本文選題：跑步姿態(tài)識(shí)別 + 運(yùn)動(dòng)跟蹤��； 參考：《東華大學(xué)》2017年碩士論文

【摘要】：隨著生活水平的不斷提高,借助于跑步機(jī)的健身跑步成為目前的有氧健身運(yùn)動(dòng)方式之一,跑步對(duì)頸椎、脊椎、心臟等各個(gè)人體機(jī)能都有好處,但是錯(cuò)誤的跑步姿勢也會(huì)對(duì)運(yùn)動(dòng)對(duì)象造成身體關(guān)節(jié)的損傷以及其他危害。為了能讓更多的健身運(yùn)動(dòng)者以正確的姿勢跑步,本文針對(duì)跑步機(jī)上的跑步視頻進(jìn)行了研究。隨著科學(xué)技術(shù)以及信息技術(shù)的持續(xù)進(jìn)步,視頻監(jiān)控在各種領(lǐng)域中的應(yīng)用已經(jīng)得到了普及,對(duì)動(dòng)態(tài)目標(biāo)的跟蹤檢測技術(shù)是應(yīng)用視頻進(jìn)行監(jiān)控的基礎(chǔ)和關(guān)鍵,該項(xiàng)技術(shù)將圖像處理、模式識(shí)別以及AI人工智能等多個(gè)領(lǐng)域融合到一起。在機(jī)器視覺領(lǐng)域中,以“人體運(yùn)動(dòng)”為對(duì)象的研究一直在不斷進(jìn)行,從人體檢測、位置跟蹤、運(yùn)動(dòng)軌跡跟蹤,到現(xiàn)在姿態(tài)識(shí)別、人體動(dòng)作識(shí)別,已經(jīng)有了一系列相關(guān)的研究算法和成果。本文以跑步機(jī)上的跑步視頻作為實(shí)驗(yàn)對(duì)象,主要進(jìn)行了以下這些工作:(1)首先對(duì)當(dāng)前在人體運(yùn)動(dòng)識(shí)別技術(shù)的應(yīng)用領(lǐng)域的背景以及意義這兩個(gè)部分的內(nèi)容進(jìn)行了簡單論述,并結(jié)合本文中的運(yùn)動(dòng)對(duì)象,對(duì)人體運(yùn)動(dòng)識(shí)別領(lǐng)域較為完整的研究成果進(jìn)行比較,同時(shí)對(duì)本文的研究中會(huì)出現(xiàn)的難點(diǎn)進(jìn)行了分析,為本文進(jìn)行研究提供了基本思路。(2)對(duì)于運(yùn)動(dòng)視頻中的對(duì)象跟蹤,為了獲取更準(zhǔn)確的運(yùn)動(dòng)軌跡,將基于Kinovea軟件的路徑跟蹤以及基于MeanShift算法的位置跟蹤方法進(jìn)行了對(duì)比,選取跟蹤結(jié)果更為準(zhǔn)確且能提高分類算法運(yùn)行的跟蹤方法,本文選用基于Kinovea軟件的跟蹤方法進(jìn)行路徑跟蹤。(3)介紹了當(dāng)前常用的識(shí)別算法。在進(jìn)行分類器的設(shè)計(jì)時(shí),結(jié)合研究對(duì)象的運(yùn)動(dòng)模型特點(diǎn),選用適合本文研究對(duì)象的分類器,在KNN分類器的基礎(chǔ)上,降低樣本維度進(jìn)行測試,提高分類識(shí)別效果。(4)進(jìn)行試驗(yàn)測試,邀請(qǐng)實(shí)驗(yàn)人員進(jìn)行跑步測試,對(duì)其跑步姿勢視頻進(jìn)行分析,分別從背面和側(cè)面兩個(gè)角度分別進(jìn)行分類識(shí)別,再獲取結(jié)論之后對(duì)其跑步姿勢提出校正訓(xùn)練建議。論文在最后總結(jié)了本文全部的研究工作,同時(shí)對(duì)接下來的研究目標(biāo)和方法進(jìn)行了分析和展望。
[Abstract]:With the continuous improvement of living standards, running with treadmill fitness has become one of the current aerobic exercise methods, running is good for the cervical spine, spine, heart and other human functions. But the wrong running posture can also cause joint damage and other hazards. In order to make more fitness athletes run in the right position, this paper studies the running video on treadmill. With the continuous progress of science and technology and information technology, the application of video surveillance in various fields has been popularized. The technology of tracking and detecting dynamic targets is the basis and key of video surveillance. Multiple fields such as pattern recognition and AI are combined. In the field of machine vision, the research on "human motion" has been going on all the time, from human body detection, position tracking, motion track tracking, to posture recognition, human motion recognition, There have been a series of related algorithms and results. This article takes the running video on the treadmill as the experimental object, mainly carries on the following work: 1) first of all, has carried on the brief discussion to the current application background and the significance of the two parts in the human body motion recognition technology domain. Combined with the moving object in this paper, the relatively complete research results in the field of human motion recognition are compared. At the same time, the difficulties that will appear in the research are analyzed. In order to obtain more accurate motion trajectory, the path tracking method based on Kinovea software and the position tracking method based on MeanShift algorithm are compared. The tracking method which is more accurate and can improve the running of the classification algorithm is selected. In this paper, the path tracking method based on Kinovea software is selected to introduce the commonly used recognition algorithms. In the design of classifier, combining the characteristics of motion model of the research object, selecting the classifier suitable for the research object in this paper, on the basis of KNN classifier, reducing the sample dimension to test, improving the classification recognition effect. The participants were invited to conduct the running test, the video of their running posture was analyzed, and the running posture was classified and recognized from the two angles of the back and the side respectively, and then the conclusion was obtained, and then the training suggestions were put forward for their running posture correction. At the end of this paper, all the research work is summarized, and the following research objectives and methods are analyzed and prospected.
【學(xué)位授予單位】：東華大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 陳強(qiáng);;五種跑姿易傷身[J];健康向?qū)?2013年02期

2 于康;;關(guān)于糖我們需要更多的了解[J];健康向?qū)?2013年02期

3 王科俊;呂卓紋;孫國振;閻濤;;基于分層分?jǐn)?shù)條件隨機(jī)場的行為識(shí)別[J];計(jì)算機(jī)應(yīng)用;2013年04期

4 趙志誠;白雅娟;周仁來;蔡安妮;;基于Tobii眼動(dòng)和多尺度條件隨機(jī)場的視覺顯著性模型[J];高技術(shù)通訊;2013年03期

5 江曉慶;肖德琴;張波;陳劍;;基于Kinect的農(nóng)作物長勢深度圖像實(shí)時(shí)獲取算法[J];廣東農(nóng)業(yè)科學(xué);2012年23期

6 李玲玲;金泰松;李翠華;;基于局部特征和隱條件隨機(jī)場的場景分類方法[J];北京理工大學(xué)學(xué)報(bào);2012年07期

7 楊旗;薛定宇;;基于雙尺度動(dòng)態(tài)貝葉斯網(wǎng)絡(luò)及多信息融合的步態(tài)識(shí)別[J];電子與信息學(xué)報(bào);2012年05期

8 錢鋒;梅雪;林錦國;;基于矩形骨架的人體動(dòng)作識(shí)別[J];微計(jì)算機(jī)信息;2012年04期

9 孫錦紅;劉衛(wèi)東;馬亮;楊偉蕾;;基于機(jī)器視覺的3D人體動(dòng)作識(shí)別研究[J];計(jì)算機(jī)與現(xiàn)代化;2011年11期

10 胡斐;羅立民;劉佳;左欣;;基于時(shí)空興趣點(diǎn)和主題模型的動(dòng)作識(shí)別[J];東南大學(xué)學(xué)報(bào)(自然科學(xué)版);2011年05期

相關(guān)博士學(xué)位論文 前2條

1 祝博薈;基于深度與視覺信息融合的行人檢測與再識(shí)別研究[D];東華大學(xué);2013年

2 任海兵;非特定人自然的人體動(dòng)作識(shí)別[D];清華大學(xué);2003年

相關(guān)碩士學(xué)位論文 前7條

1 宋詩超;基于Kinect的三維人體建模與測量的研究[D];東華大學(xué);2013年

2 王占軍;小學(xué)低年級(jí)學(xué)生直線跑偏斜現(xiàn)象分析與教學(xué)糾正措施研究[D];華東師范大學(xué);2010年

3 張偉娟;視頻序列中人體簡單行為識(shí)別的關(guān)鍵技術(shù)研究[D];青島科技大學(xué);2010年

4 肖雪;基于視頻序列的人體骨架提取與三維重建[D];大連理工大學(xué);2009年

5 陶增羽;人體膝關(guān)節(jié)的耦合特性及其前向不穩(wěn)的步態(tài)分析[D];吉林大學(xué);2009年

6 喬建軍;基于運(yùn)動(dòng)捕獲的運(yùn)動(dòng)編輯技術(shù)研究[D];山東大學(xué);2007年

7 馮蓮;基于視頻的人體運(yùn)動(dòng)跟蹤技術(shù)研究[D];湖南大學(xué);2006年

，

本文編號(hào)：1790089