Scribd
Upload
145 views10 pages

Object Detection and Segmentation On Tensor Flow Using

This document discusses object detection using deep learning on TensorFlow. It provides an introduction to deep learning and CNNs, then reviews common object detection architectures and how they work. Generic object detection aims to locate and classify objects in images with bounding boxes. Object detection workflows typically involve feature extraction to determine object classes. Applications include facial counting, people counting, industrial quality control, self-driving cars, and security. Python and TensorFlow are the main software requirements.

Uploaded by

spiro
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
145 views10 pages

Object Detection and Segmentation On Tensor Flow Using

This document discusses object detection using deep learning on TensorFlow. It provides an introduction to deep learning and CNNs, then reviews common object detection architectures and how they work. Generic object detection aims to locate and classify objects in images with bounding boxes. Object detection workflows typically involve feature extraction to determine object classes. Applications include facial counting, people counting, industrial quality control, self-driving cars, and security. Python and TensorFlow are the main software requirements.

Uploaded by

spiro
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 10

Object detection and segmentation on

tensor flow using deep learning approach


abstract
 In this project, we provide a review on deep learning based object
detection frameworks. Our review begins with a brief introduction on
the history of deep learning and its representative tool, namely
Convolutional Neural Network (CNN).
 Then we focus on typical generic object detection architectures along
with some modifications and useful tricks to improve detection
performance further. As distinct specific detection tasks exhibit
different characteristics, we also briefly survey several specific tasks,
including salient object detection, face detection and pedestrian
detection.
GENERIC OBJECT DETECTION
Generic object detection aims at locating and
classifying existing objects in any one image, and
labeling them with rectangular bounding boxes to
show the confidences of existence.
 The frameworks of generic object detection methods
can mainly be categorized into two types One follows
traditional object detection pipeline, generating region
proposals at first and then classifying each proposal
into different object categories
introduction
To gain a complete image understanding, we should
not only concentrate on classifying different images,
but also try to precisely estimate the concepts and
locations of objects contained in each image.
This task is referred as object detection which usually
consists of different subtasks such as face detection,
pedestrian detection and skeleton detection
DOMAIN OF OBJECT
DETECTION
What is Object Detection?

Object Detection is the process of finding real-world


object instances like car, bike, TV, flowers, and
humans in still images or Videos. It allows for the
recognition, localization, and detection of multiple
objects within an image which provides us with a
much better understanding of an image as a whole. It is
commonly used in applications such as image
retrieval, security, surveillance, and advanced driver
assistance system
What is TensorFlow?

Tensorflow is Google’s Open Source Machine


Learning Framework for dataflow programming across
a range of tasks. Nodes in the graph represent
mathematical operations, while the graph edges
represent the multi-dimensional data arrays (tensors)
communicated between them
Object Detection Workflow
Every Object Detection Algorithm has a different way
of working, but they all work on the same principle.
Feature Extraction: They extract features from the
input images at hands and use these features to
determine the class of the image. Be it through
MatLab, Open CV, Viola Jones or Deep Learning.
Application
 1.Facial Counting
 2. People Counting
 3. Industrial Quality Check
 4. Self Driving Cars
 5. Security
Software requirements
Front End:Python
Backages:Tensor Flow

You might also like