Object Detection
Team:Utkarsh Dubey
Pawan Jakke
Bunty Dhakar Mentor:
Dr.Apoorva Mishra
Outline:
Introduction
Motivation
Literature Survey
Problem Statement
Objective
Methodology
Conclusion and future scope
References
Introduction:
Object detection is a computer technology related to computer vision and
image processing that deals with detecting instances of semantic objects
of a certain class(such as human,buildings or cars) in a digital image and
videos.
Detection deals with distinguishing the objects from background.
The object detection algorithms use features which can be extracted to
recognize a particular object. This model is very simple and easy to
implement.Here,object is a single regression problem which detects
directly from bounding box coordinates and class probability.Every
object has its own class such as all circles are round.
Motivation:
Object detection reduces human efforts and provide efficiency.
Automatic detection and extraction adds to the smart system used
today.
Literature Survey
Name Year Future Scope
Ross Girshick, Jeff Donahue, Trevor Rich feature hierarchies 2014,70% Easily detect the objects
Darrell, and Jitendra Malik. for accurate object
detection and semantic
segmentation.
Ross Girshick Fast R-CNN 2015,66% It makes possible to create a
region proposal+CNN
framework
Shaoqing Ren, Kaiming He, Ross Towards realtime object 2015,72% Development of machine
Girshick, and Jian Sun detection with region which mimics the human
proposal networks. In brain.
Advances in Neural Development of brain like
Information Processing computer called MoNETA.
Systems (NIPS).
Joseph Redmon, Santosh Divvala, Unified, real-time object 2016,68% In real time which can catch
Ross Girshick, and Ali Farhadi. detection vehicles which is violating
traffic rules.
Problem Statement:
The main problems in object detection are classification and localization.
Classification, which is defined as predicting the class of the image.
Localization is where the image contains a single object and the system should
predict the class of the location of the object in the image (a bounding box
around the object).
Objective
:
1.The goal of achieving high accuracy with real time performance.
2.The goal of object detection is to detect all instances of objects from a known
class,such as people,cars or faces in an image.
Methodology:
The methods used for object detection
1.Bounding Boxes:
The bounding box is a rectangle drawn on the image which tightly fits the object
in the image. A bounding box exists for every instance of every object in the
image.
2.Classification and regression:
The bounding box is predicted using regression and the class within the bounding
box is predicted using classification.
3.Two stage method:
In this case, the proposals are extracted using some other computer vision technique and then
resized to fixed input for the classification network, which acts as a feature extractor. Then an
SVM is trained to classify between object and background (one SVM for each class). Also a
bounding box regressor is trained that outputs some some correction (offsets) for proposal boxes.
Conclusion and future scope:
An accurate and efficient object detection system has been
developed which achieves comparable metrics with the existing
state-of-the-art system. This project uses recent techniques in
the field of computer vision and deep learning. Custom dataset
was created using labelling and the evaluation was consistent.
This can be used in real-time applications which require object
detection for pre-processing in their pipeline. An important
scope would be to train the system on a video sequence for
usage in tracking applications. Addition of a temporally
consistent network would enable smooth detection and more
optimal than per-frame detection.
References:
[1] Ross Girshick, Jeff Donahue, Trevor Darrell, and Jitendra Malik.
Rich feature hierarchies for accurate object detection and semantic
segmentation. In The IEEE Conference on Computer Vision and
Pattern Recognition (CVPR), 2014.
[2] Ross Girshick. Fast R-CNN. In International Conference on
Computer Vision (ICCV), 2015.
[3] Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. Faster
R-CNN: Towards realtime object detection with region proposal
networks. In Advances in Neural Information Processing Systems
(NIPS), 2015.
[4] Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi.
You only look once: Unified, real-time object detection. In The IEEE
Conference on Computer Vision and Pattern Recognition (CVPR),
2016.
THANK YOU
