loading
Documents

Research.Publish.Connect.

Paper

Authors: Xuesong Li ; Ngaiming Kwok ; Jose Guivant ; Karan Narula ; Ruowei Li and Hongkun Wu

Affiliation: School of Mechanical and Manufacturing Engineering, The University of New South Wales, NSW 2052, Australia

ISBN: 978-989-758-354-4

Keyword(s): Computer Vision, Object Detection, Convolutional Neural Network.

Abstract: Dealing with multiple sizes of the object in the image has always been a challenge in object detection. Predefined multi-size anchors are usually adopted to address this issue, but they can only accommodate a limited number of object scales and aspect ratios. To cover a wider multi-size variation, we propose a detection method that utilizes depth information to estimate the size of anchors. To be more specific, a general 3D shape is selected, for each class of objects, that represents different sizes of 2D bounding boxes in the image according to the corresponding object depths. Given these 2D bounding boxes, a neural network is used to classify them into different categories and do the regression to obtain more accurate 2D bounding boxes. The KITTI benchmark dataset is used to validate the proposed approach. Compared with the detection method using pre-defined anchors, the proposed method has achieved a significant improvement in detection accuracy.

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 34.204.176.189

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Li, X.; Kwok, N.; Guivant, J.; Narula, K.; Li, R. and Wu, H. (2019). Detection of Imaged Objects with Estimated Scales.In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, ISBN 978-989-758-354-4, pages 39-47. DOI: 10.5220/0007353600390047

@conference{visapp19,
author={Xuesong Li. and Ngaiming Kwok. and Jose E. Guivant. and Karan Narula. and Ruowei Li. and Hongkun Wu.},
title={Detection of Imaged Objects with Estimated Scales},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,},
year={2019},
pages={39-47},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007353600390047},
isbn={978-989-758-354-4},
}

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,
TI - Detection of Imaged Objects with Estimated Scales
SN - 978-989-758-354-4
AU - Li, X.
AU - Kwok, N.
AU - Guivant, J.
AU - Narula, K.
AU - Li, R.
AU - Wu, H.
PY - 2019
SP - 39
EP - 47
DO - 10.5220/0007353600390047

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.