A Multipath Fusion Strategy Based Single Shot Detector

Qu, Shuyi; Huang, Kaizhu; Hussain, Amir; Goulermas, Yannis

Abstract

Object detection has wide applications in intelligent systems and sensor applications. Compared with two stage detectors, recent one stage counterparts are capable of running more efficiently with comparable accuracy, which satisfy the requirement of real-time processing. To further improve the accuracy of one stage single shot detector (SSD), we propose a novel Multi-Path fusion Single Shot Detector (MPSSD). Different from other feature fusion methods, we exploit the connection among different scale representations in a pyramid manner. We propose feature fusion module to generate new feature pyramids based on multiscale features in SSD, and these pyramids are sent to our pyramid aggregation module for generating final features. These enhanced features have both localization and semantics information, thus improving the detection performance with little computation cost. A series of experiments on three benchmark datasets PASCAL VOC2007, VOC2012, and MS COCO demonstrate that our approach outperforms many state-of-the-art detectors both qualitatively and quantitatively. In particular, for input images with size 512 × 512, our method attains mean Average Precision (mAP) of 81.8% on VOC2007 test, 80.3% on VOC2012 test, and 33.1% mAP on COCO test-dev 2015.

• Journal Article Type: Article
• Acceptance Date: Feb 9, 2021
• Online Publication Date: Feb 15, 2021
• Publication Date: 2021-02
• Deposit Date: Feb 22, 2021
• Publicly Available Date: Feb 22, 2021
• Journal: Sensors
• Publisher: MDPI
• Peer Reviewed: Peer Reviewed
• Volume: 21
• Issue: 4
• Article Number: 1360
• DOI: https://doi.org/10.3390/s21041360
• Keywords: object detection; single shot detector; feature fusion
• Public URL: http://researchrepository.napier.ac.uk/Output/2745552
• Additional Information: This paper is an extended version of our paper: Qu, S.; Huang, K.; Hussain, A.; Goulermas, Y. MPSSD: Multi-Path Fusion Single Shot Detector. In Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary, 14–19 July 2019.