室内单目监控视频动态前景提取方法研究
Research on Dynamic Foreground Extraction Method for Indoor Monocular Surveillance Video
摘要: 针对室内单目监控视频光照不均等原因产生的阴影干扰和设备、环境因素产生的抖动问题，本文提出了一种特征定位与改进帧差法融合的动态前景目标提取方法。首先，基于像素级消减动态阴影特征并干扰使用高斯滤波进行降噪处理以减少监控视频冗余特征信息。其次，使用特征匹配算法获取连续两帧图像的差分，初步捕获动态前景目标。然后，使用自适应阈值和形态学处理方法改进帧差法精确提取前景动态目标。最后，实验验证方法的有效性和精准性，本文室内单目监控视频动态前景目标提取算法准确度达到92.2%，有效消除室内单目监控视频中的阴影和抖动干扰现象。
Abstract: Aiming at the shadow interference caused by uneven illumination of indoor monocular surveillance video and the jitter problem caused by equipment and environmental factors, this paper proposes a dynamic foreground target extraction method based on feature location and improved frame dif-ference method. Firstly, dynamic shadow features are reduced at the pixel level and Gaussian fil-tering is used for noise reduction to reduce redundant feature information of surveillance video. Secondly, the feature matching algorithm is used to obtain the difference between two consecutive frames of images to initially capture the foreground dynamic target. Then, the adaptive threshold and morphological processing method are used to improve the frame difference method to accu-rately extract the foreground dynamic target. Finally, the effectiveness and accuracy of the method are verified by experiments. The accuracy of the dynamic foreground object extraction algorithm in indoor monocular surveillance video reaches 92.2%, which effectively eliminates the shadow and jitter interference in indoor monocular surveillance video.
文章引用：刘冰清. 室内单目监控视频动态前景提取方法研究[J]. 建模与仿真, 2023, 12(3): 2390-2399. https://doi.org/10.12677/MOS.2023.123219

参考文献

[1] Ghatak, S., Rup, S., Didwania, H., et al. (2021) GAN Based Efficient Foreground Extraction and HGWOSA Based Optimiza-tion for Video Synopsis Generation. Digital Signal Processing, 111, Article ID: 102988. [Google Scholar] [CrossRef] 
[2] 陈树, 丁保阔. 动态背景下自适应LOBSTER算法的前景检测[J]. 中国图象图形学报, 2017, 22(2): 161-169.
[3] Zhao, X.D., Hou, F.X., Su, J.F., et al. (2022) An Alphapose-Based Pedestrian Fall Detection Algorithm. 8th International Conference, ICAIS 2022, Qinghai, 15-20 July 2022, 650-660. [Google Scholar] [CrossRef] 
[4] Chang, C.W., Chang, C.Y. and Liu, Y.Y. (2022) A Hybrid CNN and LSTM-Based Deep Learning Model for Abnormal Behavior Detection. Multimedia Tools and Applications, 81, 11825-11843. [Google Scholar] [CrossRef] 
[5] Hsu, W.W., Guo, J.M., Chen, C.Y., et al. (2022) Fall Detection with the Spatial-Temporal Correlation Encoded by a Sequence-to-Sequence Denoised GAN. Sensors, 22, Article No. 4194. [Google Scholar] [CrossRef] [PubMed]
[6] Sheng, M.X., Hou, W.W. and Jiang, J.C. (2020) Implementation of Accelerating Video Preprocessing Based on ZYNQ Platform Resource Management. Journal of Physics Conference Series, 1544, Article ID: 012112. [Google Scholar] [CrossRef] 
[7] Han, P., Huang, T.Q., Weng, B., et al. (2021) Overcome the Brightness and Jitter Noises in Video Inter-Frame Tampering Detection. Sensors, 21, Article No. 3953. [Google Scholar] [CrossRef] [PubMed]
[8] Arnal, J. and Sucar, L. (2020) Hybrid Filter Based on Fuzzy Techniques for Mixed Noise Reduction in Color Images. Applied Sciences, 10, Article No. 243. [Google Scholar] [CrossRef] 
[9] Pei, S.W., Wang, X.R., Qin, W., et al. (2021) STARS: Spatial Temporal Graph Convolution Network for Action Recognition System on FPGAs. 2021 IEEE 45th Annual Computers, Software, and Applica-tions Conference (COMPSAC), Madrid, 12-16 July 2021, 1469-1474. [Google Scholar] [CrossRef] 
[10] Zheng, L., Yang, Y. and Tian, Q. (2018) SIFT Meets CNN: A Decade Survey of Instance Retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40, 1224-1244. [Google Scholar] [CrossRef] 
[11] 陈权, 黄俊, 徐访. 改进视觉背景提取算法在室内的研究[J]. 小型微型计算机系统, 2021, 42(6): 1250-1255.
[12] Xing, J.W., Yang, P. and Qingge, L.T. (2020) Automatic Thresholding Using a Modified Valley Emphasis. IET Image Processing, 14, 536-544. [Google Scholar] [CrossRef] 
[13] Kwolek, B. and Kepski, M. (2014) Human Fall Detection on Embedded Platform Using Depth Maps and Wireless Accelerometer. Computer Methods and Programs in Biomedicine, 117, 489-501. [Google Scholar] [CrossRef] [PubMed]
[14] Wang, Y., Jodoin, P., Porikli, F., et al. (2014) CDnet 2014: An Expand-ed Change Detection Benchmark Dataset. IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2014), Columbus, 23-28 June 2014, 393-400. [Google Scholar] [CrossRef] 
[15] Yang, H.H. and Qu, S.R. (2018) Real-Time Vehicle Detection and Counting in Complex Traffic Scenes Using Background Subtraction Model with Low-Rank Decomposition. IET Intelligent Transport Systems, 12, 75-85. [Google Scholar] [CrossRef] 
[16] Liu, J., Gu, Q.Y., Cheng, D.P., et al. (2022) VSLAM Method Based on Object Detection in Dynamic Environments. Frontiers in Neurorobotics, 16, Article ID: 990453. [Google Scholar] [CrossRef] [PubMed]

为你推荐