{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T22:49:05Z","timestamp":1776811745790,"version":"3.51.2"},"reference-count":21,"publisher":"European Society of Computational Methods in Sciences and Engineering","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCM"],"published-print":{"date-parts":[[2023,10,6]]},"abstract":"<jats:p>With the rapid development of deep learning, convolutional neural networks have gradually become the main means to extract features of dynamic image sequences. The motion vector estimation algorithm, as the key to the stability of image sequences, directly affects the performance of image stabilization systems, so the motion estimation algorithm for convolutional neural networks is necessary. The study proposes an improved convolutional neural network based on loss-free function, and applies it to the extraction of dynamic image features. On this basis, the motion estimation algorithm is then optimised by combining grey-scale projection and block matching methods. The experimental results show that the new loss-free function-based convolutional neural network has better recognition capability with an error rate of only 15% in dynamic image recognition. The accuracy of the optimised motion estimation algorithm is as high as 95.1% with a PSNR value of 16.636, which is higher than that of the traditional grey-scale projection algorithm. In terms of video processing, the improved algorithm has a higher PSNR value than the search block matching method, the bit-plane matching method and the full search block matching method, with a higher steady image accuracy and high operational efficiency, providing a new research idea for the improvement of motion estimation algorithms. In general, the proposed algorithm is a significant improvement over the current mainstream algorithms in terms of image accuracy, processing performance and number of operations, and it provides a new research idea for the improvement of motion estimation algorithms.<\/jats:p>","DOI":"10.3233\/jcm-226848","type":"journal-article","created":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T10:31:00Z","timestamp":1686306660000},"page":"2347-2360","source":"Crossref","is-referenced-by-count":0,"title":["Neural network-based motion vector estimation algorithm for dynamic image sequences"],"prefix":"10.66113","volume":"23","author":[{"given":"Yongjian","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"55691","reference":[{"issue":"1","key":"10.3233\/JCM-226848_ref1","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1016\/j.patcog.2017.09.040","article-title":"A deep convolutional neural network for video sequence background subtraction","volume":"76","author":"Babaee","year":"2018","journal-title":"Pattern Recogn."},{"issue":"8","key":"10.3233\/JCM-226848_ref2","first-page":"1","article-title":"StfNet: A two-stream convolutional neural network for spatiotemporal image fusion","volume":"57","author":"Liu","year":"2019","journal-title":"IEEE T Geosci Remote."},{"key":"10.3233\/JCM-226848_ref3","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.patrec.2017.08.017","article-title":"Motion-blur kernel size estimation via learning a convolutional neural network","volume":"119","author":"Li","year":"2017","journal-title":"Pattern Recogn Lett."},{"issue":"1","key":"10.3233\/JCM-226848_ref4","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1007\/s11859-017-1219-4","article-title":"Multiple feature fusion in convolutional neural networks for action recognition","volume":"22","author":"Li","year":"2017","journal-title":"Wuhan Univ J Nat Sci."},{"issue":"1","key":"10.3233\/JCM-226848_ref5","first-page":"9","article-title":"Aggressive action estimation: A comprehensive review on neural network based human segmentation and action recognition","volume":"9","author":"Saif","year":"2019","journal-title":"Int J Educ Manag Eng."},{"issue":"1","key":"10.3233\/JCM-226848_ref6","doi-asserted-by":"crossref","first-page":"20707","DOI":"10.1109\/ACCESS.2017.2757765","article-title":"Robust topological navigation via convolutional neural network feature and sharpness measure","volume":"5","author":"Ma","year":"2017","journal-title":"IEEE Access."},{"issue":"1","key":"10.3233\/JCM-226848_ref7","doi-asserted-by":"crossref","first-page":"160025","DOI":"10.1109\/ACCESS.2020.3020141","article-title":"Human motion gesture recognition algorithm in video based on convolutional neural features of training images","volume":"8","author":"Bu","year":"2020","journal-title":"IEEE Access."},{"issue":"11","key":"10.3233\/JCM-226848_ref8","first-page":"2613","article-title":"Temporal pyramid pooling based convolutional neural networks for action recognition","volume":"27","author":"Peng","year":"2017","journal-title":"IEEE T Multimedia."},{"issue":"1","key":"10.3233\/JCM-226848_ref9","doi-asserted-by":"crossref","first-page":"134185","DOI":"10.1109\/ACCESS.2020.3010846","article-title":"Residual learning of video frame interpolation using convolutional LSTM","volume":"8","author":"Suzuki","year":"2020","journal-title":"IEEE Access."},{"issue":"4","key":"10.3233\/JCM-226848_ref10","first-page":"7309","article-title":"Deep learning based dynamic hand gesture recognition with leap motion controller","volume":"9","author":"Jesi","year":"2020","journal-title":"Int J Adv Trends Comput Sci Eng."},{"key":"10.3233\/JCM-226848_ref11","doi-asserted-by":"crossref","unstructured":"Ahmed AV, Khot UP. An efficient generalized error concealment in video codec. International J Comput Vision Image Process. 2020; 10(3): 1-28.","DOI":"10.4018\/IJCVIP.2020100101"},{"issue":"1","key":"10.3233\/JCM-226848_ref12","doi-asserted-by":"crossref","first-page":"149122","DOI":"10.1109\/ACCESS.2020.3016030","article-title":"Study of convolutional neural networks for global parametric motion estimation on log-polar imagery","volume":"8","author":"Traver","year":"2020","journal-title":"IEEE Access."},{"issue":"Jul.","key":"10.3233\/JCM-226848_ref13","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.jvcir.2019.05.010","article-title":"Multi-person pose estimation based on a deep convolutional neural network","volume":"62","author":"Duan","year":"2019","journal-title":"J Vis Commun Image R."},{"issue":"1","key":"10.3233\/JCM-226848_ref14","doi-asserted-by":"crossref","first-page":"10159","DOI":"10.1109\/ACCESS.2020.2964285","article-title":"A novel recurrent convolutional neural network-based estimation method for switching guidance law","volume":"8","author":"Shao","year":"2020","journal-title":"IEEE Access."},{"issue":"1","key":"10.3233\/JCM-226848_ref15","doi-asserted-by":"crossref","first-page":"49563","DOI":"10.1109\/ACCESS.2018.2869465","article-title":"Simultaneous face detection and pose estimation using convolutional neural network cascade","volume":"6","author":"Wu","year":"2018","journal-title":"IEEE Access."},{"issue":"1","key":"10.3233\/JCM-226848_ref16","first-page":"38","article-title":"A novel convolutional neural network based localization system for monocular images","volume":"11","author":"Sun","year":"2019","journal-title":"Int J Softw Sci Comp."},{"issue":"5","key":"10.3233\/JCM-226848_ref17","first-page":"1070","article-title":"Implementasi convolutional neural network untuk klasifikasi variasi intensitas emosi pada dynamic image sequence","volume":"4","author":"Farokhah","year":"2020","journal-title":"Jurnal RESTI."},{"issue":"3","key":"10.3233\/JCM-226848_ref18","first-page":"25","article-title":"Tracking-DOSeqSLAM: A dynamic sequence \u2013 Based visual place recognition paradigm","volume":"15","author":"Tsintotas","year":"2021","journal-title":"IET Comput Vis."},{"key":"10.3233\/JCM-226848_ref19","doi-asserted-by":"crossref","unstructured":"Marban A, Srinivasan V, Samek W, Andeza J, Casalsa A. A recurrent convolutional neural network approach for sensorless force estimation in robotic surgery. Biomed Signal Proces. 2019; 50(Apr.): 134-150.","DOI":"10.1016\/j.bspc.2019.01.011"},{"issue":"1","key":"10.3233\/JCM-226848_ref20","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1007\/s10278-019-00282-4","article-title":"A deep convolutional neural network for annotation of magnetic resonance imaging sequence type","volume":"33","author":"Ranjbar","year":"2020","journal-title":"J Digi Imaging."},{"key":"10.3233\/JCM-226848_ref21","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.neucom.2019.04.057","article-title":"Recognition oriented facial image quality assessment via deep convolutional neural network","volume":"358","author":"Zhuang","year":"2019","journal-title":"Neurocomputing."}],"container-title":["Journal of Computational Methods in Sciences and Engineering"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JCM-226848","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T22:07:02Z","timestamp":1776809222000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JCM-226848"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,6]]},"references-count":21,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.3233\/jcm-226848","relation":{},"ISSN":["1472-7978","1875-8983"],"issn-type":[{"value":"1472-7978","type":"print"},{"value":"1875-8983","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,6]]}}}