交通信息与安全
交通信息與安全
교통신식여안전
JOURNAL OF TRANSPORT INFORMATION AND SAFETY
2014年
3期
128-131,139
,共5页
视频处理%车辆逆行%M ean-shif t跟踪%运动轨迹%单车道
視頻處理%車輛逆行%M ean-shif t跟蹤%運動軌跡%單車道
시빈처리%차량역행%M ean-shif t근종%운동궤적%단차도
video processing%vehicle retrograde%Mean-shift tracking%motion trajectory%single lane
针对城市单车道车辆逆行违章检测问题，研究了基于视频的单车道车辆逆行违章自动检测方法。使用背景差分法进行车辆检测；用 Harris角点特征补充Mean-shift算法的颜色特征，提高车辆跟踪精度，以此得出被跟踪车辆的运动轨迹；通过计算机对运动轨迹进行分析，自动地判断其是否为逆行。从逆行检测正确率和计算量两方面进行了对比实验，实验结果表明，该方法对车辆逆行检测效果良好。车辆平均逆行识别率达到约87.55％，与对比方法基本相当；在计算时间方面，文中方法平均每帧计算时间比对比方法少约1956ms，更具快速性。
針對城市單車道車輛逆行違章檢測問題，研究瞭基于視頻的單車道車輛逆行違章自動檢測方法。使用揹景差分法進行車輛檢測；用 Harris角點特徵補充Mean-shift算法的顏色特徵，提高車輛跟蹤精度，以此得齣被跟蹤車輛的運動軌跡；通過計算機對運動軌跡進行分析，自動地判斷其是否為逆行。從逆行檢測正確率和計算量兩方麵進行瞭對比實驗，實驗結果錶明，該方法對車輛逆行檢測效果良好。車輛平均逆行識彆率達到約87.55％，與對比方法基本相噹；在計算時間方麵，文中方法平均每幀計算時間比對比方法少約1956ms，更具快速性。
침대성시단차도차량역행위장검측문제，연구료기우시빈적단차도차량역행위장자동검측방법。사용배경차분법진행차량검측；용 Harris각점특정보충Mean-shift산법적안색특정，제고차량근종정도，이차득출피근종차량적운동궤적；통과계산궤대운동궤적진행분석，자동지판단기시부위역행。종역행검측정학솔화계산량량방면진행료대비실험，실험결과표명，해방법대차량역행검측효과량호。차량평균역행식별솔체도약87.55％，여대비방법기본상당；재계산시간방면，문중방법평균매정계산시간비대비방법소약1956ms，경구쾌속성。
This paper proposed a vehicle retrograde detection method on urban single lane based on video .First , background subtraction was used for moving vehicle detection .Second ,Harris corner features were combined to comple-ment the color features of Mean-shift to improve tracking accuracy ,from which motion trajectory of a vehicle can be com-puted .Finally ,the computed motion trajectory was analyzed for vehicle retrograde determination .Comparative experi-ments were conducted to evaluate retrograde detection accuracy and computational complexity .Experiment results show that the proposed detection method works well for vehicle retrograde detection .The average recognition rate is about 87 . 55% ,which is similar to that of the comparative method .However ,the proposed method has 19 .56 ms less computation time than the compared method ,therefore ,with fast processing speed .
