Research at Fynd

Improving object detection mAP by 20%

Image for post
Image for post

Introduction

Object detection powers many vision tasks like instance segmentation, pose estimation, tracking and action recognition. These computer visions tasks have many applications in surveillance, autonomous driving and visual question answering domain. With this wide range of real-world application, Object Detection naturally becomes an active research area.
Our research team at Fynd has been training a Person Detection model to power our object tracking model (more on tracking in an upcoming blog). In this article, we will explain how we selected a model architecture, created a dataset and trained it for our specific use case.

What is Object Detection?

Object detection is a computer vision technique that allows us to identify and locate objects in an image or video. Object Detection can be understood in two parts, Object Localisation and Object Classification. Localisation can be understood as predicting the exact location (bounding box) of an object in the image and Classification is to define from which class (person/car/dog etc. …


Video Colorization as a proxy task and Object Tracking as a downstream task

Image for post
Image for post
Photo by Priscilla Du Preez on Unsplash

In this article, we will learn about a novel approach of self-supervised object tracking. Self-supervised is an approach where the models learn themselves 😎, this itself makes the topic very interesting. Here we will see how our model can learn to track objects on its own. We will start with the basics of object tracking then, get to what is self-supervised learning for computer vision and finally discuss the approach in detail.

The implementation of this method can be found here

Introduction to Object Tracking 🎯

In simple language, it can be understood as identifying unique objects throughout the video sequence. The object to track is usually know as a target object. The tracking can be done by either bounding box or instance segmentation.

About

Tushar Kolhe

Deep Learning Engineer | Computer Vision | AI solutions for Retail | https://www.linkedin.com/in/tushar-kolhe-696588154

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