本文關(guān)鍵詞： 計(jì)算機(jī)視覺 糧包計(jì)數(shù) 目標(biāo)檢測(cè) 目標(biāo)跟蹤 運(yùn)動(dòng)預(yù)測(cè)　出處：《浙江理工大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：對(duì)密集型的糧食生產(chǎn)、加工企業(yè)而言,糧包儲(chǔ)運(yùn)出庫(kù)、入庫(kù)數(shù)量統(tǒng)計(jì)的準(zhǔn)確性關(guān)系到企業(yè)的生產(chǎn)效益。而在這些企業(yè)的生產(chǎn)線上,糧包的自動(dòng)、精確計(jì)量技術(shù)仍然是一個(gè)難題。傳統(tǒng)的光電糧包計(jì)數(shù)器,根據(jù)“光電傳感”原理,通過(guò)計(jì)算包袋遮擋紅外線的時(shí)間長(zhǎng)短進(jìn)行計(jì)數(shù)。但是這種計(jì)數(shù)方式存在這幾方面的問(wèn)題:有飛蟲或雜物遮擋傳感器時(shí)會(huì)對(duì)包袋計(jì)數(shù)產(chǎn)生干擾;兩包完全重疊時(shí)或三個(gè)以上包袋粘連時(shí),計(jì)數(shù)產(chǎn)生誤差;功能單一,無(wú)法識(shí)別糧包破包等情況。計(jì)算機(jī)視覺技術(shù)可以很好地解決以上存在的問(wèn)題,因此針對(duì)包袋的自動(dòng)計(jì)數(shù)問(wèn)題本文提出一種新的思路:基于計(jì)算機(jī)視覺技術(shù)實(shí)現(xiàn)運(yùn)動(dòng)糧包在線自動(dòng)計(jì)數(shù)。即通過(guò)視頻分析和圖像處理,實(shí)時(shí)在線對(duì)運(yùn)動(dòng)包袋進(jìn)行自動(dòng)計(jì)數(shù),解決連包、漏包情況下計(jì)數(shù)誤差大的問(wèn)題。通過(guò)對(duì)通道中包袋的運(yùn)動(dòng)情況分析,本文提出了一種基于跟蹤檢測(cè)的包袋計(jì)數(shù)方法。首先,對(duì)進(jìn)入監(jiān)控區(qū)域的包袋目標(biāo)進(jìn)行跟蹤,當(dāng)檢測(cè)到目標(biāo)越過(guò)第一條檢測(cè)線時(shí),跟蹤檢測(cè)目標(biāo)連通區(qū)域內(nèi)獨(dú)立包袋數(shù)目。當(dāng)目標(biāo)越過(guò)第二條檢測(cè)線時(shí)對(duì)通道內(nèi)流經(jīng)包袋數(shù)目進(jìn)行精確累計(jì)。針對(duì)包袋的運(yùn)動(dòng)特點(diǎn),本文提出了基于多項(xiàng)式運(yùn)動(dòng)插值函數(shù)的質(zhì)心位置預(yù)測(cè)方法對(duì)包袋目標(biāo)進(jìn)行跟蹤匹配,并采用了多線程編程技術(shù),實(shí)現(xiàn)多目標(biāo)自動(dòng)跟蹤。同時(shí),研究了修正系數(shù)?對(duì)預(yù)測(cè)誤差的影響,實(shí)驗(yàn)結(jié)果顯示?取0附近的值時(shí),目標(biāo)跟蹤效果最佳。另外,針對(duì)所跟蹤的目標(biāo)連通域內(nèi)包袋粘連計(jì)數(shù)問(wèn)題,提出了基于面積統(tǒng)計(jì)和連通域分析的盲分割計(jì)數(shù)方法,該方法可以有效地檢測(cè)出包袋粘連情況,并計(jì)算出連通區(qū)域獨(dú)立包袋數(shù)目。最后,對(duì)4通道中包袋流動(dòng)視頻序列進(jìn)行了實(shí)驗(yàn)分析。實(shí)驗(yàn)結(jié)果顯示,在攝像頭采幀率在30幀/秒,通道的傾斜程度在25°~35°之間,包袋運(yùn)動(dòng)速度大約在35~58cm/s,監(jiān)控區(qū)域內(nèi)包袋粘連不超過(guò)4包的情況下,4通道在線包袋計(jì)數(shù)儀的計(jì)數(shù)準(zhǔn)確率可以達(dá)到98.11%。此外,實(shí)驗(yàn)結(jié)果驗(yàn)證了本文包袋自動(dòng)計(jì)數(shù)方法的有效性,在此基礎(chǔ)之上,本文設(shè)計(jì)了4通道糧包在線計(jì)數(shù)系統(tǒng)在實(shí)際場(chǎng)景中的應(yīng)用解決方案。
[Abstract]:For the intensive grain production and processing enterprises, the accuracy of storage and transportation of grain and storage quantity statistics is related to the production benefit of the enterprises. In the production line of these enterprises, the grain package is automatic. Accurate measurement technology is still a difficult problem. The traditional photoelectric grain package counter, according to the principle of "photoelectric sensing", Counting by calculating the time of envelope blocking infrared ray. But there are some problems in this counting method: when there are flying insects or sundries to block the sensor, the bag count will be interfered; When two packets are completely overlapped or when more than three bags are conglutinated, the counting error is produced; the function is single and the broken grain package can not be identified. The computer vision technology can solve the above problems very well. In this paper, a new method is proposed to realize the automatic counting of moving bags based on computer vision, that is, through video analysis and image processing, the automatic counting of moving bags is carried out online in real time. By analyzing the movement of bags in the channel, a bag counting method based on tracking detection is proposed. Firstly, the bag objects entering the monitoring area are tracked. When the target crosses the first detection line, the number of independent bags in the connected area is tracked. When the target crosses the second detection line, the number of bags flowing through the channel is accurately accumulated. In this paper, the centroid position prediction method based on polynomial motion interpolation function is proposed to track and match the bag target, and the multi-thread programming technique is used to realize the multi-target automatic tracking. At the same time, the correction coefficient is studied. Experimental results show that? When the value near 0 is taken, the target tracking effect is the best. In addition, a blind segmentation counting method based on area statistics and connected domain analysis is proposed to solve the problem of bag adhesion counting in the connected domain. This method can effectively detect the bag adhesion and calculate the number of independent bags in the connected region. Finally, the experimental analysis of the packet flow video sequence in the four channels is carried out. The experimental results show that the frame rate of the camera is 30 frames per second. The inclination of the channel is between 25 擄and 35 擄, the velocity of bag motion is about 35 ~ 58 cm / s, and the counting accuracy of the on-line bag counter can reach 98.11 when the bag adhesion in the monitoring area is not more than 4 packets. The experimental results verify the effectiveness of this method. On the basis of this, a 4-channel on-line counting system for grain package is designed.
【學(xué)位授予單位】：浙江理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TB486;TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 付文濤;;解析視覺識(shí)別系統(tǒng)中的設(shè)計(jì)文化符碼三層論[J];包裝工程;2008年06期

2 沈丹萍;;企業(yè)視覺識(shí)別的數(shù)字化設(shè)計(jì)研究[J];硅谷;2011年24期

3 賈麗;;從“嶗山可樂(lè)”的浮沉探究“老品牌”的視覺識(shí)別設(shè)計(jì)[J];中國(guó)包裝工業(yè);2013年14期

4 唐湖;論企業(yè)視覺識(shí)別形象中的基礎(chǔ)系統(tǒng)設(shè)計(jì)[J];株洲工學(xué)院學(xué)報(bào);1994年03期

5 湯潔;;視覺識(shí)別設(shè)計(jì)在服裝品牌終端形象中的應(yīng)用[J];包裝工程;2012年06期

6 王波;李永建;盛金根;郭孜政;;振動(dòng)對(duì)視覺識(shí)別效率影響的實(shí)驗(yàn)研究[J];機(jī)械設(shè)計(jì)與制造;2012年12期

7 劉希龍;錢翰博;曹志強(qiáng);譚民;;基于符號(hào)特征的視覺識(shí)別方法[J];華中科技大學(xué)學(xué)報(bào)(自然科學(xué)版);2011年S2期

8 鄭云鳳;樊海燕;;傳統(tǒng)與現(xiàn)代的視覺傳遞——談古城中高新區(qū)的視覺識(shí)別設(shè)計(jì)[J];藝術(shù)與設(shè)計(jì)(理論);2009年11期

9 王玨;王學(xué)義;金春哲;余學(xué)軍;高雋;王云景;;不同能見度條件下飛機(jī)圖像視覺識(shí)別的研究[J];海軍醫(yī)學(xué);1994年04期

10 劉敦權(quán)，李家寶，，葛鴻翰，王濤，相儒平;激光視覺識(shí)別及其應(yīng)用[J];組合機(jī)床與自動(dòng)化加工技術(shù);1994年05期

相關(guān)會(huì)議論文 前2條

1 鐘浩;姜國(guó)華;王穎;吳文燦;廖國(guó)鋒;牟曉非;;液晶漢字尺寸對(duì)視覺識(shí)別工效的影響[A];第三屆全國(guó)人—機(jī)—環(huán)境系統(tǒng)工程學(xué)術(shù)會(huì)議論文集[C];1997年

2 沈模衛(wèi);;對(duì)漢字視覺識(shí)別加工過(guò)程的實(shí)驗(yàn)研究[A];面向21世紀(jì)的科技進(jìn)步與社會(huì)經(jīng)濟(jì)發(fā)展（下冊(cè)）[C];1999年

相關(guān)重要報(bào)紙文章 前10條

1 涂義宏;九一二大隊(duì)視覺識(shí)別會(huì)議挖掘文化內(nèi)涵[N];中國(guó)有色金屬報(bào);2009年

2 聶琳　陳毛羽 黃成輝;視覺識(shí)別：塑造標(biāo)準(zhǔn)形象[N];中國(guó)國(guó)門時(shí)報(bào);2010年

3 中國(guó)醫(yī)師協(xié)會(huì)檢驗(yàn)醫(yī)師分會(huì)會(huì)長(zhǎng) 叢玉隆;機(jī)器視覺識(shí)別 形態(tài)學(xué)檢驗(yàn)新趨向[N];健康報(bào);2010年

4 周建中 張輝;這個(gè)設(shè)計(jì)很營(yíng)銷[N];中國(guó)經(jīng)營(yíng)報(bào);2001年

5 記者 王太安 通訊員 王忠亮;中冶京唐強(qiáng)化企業(yè)基礎(chǔ)和文化管理[N];中國(guó)冶金報(bào);2007年

6 陸程;構(gòu)建“五個(gè)一”安全視覺識(shí)別體系[N];經(jīng)理日?qǐng)?bào);2006年

7 楊q

本文編號(hào)：1528738