本文選題：特征區(qū)域 + 相似度計算�。� 參考：《江蘇大學(xué)》2017年碩士論文

【摘要】：隨著養(yǎng)豬業(yè)規(guī)�；椭悄芑降牟粩嗵岣�,智能視頻監(jiān)控技術(shù)正在被廣泛地應(yīng)用和研究。傳統(tǒng)養(yǎng)豬業(yè)要求飼養(yǎng)員實時獲取豬只狀態(tài)信息,以便及時發(fā)現(xiàn)豬只異常,這不僅費時費力,還會干擾豬只的正常生長。針對此問題,本文提出了基于機器視覺的豬個體身份和飲水行為的識別方法,用此方法能夠提高豬場的生產(chǎn)效益,并減少飼養(yǎng)員的工作量。首先,針對豬只的非剛體特性,提取俯視監(jiān)控視頻中具有穩(wěn)定性和獨特性的特征區(qū)域,并依次提取顏色信息熵、形狀參數(shù)、Tamura紋理等多種特征,組合構(gòu)成多維特征向量用于表征豬只身份,結(jié)合向量相似度計算方法,得到待識別豬只和訓(xùn)練樣本豬只之間的相似性,從而實現(xiàn)豬個體的身份識別。其次,針對豬只飲水時姿態(tài)相對固定的特性,采用改進的Douglas-Peukcer多邊形近似法對飲水區(qū)域內(nèi)的豬只輪廓進行擬合,并提取角度和距離特征,構(gòu)建具有尺度不變性和旋轉(zhuǎn)不變性的二維特征量用于表征豬只飲水狀態(tài),利用匈牙利算法得到輪廓片段之間的最優(yōu)匹配,再計算該匹配下的匹配代價,完成輪廓的匹配工作,從而實現(xiàn)豬只飲水行為的識別。最后,針對身份識別算法,通過測試不同背部特征區(qū)域邊長下的識別率和單只豬的平均識別時間,選擇最優(yōu)邊長,同時針對飲水行為識別算法,通過測試不同相似度閾值下的識別率,選擇最優(yōu)閾值。再利用MATLAB GUI設(shè)計圖像處理界面,完成參數(shù)設(shè)置、身份識別、飲水行為識別等功能,實現(xiàn)豬只身份識別和飲水行為識別。實驗結(jié)果表明,測試幀中豬個體身份的識別率為86.7%,識別單只豬的平均時間為1.9154s,相比于其他典型方法,在保證時間性能的前提下取得了較高的識別率,同時豬只飲水行為的識別率為94.05%,較好地區(qū)分了飲水狀態(tài)和非飲水狀態(tài),達到了研究的預(yù)期效果。本文采用機器視覺技術(shù),實現(xiàn)了豬只的身份和飲水行為的智能監(jiān)測和識別,為今后對群養(yǎng)豬采食、排便等行為的識別研究打下了基礎(chǔ),同時為探索牲畜的身份及飲水行為識別提供了新思路。
[Abstract]:With the continuous improvement of the scale and intelligence of pig industry, intelligent video surveillance technology is widely used and studied. The traditional pig industry requires the keepers to obtain the status information of pigs in real time in order to find the abnormal pigs in time, which not only takes time and effort, but also interferes with the normal growth of pigs. In order to solve this problem, a machine vision based identification method for pig individual identity and drinking water behavior is proposed, which can improve the production efficiency of pig farm and reduce the workload of breeders. First of all, aiming at the non-rigid body characteristics of pigs, the stable and unique feature areas in the overhead surveillance video are extracted, and the color information entropy, the shape parameter Tamura texture and other features are extracted in turn. The combination of multi-dimensional feature vectors is used to represent pig identity. Combining the vector similarity calculation method, the similarity between the pig to be identified and the training sample pig is obtained, so that the identity of pig individual can be realized. Secondly, the improved Douglas-Peukcer polygonal approximation method is used to fit the profile of pigs in drinking water, and the angle and distance characteristics are extracted. Two dimensional characteristic quantities with scale invariance and rotation invariance are constructed to represent the drinking state of pigs. The optimal matching between contour segments is obtained by using Hungarian algorithm. Then the matching cost is calculated and the contour matching is completed. Thus, the recognition of drinking water behavior of pigs is realized. Finally, according to the identification algorithm, by testing the recognition rate of different back feature region side length and the average recognition time of single pig, the optimal side length is selected, and the drinking water behavior recognition algorithm is also used. The optimal threshold is selected by testing the recognition rate under different similarity thresholds. Then the image processing interface is designed by using MATLAB GUI, and the functions of parameter setting, identity recognition, drinking behavior identification and so on are completed to realize pig identification and drinking behavior recognition. The experimental results show that the identification rate of pig in the test frame is 86.7, and the average time of identifying a single pig is 1.9154s. Compared with other typical methods, a high recognition rate is obtained on the premise of ensuring the performance of the time. At the same time, the recognition rate of drinking behavior of pigs is 94.05, which can distinguish the drinking state from non-drinking state, and reach the expected effect of the study. In this paper, the machine vision technology is used to realize the intelligent monitoring and recognition of pig identity and drinking water behavior, which lays a foundation for the future research on the identification of feeding and defecation behaviors of pigs. At the same time, it provides a new idea for the identification of livestock and the identification of drinking water behavior.
【學(xué)位授予單位】：江蘇大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：S828;TP391.41

【參考文獻】

相關(guān)期刊論文 前10條

1 ;加快推進生豬養(yǎng)殖業(yè)轉(zhuǎn)型升級 促進生豬生產(chǎn)持續(xù)健康有序發(fā)展 農(nóng)業(yè)部畜牧業(yè)司司長馬有祥解讀《全國生豬生產(chǎn)發(fā)展規(guī)劃(2016-2020年)》[J];北方牧業(yè);2016年09期

2 郭依正;朱偉興;馬長華;陳晨;;基于Isomap和支持向量機算法的俯視群養(yǎng)豬個體識別[J];農(nóng)業(yè)工程學(xué)報;2016年03期

3 張鳴;閆紅梅;;基于Matlab GUI的信號與系統(tǒng)實驗平臺設(shè)計[J];實驗技術(shù)與管理;2016年01期

4 謝雙云;王芳;田建艷;黨亞男;;融合高斯混合建模和圖像�；呢i只目標檢測[J];黑龍江畜牧獸醫(yī);2016年01期

5 劉龍申;沈明霞;柏廣宇;周波;陸明洲;楊曉靜;;基于機器視覺的母豬分娩檢測方法研究[J];農(nóng)業(yè)機械學(xué)報;2014年03期

6 劉波;朱偉興;霍冠英;;生豬輪廓紅外與光學(xué)圖像的融合算法[J];農(nóng)業(yè)工程學(xué)報;2013年17期

7 胡煉;羅錫文;曾山;張智剛;陳雄飛;林潮興;;基于機器視覺的株間機械除草裝置的作物識別與定位方法[J];農(nóng)業(yè)工程學(xué)報;2013年10期

8 林曉澤;周絮語;李相軍;;基于輪廓的旋轉(zhuǎn)和尺度不變區(qū)域的檢測[J];計算機應(yīng)用研究;2012年05期

9 徐長新;彭國華;;二維Otsu閾值法的快速算法[J];計算機應(yīng)用;2012年05期

10 許新征;丁世飛;史忠植;賈偉寬;;圖像分割的新理論和新方法[J];電子學(xué)報;2010年S1期

相關(guān)碩士學(xué)位論文 前3條

1 潘珍;基于輪廓的形狀識別方法研究[D];西南大學(xué);2012年

2 張毅;基于亮度歸一化的人臉識別的研究及應(yīng)用[D];復(fù)旦大學(xué);2010年

3 徐秋平;基于圖割理論的目標提取方法研究[D];陜西師范大學(xué);2009年

，

本文編號：1884621