Skip to Content
Mastering Computer Vision with TensorFlow 2.x
book

Mastering Computer Vision with TensorFlow 2.x

by Krishnendu Kar
May 2020
Beginner to intermediate
430 pages
10h 39m
English
Packt Publishing
Content preview from Mastering Computer Vision with TensorFlow 2.x

DeepSORT tracking

At CVPR 2017, Nicolai Wojke, Alex Bewley, and Dietrich Paulus came up with DeepSORT tracking in their paper titled Simple Online and Real-Time Tracking with a Deep Association Metric. The details of the paper can be found at https://arxiv.org/abs/1703.07402.

DeepSORT is an extension of SORT and integrates appearance information within the bounding box using a CNN trained to discriminate pedestrians. Details of the tracking implementation can be found at https://github.com/nwojke/deep_sort.

The details of the architecture are outlined as follows:

  • The tracking scenario is defined on an eight-dimensional state space (u, v, γ, h, x, y, γ, h), where (u, v) is the bounding box center location, γ is the aspect ratio, and h is ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Start your free trial

You might also like

Hands-On Computer Vision with TensorFlow 2

Hands-On Computer Vision with TensorFlow 2

Benjamin Planche, Eliot Andres

Publisher Resources

ISBN: 9781838827069Supplemental Content