本文選題：視覺車輛檢測 + 視覺車輛跟蹤�。� 參考：《中國科學(xué)技術(shù)大學(xué)》2017年碩士論文

【摘要】：隨著汽車保有量的迅猛增長,公路交通事故已經(jīng)成為全球范圍內(nèi)日趨嚴(yán)重的公共安全問題,亟待解決。前碰撞預(yù)警系統(tǒng)是智能輔助駕駛系統(tǒng)的重要組成部分,能有效降低公路交通事故發(fā)生的概率。車輛檢測和跟蹤的準(zhǔn)確性、連續(xù)性和實時性是影響該系統(tǒng)功能發(fā)揮的決定性因素。其中,車輛定位的準(zhǔn)確性和連續(xù)性是預(yù)警功能的前提,而實時性是預(yù)警功能有效發(fā)揮的關(guān)鍵,能使駕駛者及早發(fā)現(xiàn)險情。因此本文致力于車載單目視覺的車輛檢測與跟蹤算法研究,具體研究內(nèi)容如下:基于主動學(xué)習(xí)的分類器模型訓(xùn)練�；跈C(jī)器學(xué)習(xí)的視覺車輛檢測需要大量帶有標(biāo)簽的樣本數(shù)據(jù),用以訓(xùn)練出能夠準(zhǔn)確分類圖像中車輛與背景的分類器模型。本文提出一種基于錯誤分類樣本抽樣策略的主動學(xué)習(xí)算法,以較小的人工標(biāo)注成本獲得最具信息量的樣本數(shù)據(jù),迭代訓(xùn)練優(yōu)化分類器的性能。Adaboost(Adaptive Boosting)級聯(lián)多目標(biāo)車輛檢測。為了提高車輛檢測的準(zhǔn)確性,本文提出一種分區(qū)域多分類器車輛檢測方法。根據(jù)車輛特征在檢測視野中的差異,把待檢測車輛分類為前向車輛、左斜側(cè)向車輛和右斜側(cè)向車輛,分別訓(xùn)練級聯(lián)分類器進(jìn)行檢測。同時,為了提高車輛檢測速度,提出一種結(jié)合相機(jī)標(biāo)定的多分辨率加速車輛檢測算法,對檢測視野中遠(yuǎn)近不同的車輛采用不同程度的圖像降采樣分別檢測。HOG(Histogram of Oriented Gradients)特征跟蹤與 Adaboost 檢測融合。針對Adaboost級聯(lián)車輛檢測結(jié)果不夠連續(xù)的問題,提出一種Adaboost級聯(lián)檢測與HOG特征跟蹤相互融合的車輛檢測跟蹤算法。通過HOG特征跟蹤的融入,提高了約10%的車輛檢測率,使檢測結(jié)果更加連續(xù)。前碰撞預(yù)警系統(tǒng)設(shè)計實現(xiàn)。文章最后應(yīng)用本文研究的車輛檢測跟蹤算法設(shè)計出一套前碰撞預(yù)警系統(tǒng),通過真實交通場景測試,該系統(tǒng)可以實時、準(zhǔn)確和連續(xù)的檢測跟蹤前方車輛并計算與其距離,實時監(jiān)控前方潛在的碰撞危險,及時發(fā)出預(yù)警信號,從而避免交通事故的發(fā)生。
[Abstract]:With the rapid growth of vehicle ownership, road traffic accidents have become more and more serious public safety problems all over the world. Pre-collision warning system is an important part of intelligent auxiliary driving system, which can effectively reduce the probability of road traffic accidents. The accuracy, continuity and real-time of vehicle detection and tracking are the decisive factors affecting the function of the system. Among them, the accuracy and continuity of vehicle positioning is the premise of early warning function, and real-time is the key to the effective use of early warning function, which can enable the driver to detect the danger as early as possible. Therefore, this paper focuses on vehicle detection and tracking algorithm based on vehicle monocular vision. The research contents are as follows: classifier model training based on active learning. Visual vehicle detection based on machine learning requires a large number of labeled sample data to train a classifier model that can accurately classify vehicles and backgrounds in images. In this paper, an active learning algorithm based on sample sampling strategy for error classification is proposed to obtain the most informative sample data at a lower cost of manual annotation, and iterative training to optimize the performance of the classifier. Adaboosting Adaptive boost) cascade multi-objective vehicle detection. In order to improve the accuracy of vehicle detection, this paper presents a multi-classifier vehicle detection method. According to the difference of vehicle characteristics in the field of vision, the vehicles to be tested are classified as forward vehicles, left oblique vehicles and right oblique vehicles, and the cascaded classifiers are trained for detection. At the same time, in order to improve the speed of vehicle detection, a multi-resolution accelerated vehicle detection algorithm combined with camera calibration is proposed. Different degrees of image demotion were used to detect different vehicles in the visual field. The feature tracking of the histogram of oriented radientsand the fusion of Adaboost detection were used respectively. In order to solve the problem that the detection results of Adaboost cascaded vehicles are not continuous, a vehicle detection and tracking algorithm based on Adaboost cascade detection and hog feature tracking is proposed. By means of HOG feature tracking, the vehicle detection rate is increased by about 10%, and the detection results are more continuous. Design and implementation of pre-collision warning system. Finally, using the vehicle detection and tracking algorithm studied in this paper, a pre-collision warning system is designed. Through the real traffic scene test, the system can detect and track the vehicle in front of the vehicle in real time, accurately and continuously, and calculate the distance between the vehicle and the vehicle. Real-time monitoring of potential collision hazards ahead, timely warning signals to avoid traffic accidents.
【學(xué)位授予單位】：中國科學(xué)技術(shù)大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：U463.6;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前3條

1 解文華;肖進(jìn)勝;易本順;張亞琪;李明;;一種基于Mean Shift和C-V模型的車輛跟蹤算法[J];湖南大學(xué)學(xué)報(自然科學(xué)版);2012年07期

2 齊美彬;潘燕;張銀霞;;基于車底陰影的前方運(yùn)動車輛檢測[J];電子測量與儀器學(xué)報;2012年01期

3 劉晨光;程丹松;劉家鋒;黃劍華;唐降龍;;一種基于交互式粒子濾波器的視頻中多目標(biāo)跟蹤算法[J];電子學(xué)報;2011年02期

相關(guān)博士學(xué)位論文 前2條

1 顧迎節(jié);面向圖像分類的主動學(xué)習(xí)算法研究[D];南京理工大學(xué);2015年

2 劉培勛;車輛主動安全中關(guān)于車輛檢測與跟蹤算法的若干研究[D];吉林大學(xué);2015年

相關(guān)碩士學(xué)位論文 前2條

1 李甫;基于典型交通事故分析的汽車運(yùn)行風(fēng)險研究[D];吉林大學(xué);2013年

2 許世強(qiáng);當(dāng)前我國重特大交通事故現(xiàn)象的分析及其治理對策研究[D];中國政法大學(xué);2010年

，

本文編號：2032219