基于機(jī)器視覺的新生仔豬目標(biāo)識(shí)別方法研究與實(shí)現(xiàn)
發(fā)布時(shí)間：2019-05-29 23:00
【摘要】：[目的]新生仔豬目標(biāo)檢測(cè)是母豬分娩監(jiān)測(cè)的關(guān)鍵環(huán)節(jié)。[方法]通過自制圖像采集器采集母豬分娩視頻圖像,機(jī)器視覺系統(tǒng)獲取分娩圖像信息,選取Canny算子對(duì)圖像進(jìn)行邊緣檢測(cè),采用Otsu算法對(duì)圖像進(jìn)行二值變換,應(yīng)用滑動(dòng)平均算法和形態(tài)學(xué)開運(yùn)算對(duì)二值圖像濾波消噪,提取圖像最大連通域,利用團(tuán)序列檢測(cè)算法對(duì)母豬目標(biāo)進(jìn)行分割,對(duì)分割后區(qū)域進(jìn)行仔豬目標(biāo)識(shí)別。[結(jié)果]試驗(yàn)結(jié)果表明,團(tuán)序列檢測(cè)算法能夠準(zhǔn)確分割出母豬目標(biāo),檢測(cè)仔豬目標(biāo)的正確率達(dá)到95.5%。[結(jié)論]提出一種能夠有效識(shí)別新生仔豬目標(biāo)的方法,為仔豬的出生預(yù)警提供了技術(shù)支撐。
[Abstract]:[objective] Target detection of newborn piglets is the key link of sows delivery monitoring. [methods] the video images of sow delivery were collected by self-made image collector, the delivery image information was obtained by machine vision system, the edge of the image was detected by Canny operator, and the binary transformation of the image was carried out by Otsu algorithm. The moving average algorithm and morphological open operation are used to filter and Denoise the binary image, extract the most Dalian domain of the image, segment the sows' target by using the cluster sequence detection algorithm, and recognize the target of piglets in the segmented area. [results] the experimental results show that the cluster sequence detection algorithm can accurately segment sows, and the correct rate of detection of piglets is 95.5%. [conclusion] A method which can effectively identify the target of newborn piglets is proposed, which provides technical support for birth early warning of piglets.
【作者單位】： 南京農(nóng)業(yè)大學(xué)工學(xué)院;
【基金】：國(guó)家自然科學(xué)基金項(xiàng)目(61503187) 江蘇省農(nóng)機(jī)三新工程項(xiàng)目(NJ2016-10) 江蘇省產(chǎn)學(xué)研合作前瞻性聯(lián)合創(chuàng)新資金項(xiàng)目(BY2014128-01)
【分類號(hào)】：S818.9;S828
本文編號(hào)：2488297
[Abstract]:[objective] Target detection of newborn piglets is the key link of sows delivery monitoring. [methods] the video images of sow delivery were collected by self-made image collector, the delivery image information was obtained by machine vision system, the edge of the image was detected by Canny operator, and the binary transformation of the image was carried out by Otsu algorithm. The moving average algorithm and morphological open operation are used to filter and Denoise the binary image, extract the most Dalian domain of the image, segment the sows' target by using the cluster sequence detection algorithm, and recognize the target of piglets in the segmented area. [results] the experimental results show that the cluster sequence detection algorithm can accurately segment sows, and the correct rate of detection of piglets is 95.5%. [conclusion] A method which can effectively identify the target of newborn piglets is proposed, which provides technical support for birth early warning of piglets.
【作者單位】： 南京農(nóng)業(yè)大學(xué)工學(xué)院;
【基金】：國(guó)家自然科學(xué)基金項(xiàng)目(61503187) 江蘇省農(nóng)機(jī)三新工程項(xiàng)目(NJ2016-10) 江蘇省產(chǎn)學(xué)研合作前瞻性聯(lián)合創(chuàng)新資金項(xiàng)目(BY2014128-01)
【分類號(hào)】：S818.9;S828
【相似文獻(xiàn)】
相關(guān)博士學(xué)位論文 前1條
1 郁志宏;基于機(jī)器視覺的種蛋篩選及孵化成活性檢測(cè)研究[D];內(nèi)蒙古農(nóng)業(yè)大學(xué);2006年
相關(guān)碩士學(xué)位論文 前3條
1 劉衛(wèi)民;基于機(jī)器視覺的奶牛體尺參數(shù)測(cè)量研究[D];山東農(nóng)業(yè)大學(xué);2016年
2 曹鵬程;基于機(jī)器視覺和力學(xué)特性肉雞體質(zhì)健康模型構(gòu)建[D];新疆農(nóng)業(yè)大學(xué);2016年
3 鄧海霞;基于機(jī)器視覺的群體禽蛋大小檢測(cè)方法研究[D];華中農(nóng)業(yè)大學(xué);2006年
，本文編號(hào)：2488297
本文鏈接：http://sikaile.net/yixuelunwen/dongwuyixue/2488297.html
最近更新
教材專著
