The University of Southampton
University of Southampton Institutional Repository

Improving object detection performance by lightweight approaches

Improving object detection performance by lightweight approaches
Improving object detection performance by lightweight approaches
Object Detection has been a significant topic in computer vision. As the continuous development of Deep Learning, many advanced academic and industrial outcomes are established on localising and classifying the target objects, such as instance segmentation, video tracking and robotic vision. As the core concept of Deep Learning, Deep Neural Networks (DNNs) and associated training are highly integrated with task-driven modelling, having great effects on accurate detection. The main focus of improving detection performance is proposing DNNs with extra layers and novel topological connections to extract the desired features from input data. However, training these models can be a computational expensive and laborious progress as the complicated model architecture and enormous parameters. Besides, dataset is another reason causing this issue and low detection accuracy, because of insufficient data samples or difficult instances. To address these training diculties, this thesis presents two different approaches to improve the detection performance in the relatively light-weight way. As the intrinsic feature of data-driven in deep learning, the first approach is "slot-based image augmentation" to enrich the dataset with extra foreground and background combinations. Instead of the commonly used image flipping method, the proposed system achieved similar mAP improvement with less extra images which decrease training time. This proposed augmentation system has extra flexibility adapting to various scenarios and the performance-driven analysis provides an alternative aspect of conducting image augmentation. The "StomaRCNN" is the second approach which is based on a realistic application task to automatically detect, segment and measure the stomata in plant microscope images. The key innovation of StomaRCNN is reorganising DNN pipeline to utilise the detailed features in high-resolution microscope images without damaging the image qualities. Despite the limited related works, StomaRCNN achieved human-level measurement accuracy for open stoma instances and demonstrates a large potential of applying Deep Learning approaches to automatically solve instance measuring problems in plant science. Those presented works propose alternative ways of improving object detection performance and highlight the importance of rethinking object detection in the aspects of data-driven and step-wise architectural design.
University of Southampton
Zhou, Yingwei
d0f80584-6ce2-490f-b512-027927aee1d1
Zhou, Yingwei
d0f80584-6ce2-490f-b512-027927aee1d1
Prugel-Bennett, Adam
b107a151-1751-4d8b-b8db-2c395ac4e14e

Zhou, Yingwei (2020) Improving object detection performance by lightweight approaches. University of Southampton, Doctoral Thesis, 85pp.

Record type: Thesis (Doctoral)

Abstract

Object Detection has been a significant topic in computer vision. As the continuous development of Deep Learning, many advanced academic and industrial outcomes are established on localising and classifying the target objects, such as instance segmentation, video tracking and robotic vision. As the core concept of Deep Learning, Deep Neural Networks (DNNs) and associated training are highly integrated with task-driven modelling, having great effects on accurate detection. The main focus of improving detection performance is proposing DNNs with extra layers and novel topological connections to extract the desired features from input data. However, training these models can be a computational expensive and laborious progress as the complicated model architecture and enormous parameters. Besides, dataset is another reason causing this issue and low detection accuracy, because of insufficient data samples or difficult instances. To address these training diculties, this thesis presents two different approaches to improve the detection performance in the relatively light-weight way. As the intrinsic feature of data-driven in deep learning, the first approach is "slot-based image augmentation" to enrich the dataset with extra foreground and background combinations. Instead of the commonly used image flipping method, the proposed system achieved similar mAP improvement with less extra images which decrease training time. This proposed augmentation system has extra flexibility adapting to various scenarios and the performance-driven analysis provides an alternative aspect of conducting image augmentation. The "StomaRCNN" is the second approach which is based on a realistic application task to automatically detect, segment and measure the stomata in plant microscope images. The key innovation of StomaRCNN is reorganising DNN pipeline to utilise the detailed features in high-resolution microscope images without damaging the image qualities. Despite the limited related works, StomaRCNN achieved human-level measurement accuracy for open stoma instances and demonstrates a large potential of applying Deep Learning approaches to automatically solve instance measuring problems in plant science. Those presented works propose alternative ways of improving object detection performance and highlight the importance of rethinking object detection in the aspects of data-driven and step-wise architectural design.

Text
Improving Object Detection Performance By Lightweight Approaches - Version of Record
Restricted to Repository staff only until 27 January 2023.
Available under License University of Southampton Thesis Licence.

More information

Published date: January 2020

Identifiers

Local EPrints ID: 439322
URI: http://eprints.soton.ac.uk/id/eprint/439322
PURE UUID: 933afea8-d2d6-4d26-9d4e-5eae45996695
ORCID for Yingwei Zhou: ORCID iD orcid.org/0000-0001-6131-3156

Catalogue record

Date deposited: 08 Apr 2020 16:40
Last modified: 10 Apr 2020 00:38

Export record

Contributors

Author: Yingwei Zhou ORCID iD
Thesis advisor: Adam Prugel-Bennett

University divisions

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×