行人檢測論文道路行人特征視覺檢測方法研究

1、行人檢測論文：道路行人特征視覺檢測方法研究【中文摘要】隨著人類社會(huì)的快速發(fā)展,車輛日益增多,道路交通事故頻頻發(fā)生,給人類社會(huì)造成了巨大的損失。因此,如何減少交通事故的發(fā)生和降低損失成為了全世界關(guān)注的熱點(diǎn)。智能輔助駕駛技術(shù)是減少交通事故的發(fā)生和降低交通事故損失的有效方法之一。行人檢測是其中的關(guān)鍵技術(shù),它是利用傳感器技術(shù)、圖像處理技術(shù)、計(jì)算機(jī)技術(shù)等多種技術(shù)融合檢測目標(biāo)區(qū)域中是否存在行人。論文對智能輔助駕駛系統(tǒng)中基于機(jī)器視覺技術(shù)進(jìn)行研究。首先分析了運(yùn)動(dòng)模糊圖像的退化模型,研究了物體運(yùn)動(dòng)模糊圖像成像原理,得到用于行人檢測的運(yùn)動(dòng)模糊圖像成像方法,確定了造成運(yùn)動(dòng)圖像模糊的主要因素,然后對運(yùn)動(dòng)模糊圖像進(jìn)行處

2、理,重點(diǎn)研究維納濾波方法,得到較好的圖像恢復(fù)效果。其次,研究了行人的輪廓特征,采用多種方法對行人圖像進(jìn)行邊緣檢測,得出基于Canny算子的邊緣檢測方法具有較好圖像邊緣檢測效果,用此邊緣檢測方法結(jié)合灰度形態(tài)學(xué)進(jìn)一步進(jìn)行圖像處理,試驗(yàn)結(jié)果顯示該方法能很好地消除行人輪廓的干擾因素。最后,詳細(xì)分析了支持向量機(jī)算法,并構(gòu)造了支持向量機(jī)分類器,分別選擇紋理特征和不變矩特征作為行人的特征點(diǎn),從樣本圖像中提取試驗(yàn)數(shù)據(jù),選取部分樣本對支持向量機(jī)分類器進(jìn)行訓(xùn)練,然后用訓(xùn)練后的分類器對測試樣本進(jìn)行識(shí)別試驗(yàn)。試驗(yàn)結(jié)果表明,這兩種特征點(diǎn)都能夠?qū)π腥诉M(jìn)行有效地識(shí)別。論文的圖像試驗(yàn)樣本采用攝像機(jī)的形式模擬車載視覺傳感器獲取

3、,對采集到的圖像進(jìn)行預(yù)處理,建立行人和非行人圖像數(shù)據(jù)庫?！居⑽恼縒ith the rapid development of human society and the increasing vehicles, the road traffic accidents which occurred frequently cause great damages. How to reduce the traffic accidents and the corresponding loss has become a hot topic. The intelligent assisted driving

4、 is one effective way to solve the problem. Pedestrian detection is the key technique for intelligent assisted driving. It detects the target area for the presence of pedestrian by the method. It is combining the technology of sensors, image processing, computer, and so on.This paper is study on mac

5、hine vision of pedestrians detection technology. Firstly, the degradation model of motion-blurred image was analysed. The method of imaging the motion-blurred image for pedestrian detection and the main factors about image blurring were derived. The wiener filter has better image processing effect b

6、y the experiments. Secondly, the pedestrian profile was researched. The method of edge detection based on Canny has a good image edge detection effect by the experiments. Then combining with grayscale morphological for image processing. The results show that the method can be used to eliminate the i

7、nterference factors of pedestrian profile. Finally, support vector machine was analysed, and support vector machine classifier was structured. Extracting test data from sample image by the texture feature and invariant moments feature. The test sample was recognized by the SVM classifier that was tr

8、ained by the part of sample image. The experimental results show that these two kinds of features of pedestrians could achieve effectively recognition of the pedestrians.In the experiments, the images were obtained by using hand-held video camera to replace the vehicle-mounted CCD. The image database of pedestrians and non-pedestrians was established by the collected images that were processed simply.【