《電子技術(shù)應(yīng)用》
您所在的位置:首頁(yè) > 其他 > 設(shè)計(jì)應(yīng)用 > 智能車(chē)控制的數(shù)顯儀表識(shí)別技術(shù)研究
智能車(chē)控制的數(shù)顯儀表識(shí)別技術(shù)研究
信息技術(shù)與網(wǎng)絡(luò)安全 10期
吳開(kāi)田1,,陳 丹 1,2,邱 洋1,,徐哲壯1,,2,,簡(jiǎn)榮貴1,,陳 劍1,2
(1.福州大學(xué) 電氣工程與自動(dòng)化學(xué)院,,福建 福州350000,; 2.工業(yè)自動(dòng)化控制技術(shù)與信息處理福建省高校重點(diǎn)實(shí)驗(yàn)室,,福建 福州350000)
摘要: 在工業(yè)現(xiàn)場(chǎng)中,通過(guò)移動(dòng)機(jī)器人自主巡檢與讀表的應(yīng)用越來(lái)越廣泛,。數(shù)顯儀表的讀數(shù)受到光照,、對(duì)焦和場(chǎng)景等因素的影響,存在識(shí)別精度低的問(wèn)題,。針對(duì)上述問(wèn)題,,提出了融合感知與控制的數(shù)顯儀表識(shí)別機(jī)制,首先使用圖像目標(biāo)檢測(cè)網(wǎng)絡(luò)識(shí)別數(shù)顯儀表,,標(biāo)出目標(biāo)區(qū)域,。隨后設(shè)計(jì)基于圖像反饋的智能車(chē)控制策略,以此抑制模糊對(duì)焦的影響,。再使用改進(jìn)的自動(dòng)色彩均衡(ACE)算法對(duì)基于色彩膨脹切割的數(shù)字塊進(jìn)行圖像色彩增強(qiáng),。最后通過(guò)卷積循環(huán)神經(jīng)網(wǎng)絡(luò)(CRNN)進(jìn)行實(shí)時(shí)儀表數(shù)字識(shí)別。通過(guò)實(shí)驗(yàn)驗(yàn)證了所設(shè)計(jì)技術(shù)的性能,,證明了方法的可行性和有效性,。
中圖分類(lèi)號(hào): TP242;TP391
文獻(xiàn)標(biāo)識(shí)碼: A
DOI: 10.19358/j.issn.2096-5133.2021.10.009
引用格式: 吳開(kāi)田,,陳丹,,邱洋,等. 智能車(chē)控制的數(shù)顯儀表識(shí)別技術(shù)研究[J].信息技術(shù)與網(wǎng)絡(luò)安全,,2021,,40(10):53-60.
Research on identification technology of digital display instrument based on intelligent vehicle control
Wu Kaitian1,,Chen Dan1,,2,Qiu Yang1,,Xu Zhezhuang1,,2,Jian Ronggui1,,Chen Jian1,,2
(1.College of Electrical Engineering and Automation,F(xiàn)uzhou University,,F(xiàn)uzhou 350000,,China; 2.Key Laboratory of Industrial Automation Control Technology and Information Processing,, Education Department of Fujian Province,,F(xiàn)uzhou 350000,China)
Abstract: In the industrial field, the application of autonomous inspection and reading tables through mobile robots is more and more widely. The reading of digital display instrument is affected by factors such as illumination, focusing and scene, which has the problem of low recognition accuracy. Because of the above problems, this paper proposes a digital display instrument recognition mechanism based on fusion perception and control. Firstly, the image target detection network is used to identify the digital display instrument and mark the target area. Then an intelligent vehicle control strategy based on image feedback is designed to suppress the influence of fuzzy focus. Then the improved automatic color equalization(ACE) algorithm is used to enhance the image color of digital blocks based on color expansion cutting. Finally, real-time instrument digital recognition is acheived using convolutional recurrent neural network(CRNN). In this paper, the performance of the designed technology is verified by experiments, and the feasibility and efficiency of the method is proved.
Key words : (1.College of Electrical Engineering and Automation,,F(xiàn)uzhou University,,F(xiàn)uzhou 350000,,China; 2.Key Laboratory of Industrial Automation Control Technology and Information Processing,, Education Department of Fujian Province,,F(xiàn)uzhou 350000,China)

0 引言

隨著人工智能技術(shù)的快速發(fā)展,,人工智能服務(wù)經(jīng)濟(jì)社會(huì)發(fā)展的情況越來(lái)越普遍,,各個(gè)行業(yè)智能化和自動(dòng)化的程度越來(lái)越高,移動(dòng)機(jī)器人是人工智能的一個(gè)重要體現(xiàn),,目前已經(jīng)廣泛應(yīng)用在智能家居,、航天航空、工業(yè)生產(chǎn)線,、商場(chǎng)服務(wù)業(yè),、安保、物流分揀,、助老助殘,、工業(yè)巡檢、軍事勘察等各個(gè)領(lǐng)域[1-3],。移動(dòng)機(jī)器人本體運(yùn)動(dòng)控制的研究雖然具有一定的基礎(chǔ),,但機(jī)器人本體的運(yùn)動(dòng)功能已經(jīng)無(wú)法適應(yīng)目前市場(chǎng)的需求,許多研究者將目光集中在機(jī)器人后續(xù)功能的開(kāi)發(fā),。

在工業(yè)生產(chǎn)的各個(gè)領(lǐng)域中,,數(shù)顯式儀表分布非常廣泛,它時(shí)刻記錄著各個(gè)生產(chǎn)節(jié)點(diǎn)的數(shù)據(jù)信息,,它是工業(yè)生產(chǎn)的關(guān)鍵數(shù)據(jù)來(lái)源,。由于數(shù)顯式具有顯示簡(jiǎn)單、使用簡(jiǎn)便,、精確度高,、集成度高等優(yōu)點(diǎn),因此其應(yīng)用越來(lái)越廣泛,。隨著機(jī)器人技術(shù)的快速發(fā)展,,使用移動(dòng)機(jī)器人代替人工巡檢的應(yīng)用已經(jīng)越來(lái)越多[4]。

目前,,數(shù)顯儀表的數(shù)字識(shí)別方法主要有三種:自動(dòng)抄表(Automated Meter Reading,,AMR)[5]、人工記錄和圖像識(shí)別[6],。很多數(shù)顯式儀表不具有無(wú)線通信模塊或者計(jì)算機(jī)接口,,無(wú)法通過(guò)AMR技術(shù)進(jìn)行自動(dòng)記錄數(shù)據(jù),而且AMR技術(shù)通常需要對(duì)儀表本身進(jìn)行結(jié)構(gòu)改造,,這是一項(xiàng)高成本,、長(zhǎng)時(shí)間以及工作量巨大的工作,。傳統(tǒng)的人工抄表無(wú)法適應(yīng)應(yīng)用廣泛的儀表,迫使研究學(xué)者從其他方面解決這些問(wèn)題,。越來(lái)越多的研究學(xué)者將目光轉(zhuǎn)移到圖像上,,通過(guò)圖像對(duì)數(shù)顯儀表進(jìn)行數(shù)字識(shí)別可以很好地降低成本,提升識(shí)別精度,。



本文詳細(xì)內(nèi)容請(qǐng)下載:http://forexkbc.com/resource/share/2000003804





作者信息:

吳開(kāi)田1,,陳  丹 1,2,,邱  洋1,,徐哲壯1,2,,簡(jiǎn)榮貴1,,陳  劍1,2

(1.福州大學(xué) 電氣工程與自動(dòng)化學(xué)院,,福建 福州350000,;

2.工業(yè)自動(dòng)化控制技術(shù)與信息處理福建省高校重點(diǎn)實(shí)驗(yàn)室,福建 福州350000)


此內(nèi)容為AET網(wǎng)站原創(chuàng),,未經(jīng)授權(quán)禁止轉(zhuǎn)載,。