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

Chinese Word Segmentation

Embedding for spelling correction

Neural Machine Translation using Simple Seq2Seq

Bias in Natural Language Processing (NLP): A Dangerous But Fixable Problem

Why Not Use Raman Amplifier to Extend the CWDM Network Reach?

Counterfactual Regret Minimization

How computer vision can detect BMI?

Diverse uses for sequence alignment

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

Application of Computer Vision : Object Classification

Neural Networks: the best open-source library for object detection & classification

Learning the ASL Alphabet with Computer Vision and Flask

IMAGE CAPTIONING USING DEEP LEARNING — WITH SOURCE CODE — EASY EXPLANATION

Image Captioning