Detection of imaged objects with estimated scales

Xuesong Li, Ngaiming Kwok, Jose E. Guivant, Karan Narula, Ruowei Li, Hongkun Wu

Research output: Chapter in Book / Conference PaperConference Paperpeer-review

4 Citations (Scopus)

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.
Original languageEnglish
Title of host publicationVISIGRAPP 2019: Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (Volume 5), 25 - 27 February, 2019, Prague, Czech Republic
PublisherSciTePress
Pages39-47
Number of pages9
ISBN (Print)9789897583544
DOIs
Publication statusPublished - 2019
EventVISIGRAPP (Conference) -
Duration: 25 Feb 2019 → …

Publication series

Name
ISSN (Print)2184-4321

Conference

ConferenceVISIGRAPP (Conference)
Period25/02/19 → …

Fingerprint

Dive into the research topics of 'Detection of imaged objects with estimated scales'. Together they form a unique fingerprint.

Cite this