Abstract
This paper presents a framework to automatically replant timestamps for panorama video surveillance. The system mainly comprises six modules: 1) timestamp localization; 2) image registration; 3) timestamp pixel recovery; 4) color correction; 5) timestamp recognition; and 6) panorama video generation. The proposed framework first develops a method to localize the timestamp by employing the method of locating digital video clocks. Then, a fast and novel method is developed to recover the pixels covered by timestamps. The proposed method has fast speed because a fast image translation estimation procedure is introduced based on the PTZ camera motion estimation and global histogram-based image matching. Moreover, a hybrid color correction method by combining region matching with the gamma correction and the linear correction is presented. To plant timestamps accurately, a timestamp recognition procedure is developed by adopting the time recognition method for digit video clocks. Experimental results show that the proposed approach can accurately remove timestamps in real time, the recovered frames are visually consistent with the real scene, and the performance of color correction for panorama video is visually acceptable.
Similar content being viewed by others
References
Bay H, Tuytelaars T, Gool L (2006) SURF: speeded up robust features. Eur Conf Comput Vis 404–417
Beucher S, Lantuejoul C (1979) Use of watersheds in contour detection. International workshop on image processing, real-time edge and motion detection
Bu F, Sun L, Ding X et al (2008) Detect and recognize clock time in sports video. Advances in Multimedia Information Processing-PCM, Springer 306–316
Chugh S, Jain Y (2011) Character localization from natural images using nearest neighbours approach. Int J Sci Eng Res 2(12):1–6
Covavisaruch N, Saengpanit C (2004)Timestamp detection and recognition in video frames. Int Conf Imaging Sci Syst Technol 173–178
Criminisi A, Pérez P, Toyama K (2004) Region filling and object removal by exemplar-based image inpainting. IEEE Trans Image Process 13(9):1200–1212
EpshteinB, OfekE, WexlerY (2010) Detecting text in natural scenes with stroke width transform. IEEE Int Conf Comput Vis Pattern Recognit 2963–2970
Farbman Z, Hoffer G, Lipman Y et al (2009) Coordinates for instant image cloning. ACM Trans Graph (TOG) 28(3):1–9
Fischler M, Bolles R (1981) Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 24(6):381–395
Gevrekci M, Gunturk B (2007) On geometric and photometric registration of images. IEEE Int Conf Acoust Speech Signal Process 1:1261–1264
Ha S, Koo H, Lee S et al (2007) Panorama mosaic optimization for mobile camera systems. IEEE Trans Consum Electron 53(4):1217–1225
Li Y, Wan K, Yan X et al (2006) Video clock time recognition based on temporal periodic pattern. IEEE Int Conf Acoust Speech Sig Process 2:653–656
Li Y, Xu C, Wan K et al (2006) Reliable video clock time recognition. IEEE Int Conf Pattern Recognit 4:128–131
Liu M, Chen S, Liu J et al (2009) Video completion via motion guided spatial-temporal global optimization. ACM Int Conf Multimedia 537–540
Lowe D (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110
Lyu M, Song J, Cai M (2005) A comprehensive method for multilingual video text detection, localization, and extraction. IEEE Trans Circuits Syst Video Technol 15(2):243–255
Mishra A, Alahari K and Jawahar C (2012) Top-down and bottom-up cues for scene text recognition. IEEE Int Conf Comput Vis Pattern Recognit 2687–2694
Neumann L, Matas J (2012) Real-time scene text localization and recognition. IEEE Int Conf Comput Vis Pattern Recognit 3538–3545
Rublee E, Rabaud V, Konolige K et al (2011) ORB: an efficient alternative to SIFT or SURF. IEEE Int Conf on Comput Vis 2564–2571
Shahab A, Shafait F and Dengel A (2011) Robust reading competition challenge 2: reading text in scene images. Int Conf Doc Anal Recognit 1491–1496
Smith R (2007) An overview of the Tesseract OCR engine. Int Conf Doc Anal Recognit 7:629–633
TianG, Gledhill D, Taylor D et al (2002) Colour correction for panoramic imaging. Int Conf Inf Vis 483–488
Tico M, Pulli K (2010) Robust image registration for multi-frame mobile applications. Asilomar Conf Signals Syst Comput 860–864
Wang K, Babenko B, Belongie S (2011) End-to-end scene text recognition. IEEE Int Conf Comput Vis 1457–1464
Wang T, Wu D, Coates A et al (2012) End-to-end text recognition with convolutional neural networks, IEEE Int Conf Pattern Recognit 3304–3308
Weinman J, Learned-Miller E, Hanson A (2009) Scene text recognition using similarity and a lexicon with sparse belief propagation. IEEE Trans Pattern Anal Mach Intell 31(10):1733–1746
Wexler Y, Shechtman E, Irani M (2007) Space-time completion of video. IEEE Trans Pattern Anal Mach Intell 29(3):463–476
Wu S, Li Z, Zheng J et al (2014) Exposure-robust alignment of differently exposed images. IEEE Signal Process Lett 21(7):885–889
Xiong Y, Pulli K (2009) Color correction for mobile panorama imaging. Int Conf Internet Multimedia Comput Serv 219–226
Xiong Y, Pulli K (2010) Color matching for high-quality panoramic images on mobile phones. IEEE Trans Consum Electron 56(4):2592–2600
Xu W, Mulligan J (2010) Performance evaluation of color correction approaches for automatic multi-view image and video stitching. IEEE Int Conf Comput Vis Pattern Recognit 263–270
Yin P, Hua X, Zhang H (2002) Automatic time stamp extraction system for home videos. IEEE Int Sympo Circuits Algorithm 2:73–76
Yu X (2012) Localization and extraction of the four clock-digits using the knowledge of the digital video clock. IEEE Int Conf Pattern Recognit 1217–1220
Yu X, Ding W, Zeng Z et al (2015) Reading digital video clocks. Int J Pattern Recognit Artif Intell 29(4)
Yu X, Li Y, Lee W (2008) Robust time recognition of video clock based on digit transit detection and digit-sequence recognition. IEEE Int Conf Pattern Recognit 1–4
Zhang M, Xie J, Li Y et al (2001) Color histogram correction for panoramic images. Int Conf Virtual Syst Multimedia 328–331
Zitova B, Flusser J (2003) Image registration methods: a survey. Image Vis Comput 21:977–1000
Acknowledgments
This work is partially supported by National Natural Science Foundation of China (No.61272206).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Yu, X., Cheng, J., Wu, S. et al. A framework of timestamp replantation for panorama video surveillance. Multimed Tools Appl 75, 10357–10381 (2016). https://doi.org/10.1007/s11042-015-3051-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-015-3051-1