Object Localization with Classification in Real-Time

Figure 1.1: Object Localization with Classification
Figure 1.2
Figure 1.3 [2]
Figure 1.4: Concept of the grid cell and midpoint
Figure 1.5: Output Format
Figure 1.6 Model Output [5]
Figure 1.7
Figure 1.8
Figure 1.9
Figure 1.10 Image with unnecessary bounding boxes
  1. Discard all the bounding boxes having pc < 0.6, as shown in Figure 1.11.
Figure 1.11
  • Pick the box having the largest pc as the prediction.
  • Discard any remaining box with IOU ≥ 0.5 with the selected box in the previous step.
Figure 1.12 Final output with necessary boxes
Figure 1.13
Figure 1.14
Figure 1.15 [6]
Figure 1.16 [7]
Figure 1.17
Figure 1.18
YOLO can detect fast-moving objects as well as objects that are too close

--

--

--

Qualcomm| Indian Institute of Technology, Bhubaneswar| Passionate about Deep Learning| https://shobhiit.me/

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Product categorization: classical Machine Learning problem for a difficult e-commerce task

Using Machine Learning & Regression Techniques to Predict House Prices

What’s new in Apache Spark 2.3 ?

Pitfalls in Advanced ML Techniques — Flower Classification Example

Support Vector Machines : Part 1

Synthetic Data Generation Using CTGAN

Recognizing Handwritten Digits

Image Processing for MNIST using Keras

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Shobhit

Shobhit

Qualcomm| Indian Institute of Technology, Bhubaneswar| Passionate about Deep Learning| https://shobhiit.me/

More from Medium

Selfie segmentation in Python using OpenCV and Mediapipe

Handwritten Text Recognition using Convolutional Neural Networks (CNN)

Image Segmentation: Extending Faster R-CNN into Mask R-CNN

R-CNN Object Detection and Semantic Segmentation