Year: 2021
Type: article
Abstract: Non-maximum suppression (NMS) is an unavoidable post-processing step in the object detection pipeline. NMS selects the bounding boxes with a locally maximum confidence score and eliminates its neighboring candidates which have a large overlap with the selected boxes. Because this procedure is a sequential and iterative algorithm of O(N2) complexity, NMS running time is too slow to be applied to real-time object detection on the image which has many objects. To consider this issue, we propose a parallel computation method using GPU multi-cores to compute faster than the previous NMS. Our parallel NMS replicates the candidate boxes and performs both IoU calculation and comparison in parallel. We drastically reduced the complexity from O(N2) to O(N) and the time consumption of NMS to be applied to real-time detection with negligible degradation of detection performance and very slight additional memory consumption. Furthermore, when there is a small number of overlapped objects, our parallel NMS achieved an improvement in precision.
Source: IEEE Access
Authors: Hyeonjin Lee, Jeong-Sik Lee, Hyun-Chul Choi
Institution: Yeungnam University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $1,750
Awards: G5763167314, G7500698872
OpenAlex ID: W4206765847
