Missing Frame Detection of Surveillance Videos Based on Deep Learning in Forensic Science

The identification of road traffic accidents plays an essential role in the litigation process of complicated traffic cases. Speed appraisement is the main part among all kinds of judicial identification in the area of road traffic accident. When evaluating the speed of vehicles, video frame time is an important parameter. The situation of missing frames may cause an imprecision of speed inspection. In this paper, we propose a method to detect missing frames by the movement of objects in video based on deep learning techniques. The method is based on object detection neural network. A derived distance of target object is calculated and applied to detect missing frames. We then confirm the performance of proposed method on dataset consisted of collected surveillance videos. It can find missing frames accurately and rapidly, which effectively reduces calculation errors of vehicle speed and promotes the authenticity of forensic investigation.

[1]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[2]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Mark Goadrich,et al.  The relationship between Precision-Recall and ROC curves , 2006, ICML.

[4]  Yi Li,et al.  R-FCN: Object Detection via Region-based Fully Convolutional Networks , 2016, NIPS.

[5]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[6]  Anastasis A. Sofokleous,et al.  Review: H.264 and MPEG-4 Video Compression: Video Coding for Next-generation Multimedia , 2005, Comput. J..

[7]  Iain E. G. Richardson,et al.  H.264 and MPEG-4 Video Compression: Video Coding for Next-Generation Multimedia , 2003 .

[8]  Adrien Chan-Hon-Tong,et al.  Pertinence of Video for Single Image Deep Network , 2017 .

[9]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Trevor York,et al.  Book Review: Principles of CMOS VLSI Design: A Systems Perspective , 1986 .

[11]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[12]  Tara . Saikumar,et al.  Improved Fuzzy C-Means Clustering Algorithm Using Watershed Transform on Level Set Method for Image Segmentation , 2012 .

[13]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Chen Jian-guo.  Speed Determination Using Video Recording , 2009 .

[15]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[16]  David M. W. Powers,et al.  Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation , 2011, ArXiv.

[17]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.