9 月 19 日
This is my code
img = imread("C:\Users\ZBook\Desktop\New folder\new road.v2i.darknet\train\2_jpg.rf.e03c022bb9ccc6987308e66d130f4db7.jpg");
[bboxes,scores,labels] = detect(detector,img,'Threshold',thrusholdvalue);
detectedImg = insertObjectAnnotation(img,"Rectangle",bboxes,labels);
imshow(detectedImg)
Image Analyst
Image Analyst 2023 年 9 月 20 日
You forgot to attach "2_jpg.rf.e03c022bb9ccc6987308e66d130f4db7.jpg"
ahmad
ahmad 2023 年 9 月 20 日
I change my image to check whether it detect or not
ahmad
ahmad 2023 年 9 月 20 日
I place the attackrd image name in image to detect
Image Analyst
Image Analyst 2023 年 9 月 20 日
img = imread("C:\Users\ZBook\Desktop\New folder\new road.v2i.darknet\train\2_jpg.rf.e03c022bb9ccc6987308e66d130f4db7.jpg");
Error using imread>get_full_filename
File "C:\Users\ZBook\Desktop\New folder\new road.v2i.darknet\train\2_jpg.rf.e03c022bb9ccc6987308e66d130f4db7.jpg" does not exist.

Error in imread (line 372)
fullname = get_full_filename(filename);
[bboxes,scores,labels] = detect(detector,img,'Threshold',thrusholdvalue);
detectedImg = insertObjectAnnotation(img,"Rectangle",bboxes,labels);
imshow(detectedImg)

サインインしてコメントする。

カテゴリ

ヘルプ センター および File ExchangeComputer Vision Toolbox についてさらに検索

質問済み:

2023 年 9 月 19 日

コメント済み:

2023 年 9 月 20 日

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by