Abstract:
Object detection has achieved good performance on perspective images. However, a general object detector does not maintain this performance when applied to a 360° image i...Show MoreNotes: This DOI was registered to an article that was not presented by the author(s) at this conference. As per section 8.2.1.B.13 of IEEE's "Publication Services and Products Board Operations Manual," IEEE has chosen to exclude this article from distribution. We regret any inconvenience.
Metadata
Abstract:
Object detection has achieved good performance on perspective images. However, a general object detector does not maintain this performance when applied to a 360° image in a single equirectangular projection (ERP) or multi-projection representation because of the distortion in the high-latitude region or discontinuity at the boundaries. In this paper, we proposed dual-ERP, which is a multi-view ERP representation, as the network input for 360° object detection in training and inference. Dual-ERP combines the advantages of single ERP and multi-projection representations, and it can easily be integrated with existing object detectors. The experimental results showed that compared to other representations, dual-ERP significantly improved the performance of different baseline object detectors.
Notes: This DOI was registered to an article that was not presented by the author(s) at this conference. As per section 8.2.1.B.13 of IEEE's "Publication Services and Products Board Operations Manual," IEEE has chosen to exclude this article from distribution. We regret any inconvenience.
Date of Conference: 16-19 October 2022
Date Added to IEEE Xplore: 18 October 2022
ISBN Information: