dc.contributor.author |
Kunene, Dumisani C
|
|
dc.contributor.author |
Vadapalli, H
|
|
dc.date.accessioned |
2017-11-16T07:25:48Z |
|
dc.date.available |
2017-11-16T07:25:48Z |
|
dc.date.issued |
2017-09 |
|
dc.identifier.citation |
Kunene, D.C. and Vadapalli, H. 2017. Better feature acquisition through the use of infrared imaging for human detection systems. SAICSIT 17, Thaba Nchu, 26-28 September 2017, Bloemfontein, South Africa |
en_US |
dc.identifier.isbn |
978-1-4503-5250-5 |
|
dc.identifier.uri |
https://dl.acm.org/citation.cfm?id=3129437
|
|
dc.identifier.uri |
http://hdl.handle.net/10204/9787
|
|
dc.description |
Copyright: 2017 ACM. Due to copyright restrictions, the attached PDF file only contains the abstract of the full text item. For access to the full text item, please consult the publisher's website. |
en_US |
dc.description.abstract |
Human detection on static images remains a challenging research problem. This work evaluates the significance of using infrared imaging (IIR) over several human detection systems. Larger complexities arise when detecting people in colour images due to the possibility of random colour patterns on the image backgrounds and clothes of pedestrians. In most cases, the colour clutter contributes negatively to image representation methods that solely rely on edge information. The basis of our supposition is that the choice of information has a large impact on the robustness of statistical learning systems. To test this supposition, we created and published a new infrared-based pedestrian dataset called “SIGNI". Several datasets of the same size were prepared and tested on three different classifiers. The classifiers are first trained with popular colour datasets to determine the optimal parameters that obtain high classification rates on unseen samples. Once satisfactory results are obtained, the same parameters are used for training the classifiers with infrared samples. The conventional use of support vector machines (SVM) on HOG features is tested against extreme learning machines (ELM) and convolutional neural networks (CNN). The results obtained show that the reduction of noise clutter improves the quality of acquired HOG features. As slight performance gains were observed during the classification of infrared samples over the use of visual samples. |
en_US |
dc.language.iso |
en |
en_US |
dc.publisher |
ACM Digital Library |
en_US |
dc.relation.ispartofseries |
Worklist;19732 |
|
dc.subject |
Human detection |
en_US |
dc.subject |
Feature extraction |
en_US |
dc.subject |
Noise-reduction |
en_US |
dc.subject |
Support vector machines |
en_US |
dc.subject |
Extreme learning machines |
en_US |
dc.subject |
Convolutional neural networks |
en_US |
dc.subject |
Infrared imaging |
en_US |
dc.title |
Better feature acquisition through the use of infrared imaging for human detection systems |
en_US |
dc.type |
Conference Presentation |
en_US |
dc.identifier.apacitation |
Kunene, D. C., & Vadapalli, H. (2017). Better feature acquisition through the use of infrared imaging for human detection systems. ACM Digital Library. http://hdl.handle.net/10204/9787 |
en_ZA |
dc.identifier.chicagocitation |
Kunene, Dumisani C, and H Vadapalli. "Better feature acquisition through the use of infrared imaging for human detection systems." (2017): http://hdl.handle.net/10204/9787 |
en_ZA |
dc.identifier.vancouvercitation |
Kunene DC, Vadapalli H, Better feature acquisition through the use of infrared imaging for human detection systems; ACM Digital Library; 2017. http://hdl.handle.net/10204/9787 . |
en_ZA |
dc.identifier.ris |
TY - Conference Presentation
AU - Kunene, Dumisani C
AU - Vadapalli, H
AB - Human detection on static images remains a challenging research problem. This work evaluates the significance of using infrared imaging (IIR) over several human detection systems. Larger complexities arise when detecting people in colour images due to the possibility of random colour patterns on the image backgrounds and clothes of pedestrians. In most cases, the colour clutter contributes negatively to image representation methods that solely rely on edge information. The basis of our supposition is that the choice of information has a large impact on the robustness of statistical learning systems. To test this supposition, we created and published a new infrared-based pedestrian dataset called “SIGNI". Several datasets of the same size were prepared and tested on three different classifiers. The classifiers are first trained with popular colour datasets to determine the optimal parameters that obtain high classification rates on unseen samples. Once satisfactory results are obtained, the same parameters are used for training the classifiers with infrared samples. The conventional use of support vector machines (SVM) on HOG features is tested against extreme learning machines (ELM) and convolutional neural networks (CNN). The results obtained show that the reduction of noise clutter improves the quality of acquired HOG features. As slight performance gains were observed during the classification of infrared samples over the use of visual samples.
DA - 2017-09
DB - ResearchSpace
DP - CSIR
KW - Human detection
KW - Feature extraction
KW - Noise-reduction
KW - Support vector machines
KW - Extreme learning machines
KW - Convolutional neural networks
KW - Infrared imaging
LK - https://researchspace.csir.co.za
PY - 2017
SM - 978-1-4503-5250-5
T1 - Better feature acquisition through the use of infrared imaging for human detection systems
TI - Better feature acquisition through the use of infrared imaging for human detection systems
UR - http://hdl.handle.net/10204/9787
ER -
|
en_ZA |