dc.contributor.author |
Skosana, Vusi J
|
|
dc.contributor.author |
Ngxande, M
|
|
dc.date.accessioned |
2021-03-03T10:22:57Z |
|
dc.date.available |
2021-03-03T10:22:57Z |
|
dc.date.issued |
2020-01 |
|
dc.identifier.citation |
Skosana, V.J. & Ngxande, M. 2020. The effects of image smoothing on CNN-based detectors. http://hdl.handle.net/10204/11821 . |
en_ZA |
dc.identifier.isbn |
978-1-7281-4162-6 |
|
dc.identifier.isbn |
978-1-7281-4163-3 |
|
dc.identifier.uri |
http://hdl.handle.net/10204/11821
|
|
dc.description.abstract |
Edge-preserving smoothing filters have been shown to improve generalisation performance on the HOG features with a SVM classifier. However, not all smoothing filters and parameters lead to better performance. The effects of smoothing filters are studied on the Faster R-CNN detector using generic object and human detection datasets, namely the PASCAL VOC and KITTI respectively. The total variation (TV) smoothing filter was used for this study. It was found that the TV smoothing removed details the CNN was using for detection which degraded performance for both datasets. The results are consistent with previous observations that CNNs tend to learn weak visual features. The performance loss, however, was moderate and could be justified in the context of improving robustness to perturbations. The PASCAL VOC and KITTI datasets had comparable performance loss despite the latter having many more small objects that tend to blend into the background when smoothing is applied. |
en_US |
dc.format |
Abstract |
en_US |
dc.language.iso |
en |
en_US |
dc.relation.uri |
https://ieeexplore.ieee.org/document/9041035 |
en_US |
dc.relation.uri |
doi: 10.1109/SAUPEC/RobMech/PRASA48453.2020.9041035 |
en_US |
dc.source |
2020 International SAUPEC/RobMech/PRASA Conference, Cape Town, South Africa |
en_US |
dc.subject |
Object detection |
en_US |
dc.subject |
Image smoothing |
en_US |
dc.subject |
Edge-preserving filter |
en_US |
dc.subject |
Human detection |
en_US |
dc.subject |
Pedestrian detection |
en_US |
dc.subject |
Convolutional neural networks |
en_US |
dc.title |
The effects of image smoothing on CNN-based detectors |
en_US |
dc.type |
Conference Presentation |
en_US |
dc.description.pages |
6pp |
en_US |
dc.description.note |
Copyright: 2020 IEEE. Due to copyright restrictions, the attached PDF file contains the abstract of the full-text item. For access to the full-text item, please consult the publisher's website: https://ieeexplore.ieee.org/document/9041035 |
en_US |
dc.description.cluster |
Defence and Security |
|
dc.description.impactarea |
Optronic Sensor Systems |
en_US |
dc.identifier.apacitation |
Skosana, V. J., & Ngxande, M. (2020). The effects of image smoothing on CNN-based detectors. http://hdl.handle.net/10204/11821 |
en_ZA |
dc.identifier.chicagocitation |
Skosana, Vusi J, and M Ngxande. "The effects of image smoothing on CNN-based detectors." <i>2020 International SAUPEC/RobMech/PRASA Conference, Cape Town, South Africa</i> (2020): http://hdl.handle.net/10204/11821 |
en_ZA |
dc.identifier.vancouvercitation |
Skosana VJ, Ngxande M, The effects of image smoothing on CNN-based detectors; 2020. http://hdl.handle.net/10204/11821 . |
en_ZA |
dc.identifier.ris |
TY - Conference Presentation
AU - Skosana, Vusi J
AU - Ngxande, M
AB - Edge-preserving smoothing filters have been shown to improve generalisation performance on the HOG features with a SVM classifier. However, not all smoothing filters and parameters lead to better performance. The effects of smoothing filters are studied on the Faster R-CNN detector using generic object and human detection datasets, namely the PASCAL VOC and KITTI respectively. The total variation (TV) smoothing filter was used for this study. It was found that the TV smoothing removed details the CNN was using for detection which degraded performance for both datasets. The results are consistent with previous observations that CNNs tend to learn weak visual features. The performance loss, however, was moderate and could be justified in the context of improving robustness to perturbations. The PASCAL VOC and KITTI datasets had comparable performance loss despite the latter having many more small objects that tend to blend into the background when smoothing is applied.
DA - 2020-01
DB - ResearchSpace
DP - CSIR
J1 - 2020 International SAUPEC/RobMech/PRASA Conference, Cape Town, South Africa
KW - Object detection
KW - Image smoothing
KW - Edge-preserving filter
KW - Human detection
KW - Pedestrian detection
KW - Convolutional neural networks
LK - https://researchspace.csir.co.za
PY - 2020
SM - 978-1-7281-4162-6
SM - 978-1-7281-4163-3
T1 - The effects of image smoothing on CNN-based detectors
TI - The effects of image smoothing on CNN-based detectors
UR - http://hdl.handle.net/10204/11821
ER - |
en_ZA |
dc.identifier.worklist |
24284 |
en_US |