{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,30]],"date-time":"2025-08-30T16:50:47Z","timestamp":1756572647151},"reference-count":27,"publisher":"IGI Global","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,7]]},"abstract":"<jats:p>Neural network models have been widely used in the field of object detecting. The region proposal methods are widely used in the current object detection networks and have achieved well performance. The common region proposal methods hunt the objects by generating thousands of the candidate boxes. Compared to other region proposal methods, the region proposal network (RPN) method improves the accuracy and detection speed with several hundred candidate boxes. However, since the feature maps contains insufficient information, the ability of RPN to detect and locate small-sized objects is poor. A novel multi-scale feature fusion method for region proposal network to solve the above problems is proposed in this article. The proposed method is called multi-scale region proposal network (MS-RPN) which can generate suitable feature maps for the region proposal network. In MS-RPN, the selected feature maps at multiple scales are fine turned respectively and compressed into a uniform space. The generated fusion feature maps are called refined fusion features (RFFs). RFFs incorporate abundant detail information and context information. And RFFs are sent to RPN to generate better region proposals. The proposed approach is evaluated on PASCAL VOC 2007 and MS COCO benchmark tasks. MS-RPN obtains significant improvements over the comparable state-of-the-art detection models.<\/jats:p>","DOI":"10.4018\/ijdwm.2020070107","type":"journal-article","created":{"date-parts":[[2020,5,28]],"date-time":"2020-05-28T14:30:35Z","timestamp":1590676235000},"page":"132-145","source":"Crossref","is-referenced-by-count":11,"title":["A Novel Multi-Scale Feature Fusion Method for Region Proposal Network in Fast Object Detection"],"prefix":"10.4018","volume":"16","author":[{"given":"Gang","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science, Hubei University of Technology, China"}]},{"given":"Chuyi","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Hubei University of Technology, China"}]}],"member":"2432","reference":[{"key":"IJDWM.2020070107-0","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_22"},{"key":"IJDWM.2020070107-1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.314"},{"key":"IJDWM.2020070107-2","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"IJDWM.2020070107-3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"IJDWM.2020070107-4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"IJDWM.2020070107-5","unstructured":"Fu, C.-Y., Liu, W., Ranga, A., Tyagi, A., & Berg, A. C. (2017). DSSD: Deconvolutional single shot detector."},{"key":"IJDWM.2020070107-6","first-page":"1440","article-title":"Fast R-CNN","author":"R.Girshick","year":"2015","journal-title":"Proceedings of 15th IEEE International Conference on Computer Vision"},{"key":"IJDWM.2020070107-7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"IJDWM.2020070107-8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"IJDWM.2020070107-9","first-page":"770","article-title":"Deep residual learning for image recognition","author":"K.He","year":"2016","journal-title":"Proceedings of 29th IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"IJDWM.2020070107-10","unstructured":"Ioffe, S., & Szegedy, C. (2015, July). Batch normalization: Accelerating deep mnetwork training by reducing internal covariate shift. In Proceedings of 32nd International Conference on Machine Learning (pp. 448\u2013456). Academic Press."},{"key":"IJDWM.2020070107-11","article-title":"On-road object detection using deep neural network","author":"H.Kim","year":"2017","journal-title":"Proceedings of 2016 IEEE International Conference on Consumer Electronics-Asia"},{"key":"IJDWM.2020070107-12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.557"},{"key":"IJDWM.2020070107-13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.98"},{"key":"IJDWM.2020070107-14","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012, December). ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems (pp. 1097\u20131105). Academic Press."},{"key":"IJDWM.2020070107-15","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098115"},{"key":"IJDWM.2020070107-16","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., . . . Zitnick, C. L. (2014, September). Microsoft COCO: Common objects in context. In Proceedings of 13th European Conference on Computer Vision (pp. 740\u2013755). Academic Press.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"IJDWM.2020070107-17","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016, October). SSD: Single shot multibox detector. In Proceedings of 14th European Conference on Computer Vision (pp. 21\u201337). Academic Press.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"IJDWM.2020070107-18","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"IJDWM.2020070107-19","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2016.2615329"},{"key":"IJDWM.2020070107-20","unstructured":"Ramachandran, P., Zoph, B., & Le, Q. V. (2018, April). Searching for Activation Functions. In Proceedings of 6th International Conference on Learning Representations. Academic Press."},{"key":"IJDWM.2020070107-21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"IJDWM.2020070107-22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"IJDWM.2020070107-23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"IJDWM.2020070107-24","unstructured":"Singh, S., & Gupta, S. C. (2016, December). Human object detection by HOG, HoB, HoC and BO features. In Proceedings of 4th IEEE International Conference on Parallel, Distributed and Grid Computing (pp. 742\u2013746). IEEE Press."},{"key":"IJDWM.2020070107-25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"IJDWM.2020070107-26","first-page":"6230","article-title":"Pyramid scene parsing network","author":"H.Zhao","year":"2017","journal-title":"Proceedings of 30th IEEE Conference on Computer Vision and Pattern Recognition"}],"container-title":["International Journal of Data Warehousing and Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.igi-global.com\/viewtitle.aspx?TitleId=256166","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,6]],"date-time":"2022-05-06T13:53:04Z","timestamp":1651845184000},"score":1,"resource":{"primary":{"URL":"http:\/\/services.igi-global.com\/resolvedoi\/resolve.aspx?doi=10.4018\/IJDWM.2020070107"}},"subtitle":[""],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":27,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.4018\/ijdwm.2020070107","relation":{},"ISSN":["1548-3924","1548-3932"],"issn-type":[{"value":"1548-3924","type":"print"},{"value":"1548-3932","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7]]}}}