基于車載機(jī)器視覺的安全帶識別方法研究
發(fā)布時(shí)間：2019-06-17 14:56
【摘要】：為提高安全帶佩戴率,論文從三點(diǎn)式安全帶使用過程中存在的問題出發(fā),分析三點(diǎn)式安全帶的不同佩戴方式對乘員損傷的影響,利用車載機(jī)器視覺對其進(jìn)行識別,提出安全帶識別評價(jià)方法,構(gòu)建滿足實(shí)時(shí)性和高精度要求的識別模型,實(shí)現(xiàn)了嵌入式車載安全帶監(jiān)控系統(tǒng)設(shè)計(jì)。論文研究內(nèi)容包括： 1)三點(diǎn)式安全帶使用情況調(diào)查與分析。針對我國典型城市安全帶的使用狀況展開調(diào)查,結(jié)果顯示,安全帶使用過程中存在兩類問題：不規(guī)范佩戴安全帶和卷曲佩戴安全帶。其中,導(dǎo)致安全帶佩戴提示系統(tǒng)失效的不規(guī)范佩戴行為包括：單獨(dú)使用安全帶帶扣、預(yù)佩戴和僅系肩帶；卷曲佩戴包括：肩帶卷曲、腰帶卷曲和嚴(yán)重卷曲。 2)三點(diǎn)式安全帶的不同佩戴方式對乘員損傷影響。采用MADYMO構(gòu)建乘員約束系統(tǒng)模型,并驗(yàn)證模型的有效性。運(yùn)用該模型進(jìn)行三點(diǎn)式安全帶在不同佩戴方式下的乘員損傷分析,結(jié)果表明：車輛碰撞時(shí),預(yù)佩戴安全帶的乘員將從座椅位置飛出；僅系肩帶將產(chǎn)生明顯的下潛、滑移運(yùn)動(dòng)。上述情況均導(dǎo)致乘員受到致命性損傷。相比正確使用三點(diǎn)式安全帶,卷曲佩戴將導(dǎo)致乘員各項(xiàng)損傷指標(biāo)明顯上升。因此,對三點(diǎn)式安全帶不同的佩戴方式進(jìn)行識別,為充分發(fā)揮安全帶應(yīng)有的保護(hù)作用,具有積極意義。 3)車載視頻監(jiān)控平臺搭建及安全帶圖像采集試驗(yàn)設(shè)計(jì)。搭建安全帶圖像采集試驗(yàn)平臺,在CCD傳感器性能參數(shù)、紅外補(bǔ)光裝置和特殊材料安全帶等方面展開具體研究；設(shè)計(jì)并實(shí)施不同光線環(huán)境下的車輛行駛試驗(yàn),采集獲得安全帶不同佩戴方式下的乘員圖像信息；研究適用于安全帶識別的圖像預(yù)處理技術(shù),為構(gòu)建安全帶識別的多特征參數(shù)模型奠定基礎(chǔ)。 4)構(gòu)建滿足實(shí)時(shí)性要求的安全帶識別模型。針對安全帶在線檢測的要求,采用主成分分析法降維后的安全帶空間參數(shù)特征作為輸入向量,選用BP神經(jīng)網(wǎng)絡(luò)作為分類器,構(gòu)建基于BP神經(jīng)網(wǎng)絡(luò)的安全帶識別模型,以滿足實(shí)時(shí)性要求。引入遺傳算法(GA)對其內(nèi)部參數(shù)進(jìn)行優(yōu)化,構(gòu)建基于GA-BP神經(jīng)網(wǎng)絡(luò)的安全帶識別實(shí)時(shí)性模型,以滿足準(zhǔn)確性要求。通過硬件在環(huán)測試(HIL)和模型在環(huán)測試(MIL)驗(yàn)證了模型的實(shí)時(shí)性和準(zhǔn)確性。 5)構(gòu)建滿足高精度要求的卷曲佩戴識別模型。提取安全帶結(jié)構(gòu)參數(shù)的統(tǒng)計(jì)特征值作為輸入向量,選用支持向量機(jī)(SVM)作為模型核心分類器,以交叉驗(yàn)證方法對內(nèi)部參數(shù)進(jìn)行選擇,采用粒子群算法(PSO)對其進(jìn)行優(yōu)化,構(gòu)建基于PSO-SVM的高精度識別模型,并進(jìn)行軟件在環(huán)測試以驗(yàn)證代碼的有效性,從而將其應(yīng)用于高精度離線檢測之中。 6)實(shí)現(xiàn)了嵌入式車載安全帶監(jiān)控系統(tǒng)的設(shè)計(jì)。從分析車載系統(tǒng)對軟硬件的性能要求著手,探討了DSP內(nèi)核高速處理數(shù)據(jù)的特點(diǎn)以及ARM內(nèi)核控制和管理的功能,選擇ICETEK-DM642-B評估板作為硬件平臺,實(shí)現(xiàn)了基于嵌入式技術(shù)的安全帶識別系統(tǒng)的設(shè)計(jì)；完成系統(tǒng)功能的總體設(shè)計(jì)和功能模塊的軟件設(shè)計(jì),并進(jìn)行程序優(yōu)化。 論文研究的創(chuàng)新點(diǎn)如下： 1)提出基于車載機(jī)器視覺識別安全帶的方法,搭建嵌入式車載安全帶識別系統(tǒng)平臺； 2)揭示了三點(diǎn)式安全帶的不同佩戴方式(不規(guī)范佩戴和卷曲佩戴)與乘員損傷之間的關(guān)系； 3)提出安全帶識別的實(shí)時(shí)性和準(zhǔn)確性評價(jià)方法； 4)構(gòu)建基于GA-BP神經(jīng)網(wǎng)絡(luò)的安全帶識別實(shí)時(shí)性模型； 5)構(gòu)建基于PSO-SVM的卷曲佩戴識別高精度模型。
[Abstract]:In order to improve the wearing rate of the safety belt, the paper analyzes the influence of the different wearing modes of the three-point safety belt on the injury of the passenger from the problems existing in the use of the three-point safety belt, The identification model satisfying the real-time and high-precision requirements is constructed, and the design of the embedded in-vehicle safety belt monitoring system is realized. The research contents include: 1) Investigation and distribution of the use of three-point safety belt Analysis of the use situation of the typical urban safety belt in China, the result shows that there are two kinds of problems in the use of the safety belt: the safety belt and the curling and wearing safety are not regulated Belt. In which, the non-standard wearing behavior that results in a failure of the safety belt wear warning system includes the individual use of the belt buckle, the pre-wear and only the shoulder strap; the crimp wear includes a shoulder strap curl, a belt curl, and a serious roll (2) Different wearing modes of the three-point safety belt to the passenger's loss Impact of injury. Build an occupant restraint system model using MADYMO and verify the model Effectiveness. The model is used to analyze the occupant injury of the three-point safety belt in different wearing modes. The results show that when the vehicle is in collision, the occupant of the pre-wear safety belt will fly out of the seat position; only the shoulder belt will produce a clear subpotential and slide. Moving. This results in a fatal occupant. Sexual damage. The use of a three-point seat belt in comparison to the correct use of a three-point seat belt will result in the occupant's various injury indicators In order to give full play to the protective effect of the safety belt, the wearing mode of the three-point safety belt shall be recognized and the product shall have the product. (3) Construction of on-board video monitoring platform and image collection of safety belt Set the test design. Set up the safety belt image acquisition test platform, and carry out specific research on the performance parameters of the CCD sensor, the infrared light-supplementing device and the special material safety belt, and design and implement the vehicle running test under different light environment, and collect the multiplication of the different wearing modes of the safety belt The paper studies the image pre-processing technology which is suitable for the identification of the safety belt, and provides a multi-feature parameter model for the safety belt recognition. form the foundation.4) Build the foundation to meet the real-time requirements According to the requirement of the on-line detection of the safety belt, the characteristic of the seat belt space parameter after the dimension reduction is taken as an input vector by adopting a main component analysis method, a BP neural network is used as a classifier, a safety belt identification model based on the BP neural network is constructed, The real-time requirement is met. Genetic algorithm (GA) is introduced to optimize the internal parameters, and the real-time model of safety belt recognition based on GA-BP neural network is constructed. The accuracy requirements are met. The model is validated by hardware in the loop test (HIL) and the model in the loop test (MIL) real-time and accuracy.5) The construction of high-precision requirements According to the method, a support vector machine (SVM) is used as the core classifier of the model, the internal parameters are selected by a cross-verification method, the particle swarm optimization (PSO) is adopted to optimize the internal parameters, and the PSO-SV is constructed. M's high-precision identification model, and the software is used in the loop test to verify the validity of the code, so as to apply it to high-precision off-line detection The design of the safety belt monitoring system is carried out. The characteristics of the high-speed processing data of the DSP core and the function of ARM core control and management are discussed from the analysis of the performance requirements of the on-board system. The ICETEK-DM642-B evaluation board is selected as the hardware platform, and the embedded technology is realized. The design of the safety belt recognition system; the overall design of the system function and the soft of the functional module The design of the part and the optimization of the program The innovation points of the thesis are as follows:1) Put forward the method to recognize the safety belt based on the on-board machine vision, and Built-in vehicle-mounted safety belt identification system platform;2) The different wearing modes of the three-point safety belt are revealed (not to be standardized the relationship between the wearing and curling of the wearer) and the occupant's injury;3) The real-time and accuracy evaluation method of safety belt recognition is put forward; and 4) the basis of construction Real-time model of safety belt recognition based on GA-BP neural network
【學(xué)位授予單位】：江蘇大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2014
【分類號】：U463.6;U491.61
本文編號：2501069
[Abstract]:In order to improve the wearing rate of the safety belt, the paper analyzes the influence of the different wearing modes of the three-point safety belt on the injury of the passenger from the problems existing in the use of the three-point safety belt, The identification model satisfying the real-time and high-precision requirements is constructed, and the design of the embedded in-vehicle safety belt monitoring system is realized. The research contents include: 1) Investigation and distribution of the use of three-point safety belt Analysis of the use situation of the typical urban safety belt in China, the result shows that there are two kinds of problems in the use of the safety belt: the safety belt and the curling and wearing safety are not regulated Belt. In which, the non-standard wearing behavior that results in a failure of the safety belt wear warning system includes the individual use of the belt buckle, the pre-wear and only the shoulder strap; the crimp wear includes a shoulder strap curl, a belt curl, and a serious roll (2) Different wearing modes of the three-point safety belt to the passenger's loss Impact of injury. Build an occupant restraint system model using MADYMO and verify the model Effectiveness. The model is used to analyze the occupant injury of the three-point safety belt in different wearing modes. The results show that when the vehicle is in collision, the occupant of the pre-wear safety belt will fly out of the seat position; only the shoulder belt will produce a clear subpotential and slide. Moving. This results in a fatal occupant. Sexual damage. The use of a three-point seat belt in comparison to the correct use of a three-point seat belt will result in the occupant's various injury indicators In order to give full play to the protective effect of the safety belt, the wearing mode of the three-point safety belt shall be recognized and the product shall have the product. (3) Construction of on-board video monitoring platform and image collection of safety belt Set the test design. Set up the safety belt image acquisition test platform, and carry out specific research on the performance parameters of the CCD sensor, the infrared light-supplementing device and the special material safety belt, and design and implement the vehicle running test under different light environment, and collect the multiplication of the different wearing modes of the safety belt The paper studies the image pre-processing technology which is suitable for the identification of the safety belt, and provides a multi-feature parameter model for the safety belt recognition. form the foundation.4) Build the foundation to meet the real-time requirements According to the requirement of the on-line detection of the safety belt, the characteristic of the seat belt space parameter after the dimension reduction is taken as an input vector by adopting a main component analysis method, a BP neural network is used as a classifier, a safety belt identification model based on the BP neural network is constructed, The real-time requirement is met. Genetic algorithm (GA) is introduced to optimize the internal parameters, and the real-time model of safety belt recognition based on GA-BP neural network is constructed. The accuracy requirements are met. The model is validated by hardware in the loop test (HIL) and the model in the loop test (MIL) real-time and accuracy.5) The construction of high-precision requirements According to the method, a support vector machine (SVM) is used as the core classifier of the model, the internal parameters are selected by a cross-verification method, the particle swarm optimization (PSO) is adopted to optimize the internal parameters, and the PSO-SV is constructed. M's high-precision identification model, and the software is used in the loop test to verify the validity of the code, so as to apply it to high-precision off-line detection The design of the safety belt monitoring system is carried out. The characteristics of the high-speed processing data of the DSP core and the function of ARM core control and management are discussed from the analysis of the performance requirements of the on-board system. The ICETEK-DM642-B evaluation board is selected as the hardware platform, and the embedded technology is realized. The design of the safety belt recognition system; the overall design of the system function and the soft of the functional module The design of the part and the optimization of the program The innovation points of the thesis are as follows:1) Put forward the method to recognize the safety belt based on the on-board machine vision, and Built-in vehicle-mounted safety belt identification system platform;2) The different wearing modes of the three-point safety belt are revealed (not to be standardized the relationship between the wearing and curling of the wearer) and the occupant's injury;3) The real-time and accuracy evaluation method of safety belt recognition is put forward; and 4) the basis of construction Real-time model of safety belt recognition based on GA-BP neural network
【學(xué)位授予單位】：江蘇大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2014
【分類號】：U463.6;U491.61
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 李汝寧;何勇靈;;基于遺傳算法的柴油機(jī)噴油系統(tǒng)模型參數(shù)辨識[J];北京航空航天大學(xué)學(xué)報(bào);2012年04期
2 雷正保,鐘志華;汽車碰撞仿真研究發(fā)展趨勢[J];長沙交通學(xué)院學(xué)報(bào);1999年01期
3 湯寶平;劉文藝;蔣永華;;基于交叉驗(yàn)證法優(yōu)化參數(shù)的Morlet小波消噪方法[J];重慶大學(xué)學(xué)報(bào);2010年01期
4 劉輝;趙建彪;李闖;楊松;林學(xué)東;董仁;高紅;;基于限制車速的安全帶強(qiáng)制使用裝置[J];電子設(shè)計(jì)工程;2011年01期
5 李峰,曾超,徐向東;駕駛防瞌睡裝置中人眼快速定位方法研究[J];光學(xué)儀器;2002年Z1期
6 張烈平;張?jiān)粕?楊桂華;;基于粒子群算法的流程工業(yè)生產(chǎn)調(diào)度研究[J];計(jì)算機(jī)工程與應(yīng)用;2012年06期
7 馮建強(qiáng),劉文波,于盛林;基于灰度積分投影的人眼定位[J];計(jì)算機(jī)仿真;2005年04期
8 孫志田;張建梅;閆常麗;;基于遺傳算法公交線路網(wǎng)優(yōu)化模型仿真研究[J];計(jì)算機(jī)仿真;2011年11期
9 朱海濤;孫振東;白鵬;呂恒緒;;汽車正面碰撞中乘員的胸部傷害分析[J];交通標(biāo)準(zhǔn)化;2009年11期
10 ＥｂｅｒｈａｒｄＨａｕｇ,ＪａｎＣｌｉｎｃｋｅｍａｉｌｌｉｅ,ＡｎｔｈｏｎｙＫＰｉｃｋｅｔｔ;汽車碰撞仿真與設(shè)計(jì)的最新進(jìn)展和發(fā)展趨勢[J];機(jī)械工程學(xué)報(bào);1998年01期
相關(guān)博士學(xué)位論文 前3條
1 袁東輝;蟻群算法在飛行模擬器平臺中若干應(yīng)用問題的研究[D];吉林大學(xué);2011年
2 黃靜華;支持向量機(jī)算法研究及在氣象數(shù)據(jù)挖掘中的應(yīng)用[D];中國礦業(yè)大學(xué)（北京）;2011年
3 葛如海;汽車正面碰撞乘員約束系統(tǒng)匹配研究[D];江蘇大學(xué);2007年
，本文編號：2501069
本文鏈接：http://sikaile.net/kejilunwen/jiaotonggongchenglunwen/2501069.html
最近更新
教材專著
