[1] He Tiejun, Zhang Ning, Gao Zhaohui, Huang Wei, et al. Vehicle detection method for expressway by MPEG compressed domain [J]. Journal of Southeast University (English Edition), 2008, 24 (4): 522-527. [doi:10.3969/j.issn.1003-7985.2008.04.025]
Copy
Vehicle detection method for expressway by MPEG compressed domain(
)
基于MPEG压缩域的高速公路车辆检测方法
)Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]
- Volumn:
- 24
- Issue:
- 2008 4
- Page:
- 522-527
- Research Field:
- Computer Science and Engineering
- Publishing date:
- 2008-12-30
Info
- Title:
- Vehicle detection method for expressway by MPEG compressed domain
- 基于MPEG压缩域的高速公路车辆检测方法
- Author(s):
- He Tiejun; Zhang Ning; Gao Zhaohui; Huang Wei
- ITS Research Center, Southeast University, Nanjing 210096, China
- Keywords:
- vehicle detection; compressed domain; discrete cosine transform(DCT)coefficient; motion vector
- PACS:
- TP391.41
- DOI:
- 10.3969/j.issn.1003-7985.2008.04.025
- Abstract:
- A method which extracts traffic information from an MPEG-2 compressed video is proposed.According to the features of vehicle motion, the motion vector of a macro-block is used to detect moving vehicles in daytime, and a filter algorithm for removing noises of motion vectors is given.As the brightness of the headlights is higher than that of the background in night images, discrete cosine transform(DCT)coefficient of image block is used to detect headlights of vehicles at night, and an algorithm for calculating the DCT coefficients of P-frames is introduced.In order to prevent moving objects outside the expressway and video shot changes from disturbing the detection, a driveway location method and a video-shot-change detection algorithm are suggested.The detection rate is 97.4% in daytime and 95.4% in nighttime by this method.The results prove that this vehicle detection method is effective.
- 提出了一种从MPEG-2压缩数据流中提取高速公路车流量的方法.白天根据车辆运动的特点, 利用宏块的运动矢量检测车辆, 并给出了运动矢量噪声的滤除算法.夜间根据车灯的亮度高于背景区域的特点, 利用图像块的DCT系数检测车辆的车灯, 并介绍了P帧图像块的DCT系数的计算方法.为了防止道路外物体的移动以及镜头的移动对检测造成的影响, 给出了车道定位的方法以及镜头移动检测的算法.采用此方法, 白天的检测准确率可达97.4%, 夜间的检测准确率可达95.4%.实验表明本检测方法是有效的.
References:
[1] Chuai Jinhua, Li Xulong, Xu Hongke.Traffic flow detection method based on video images processing [J].Journal of Chang’an University:Natural Science Edition, 2005, 25(5):86-89.(in Chinese)
[2] Ju Yongfeng, Zhu Hui, Pan Yong.Vehicle flow detection algorithm based on computer vision [J].Journal of Chang’an University:Natural Science Edition, 2004, 24(1):92-95.(in Chinese)
[3] Liu Guangyao, Ye Xiuqing, Gu Weikang.3D reconstruct based traffic flux detection algorithm[J].Journal of Image and Graphics, 2003, 8(6):631-636.(in Chinese)
[4] Yu Mei, Jiang Gangyi, He Sailong.Land mark based method for vehicle detection and counting from video[J].Chinese Journal of Scientific Instrument, 2002, 23(4):386-390.(in Chinese)
[5] He Tiejun, Huang Wei, Chen Lide.Development and application of digital video transmission system based on MPEG-2[J].Journal of Highway and Transportation Research and Development, 2004, 21(11):86-88.(in Chinese)
[6] ISO/IEC 13818 Information technology-generic coding of moving pictures and associated audio information[S].1995.
[7] Jin Hong, Zhou Yuanhua.Review of video parsing techniques for contented based video retrieval [J].Journal of Image and Graphics, 2000, 4(3):276-281.(in Chinese)
[8] Yeo B L, Liu B.Rapid scene analysis on compressed video [J].IEEE Transactions on Circuits and Systems for Video Technology, 1995, 5(6):533-544.
[9] Lee Seong-Whan, Kim Young-Min, Choi Sung Woo.Fast scene change detection using direct feature extraction from MPEG compressed videos [J].IEEE Transactions on Multimedia, 2000, 2(4):240-254.
[10] Pei Soochang, Chou Yuzuong.Efficient MPEG compressed video analysis using macroblock type information [J].IEEE Transactions on Multimedia, 1999, 1(4):321-333.
[11] Wang Zhanhui, Liu Guizhong, Liu Long, et al.A fast and accurate moving object extraction method from compressed video stream [J].Journal of Electronics and Information Technology, 2004, 26(7):1157-1161.(in Chinese)
[12] Zhan Yiqiang, Qi Feihu, Liu Tianming.Fast object tracking algorithm based on MPEG-2 video sequence [J].Journal of Shanghai Jiaotong University:Natural Science Edition, 2001, 35(9):1321-1324.(in Chinese)
[13] Huang Ruoyun, Mo Yulong.Moving objects detection from MPEG-1 video stream [J].Journal of Shanghai University:Natural Science Edition, 2003, 9(2):100-104.(in Chinese)
[14] Chen Li, Fang Xiangzhong, Yu Songyu.Changing frame type in the compressed domain[J].Journal of Shanghai Jiaotong University:Natural Science Edition, 2003, 37(8):1293-1296.(in Chinese)
[15] Xiao Wangxin, Zhang Xue, Huang Wei.Adaptive thresholds edge detection of traffic image [J].Journal of Traffic and Transportation Engineering, 2003, 3(4):104-107.(in Chinese)
[16] Zhou Xin, Huang Xiyue.Detection and reconstruction for multi-lane line on freeway[J].China Journal of Highway and Transport, 2005, 18(2):107-111.(in Chinese)
Memo
- Memo:
-
Biography: He Tiejun(1974—), male, doctor, lecturer, hetiejun56826@yahoo.com.cn.
Foundation items: The Cultivation Fund of the Key Scientific and Technical Innovation Project of Higher Education of Ministry of Education(No.705020), the Natural Science Foundation of Jiangsu Province(No.BK2004077).
Citation: He Tiejun, Zhang Ning, Gao Zhaohui, et al.Vehicle detection method for expressway by MPEG compressed domain[J].Journal of Southeast University(English Edition), 2008, 24(4):522-527.