Hao Chen; Hong Zheng; Xiaolong Li
School of Automation Science and Electrical Engineering, Beihang University, China
Received 12 June 2020; Revised 25 October 2020; Accepted 26 October 2020; Published online 28 December 2020
Anchor-based detectors are widely used in object detection. To improve the accuracy of object detection, multiple anchor boxes are intensively placed on the input image, yet. Most of which are invalid. Although the anchor-free method can reduce the number of useless anchor boxes, the invalid ones still occupy a high proportion. On this basis, this paper proposes a multi-scale center point object detection method based on parallel network to further reduce the number of useless anchor boxes. This study adopts the parallel network architecture of hourglass-104 and darknet-53 of which the first one outputs heatmaps to generate the center point for object feature location on the output attribute feature map of darknet-53. Combining feature pyramid and CIOU loss function this algorithm is trained and tested on MSCOCO dataset, increasing the detection rate of target location and the accuracy rate of small object detection. Though resembling the state-of-the-art two-stage detectors in overall object detection accuracy speed.
Deep learning; Heatmap; Feature pyramid networks; Object detection; Center point