Please use this identifier to cite or link to this item:
Title: A unified multi-task learning architecture for fast and accurate pedestrian detection
Authors: Zhou, Chengju
Wu, Meiqing
Lam, Siew-Kei
Keywords: Engineering::Computer science and engineering
Issue Date: 2020
Source: Zhou, C., Wu, M. & Lam, S. (2020). A unified multi-task learning architecture for fast and accurate pedestrian detection. IEEE Transactions On Intelligent Transportation Systems.
Journal: IEEE Transactions on Intelligent Transportation Systems
Abstract: We present a unified multi-task learning architecture for fast and accurate pedestrian detection. Different from existing methods which often focus on either a new loss function or architecture, we propose an improved multi-task convolutional neural network learning architecture to effectively and efficiently interfuse the task of pedestrian detection and semantic segmentation. To achieve this, we integrate a lightweight semantic segmentation branch to Faster R-CNN detection framework that enables end-to-end hard parameter sharing in order to boost the detection performance and maintain computational efficiency as follows. Firstly, a Semantic Segmentation to Feature Module (SS2FM) refines the convolutional features in RPN stage by integrating the features generated from the semantic segmentation branch. Secondly, a Semantic Segmentation to Confidence Module (SS2CM) refines the classification confidence in RPN stage by fusing it with the semantic segmentation confidence. We also introduce an effective anchor matching point transform to alleviate the problem of feature misalignment for heavily occluded pedestrians. The proposed unified multi-task learning architecture lends itself well to more robust pedestrian detection in diverse scenarios with negligible computation overhead. In addition, the proposed architecture can achieve high detection performance with low resolution input images, which significantly reduces the computational complexity. Experiment results on CityPersons and Caltech datasets show that our method is the fastest among all state-of-the-art pedestrian detection methods while exhibiting competitive detection performance.
ISSN: 1524-9050
DOI: 10.1109/TITS.2020.3019390
Rights: © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at:
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Journal Articles

Files in This Item:
File Description SizeFormat 
09186837.pdf3.23 MBAdobe PDFView/Open

Page view(s)

Updated on May 24, 2022

Download(s) 50

Updated on May 24, 2022

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.