【摘要】：客流計(jì)數(shù)是車(chē)載智能視頻監(jiān)控系統(tǒng)運(yùn)作的基礎(chǔ),通過(guò)客流計(jì)數(shù),可以實(shí)時(shí)地獲取各路公交車(chē)在各個(gè)時(shí)段的上下車(chē)人數(shù),方便維護(hù)公交車(chē)秩序和安全。然而,由于公交車(chē)上的復(fù)雜環(huán)境,車(chē)體的抖動(dòng),圖像的失真,乘客間的相互遮擋等問(wèn)題,使得目前還沒(méi)有一套實(shí)時(shí)的、精確的客流計(jì)數(shù)方案。針對(duì)以上問(wèn)題,本文提出一種基于圖像處理和乘客檢測(cè)及跟蹤技術(shù)的客流計(jì)數(shù)方法。首先對(duì)視頻進(jìn)行穩(wěn)像,減小公交車(chē)抖動(dòng)引起的圖像序列間的偏移,然后對(duì)圖像進(jìn)行梯形校正,減小攝像頭角度引起的圖像梯形失真,最后對(duì)乘客進(jìn)行檢測(cè)和跟蹤,解決公交車(chē)上乘客相互遮擋和光照變化明顯的問(wèn)題,并根據(jù)乘客的運(yùn)動(dòng)方向判斷乘客上下車(chē)情況,實(shí)現(xiàn)客流計(jì)數(shù)。首先,在當(dāng)前抖動(dòng)圖像的左上角和右上角選取兩個(gè)子塊,進(jìn)行局部運(yùn)動(dòng)估計(jì),并用局部運(yùn)動(dòng)矢量的平均值作為運(yùn)動(dòng)補(bǔ)償矢量,減小視頻抖動(dòng)。其次,根據(jù)攝像頭傾斜角度,計(jì)算得到透射變換矩陣,對(duì)失真圖像進(jìn)行視角變換,并通過(guò)雙線性插值算法對(duì)圖像進(jìn)行梯形校正。然后,對(duì)待檢測(cè)圖像進(jìn)行自適應(yīng)閾值背景差分,實(shí)現(xiàn)乘客目標(biāo)分割,去除背景中類(lèi)似人體輪廓物體的干擾;提取乘客頭肩部梯度方向直方圖(Histogram of Oriented Gradient,HOG)特征,訓(xùn)練支持向量機(jī)(Support Vector Machine,SVM)頭肩分類(lèi)器,實(shí)現(xiàn)乘客目標(biāo)檢測(cè);對(duì)乘客進(jìn)行基于快速魯棒性特征(Speeded-Up Robust Feature,SURF)的目標(biāo)跟蹤。最后,對(duì)視頻圖像設(shè)置計(jì)數(shù)線,判斷乘客是否跨越計(jì)數(shù)線,并根據(jù)乘客運(yùn)動(dòng)的方向,統(tǒng)計(jì)出各個(gè)站點(diǎn)的上下車(chē)人數(shù)和車(chē)廂乘客總?cè)藬?shù)。
[Abstract]:The passenger flow count is the basis of the intelligent video surveillance system. Through the passenger flow count, the number of buses can be obtained in real time, and it is convenient to maintain the order and safety of the bus. However, due to the complex environment on the bus, the jitter of the body, the distortion of the image and the mutual occlusion among the passengers, there is still no real-time and accurate passenger flow counting scheme. In view of the above problems, this paper presents a passenger flow counting method based on image processing and passenger detection and tracking techniques. Firstly, the video is stabilized to reduce the deviation between image sequences caused by bus jitter, and then trapezoidal correction is carried out to reduce the trapezoidal distortion caused by camera angle. Finally, passengers are detected and tracked. The problem of mutual occlusion and obvious change of illumination on bus is solved, and passenger flow count is realized by judging the situation of passengers getting on and off according to the movement direction of passengers. Firstly, two sub-blocks are selected in the upper left corner and the upper right corner of the current jitter image to estimate the local motion, and the average value of the local motion vector is used as the motion compensation vector to reduce the video jitter. Secondly, according to the tilt angle of the camera, the transmission transformation matrix is obtained, and the distorted image is transformed into the angle of view, and the trapezoidal correction of the image is carried out by bilinear interpolation algorithm. Then, the detection image is treated with adaptive threshold background difference to achieve passenger target segmentation, remove the interference similar to human contour objects in the background, and extract the (Histogram of Oriented Gradient,HOG features of passenger head and shoulder gradient direction histogram. Support vector machine (Support Vector Machine,SVM) head-shoulder classifier is trained to realize passenger target detection and passenger target tracking based on fast robust feature (Speeded-Up Robust Feature,SURF) is carried out. Finally, the counting line is set to determine whether the passengers cross the counting line, and according to the direction of passenger movement, the number of passengers in and out of each station and the total number of passengers are calculated.
【學(xué)位授予單位】：天津大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類(lèi)號(hào)】：U463.67;TN948.6

【參考文獻(xiàn)】

相關(guān)期刊論文 前5條

1 張春鳳;宋加濤;王萬(wàn)良;;行人檢測(cè)技術(shù)研究綜述[J];電視技術(shù);2014年03期

2 謝璐;金志剛;王穎;;基于視頻穩(wěn)像和視角變換的公交客流計(jì)數(shù)方法[J];計(jì)算機(jī)應(yīng)用;2013年10期

3 李鴻生;薛月菊;黃曉琳;黃珂;何金輝;;改進(jìn)的自適應(yīng)混合高斯前景檢測(cè)方法[J];計(jì)算機(jī)應(yīng)用;2013年09期

4 趙璐璐;耿國(guó)華;李康;何阿靜;;基于SURF和快速近似最近鄰搜索的圖像匹配算法[J];計(jì)算機(jī)應(yīng)用研究;2013年03期

5 張洪艷;沈煥鋒;張良培;李平湘;;一種保邊緣影像超分辨率重建方法[J];中國(guó)圖象圖形學(xué)報(bào);2009年11期

，

本文編號(hào)：2246729