Intersection Over Union (IoU) | Essentials of Object Detection

Поділитися
Вставка
  • Опубліковано 18 гру 2024

КОМЕНТАРІ • 16

  • @deep-ti-rawat
    @deep-ti-rawat 5 місяців тому +1

    This is the best series I have watched on explanation of object detection algorithms.
    Also, your approach of asking fundamental questions like "Why in this case, a metric of evaluation can't be used as a loss function" and many more such questions you addressed were so insightful. Really grateful for the efforts you've put in here. Thank you. 🙏🙏

  • @dhairy-kumar-learn
    @dhairy-kumar-learn 7 місяців тому +1

    So, in-depth and with those visualization it is a grate learning experience

  • @johngrabner
    @johngrabner Рік тому +2

    Binge watching your videos. Excellent content and excellent teaching. Thank you.

  • @kask198
    @kask198 7 місяців тому +1

    We are okay with imperfections as long as they are useful to us ... great wisdom🙏

  • @deeplearningexplained
    @deeplearningexplained 3 місяці тому

    awesome explanation!

  • @anilsarode6164
    @anilsarode6164 9 місяців тому +1

    Great Video !! Thanks.

  • @softwaretestingstudiosts5200
    @softwaretestingstudiosts5200 Рік тому +1

    Thanks. Really helpful and easy to understand tutorial. you mentioned that this is used to measure similarity between boxes. Can you elaborate how this can be used with geospatial and image capture?

    • @KapilSachdeva
      @KapilSachdeva  Рік тому

      I am not sure if I understand your question. Possible to elaborate and give an example?

    • @softwaretestingstudiosts5200
      @softwaretestingstudiosts5200 Рік тому

      @@KapilSachdeva Is it used for compring 2 images and checking the differences/similarity? I am actually after an example in real life.

    • @KapilSachdeva
      @KapilSachdeva  Рік тому +1

      It is not about comparing the images rather the two bounding boxes in a given image. The metric is used in the field of object detection and is used to compare the ground truth box and the predicted box by the neural network.

  • @harshith_takkala
    @harshith_takkala Рік тому

    is the same understanding can also be put on semantic and instance segmentation ?

    • @KapilSachdeva
      @KapilSachdeva  Рік тому

      You can use the notion of overlap in segmentation as well.

  • @nolan7106
    @nolan7106 Рік тому

    Respect! #1 place for online marketing 'PromoSM'!

    • @KapilSachdeva
      @KapilSachdeva  Рік тому

      Sorry. Not sure I understand your comment.