Change search
ReferencesLink to record
Permanent link

Direct link
Semi-Supervised Learning for Object Detection
Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, The Institute of Technology.
2015 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Many automotive safety applications in modern cars make use of cameras and object detection to analyze the surrounding environment. Pedestrians, animals and other vehicles can be detected and safety actions can be taken before dangerous situations arise.

To detect occurrences of the different objects, these systems are traditionally trained to learn a classification model using a set of images that carry labels corresponding to their content. To obtain high performance with a variety of object appearances, the required amount of data is very large. Acquiring unlabeled images is easy, while the manual work of labeling is both time-consuming and costly. Semi-supervised learning refers to methods that utilize both labeled and unlabeled data, a situation that is highly desirable if it can lead to improved accuracy and at the same time alleviate the demand of labeled data. This has been an active area of research in the last few decades, but few studies have investigated the performance of these algorithms in larger systems.

In this thesis, we investigate if and how semi-supervised learning can be used in a large-scale pedestrian detection system. With the area of application being automotive safety, where real-time performance is of high importance, the work is focused around boosting classifiers. Results are presented on a few publicly available UCI data sets and on a large data set for pedestrian detection captured in real-life traffic situations. By evaluating the algorithms on the pedestrian data set, we add the complexity of data set size, a large variety of object appearances and high input dimension.

It is possible to find situations in low dimensions where an additional set of unlabeled data can be used successfully to improve a classification model, but the results show that it is hard to efficiently utilize semi-supervised learning in large-scale object detection systems. The results are hard to scale to large data sets of higher dimensions as pair-wise computations are of high complexity and proper similarity measures are hard to find.

Place, publisher, year, edition, pages
2015. , 72 p.
Keyword [en]
semi-supervised learning, object detection, pedestrian detection, boosting, machine learning, supervised learning, adaboost, semiboost, regboost, self-learning
National Category
Control Engineering
URN: urn:nbn:se:liu:diva-113560ISRN: LiTH-ISY-EX--14/4817--SEOAI: diva2:782911
External cooperation
Autoliv Electronics AB
Subject / course
Automatic Control
2014-12-11, Signalen, Linköpings universitet, Linköping, 16:15 (Swedish)
Available from: 2015-01-23 Created: 2015-01-22 Last updated: 2015-01-23Bibliographically approved

Open Access in DiVA

Semi-Supervised Learning for Object Detection(1669 kB)193 downloads
File information
File name FULLTEXT01.pdfFile size 1669 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Rosell, Mikael
By organisation
Automatic ControlThe Institute of Technology
Control Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 193 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 2708 hits
ReferencesLink to record
Permanent link

Direct link