基于貝葉斯融合的時空流異常行為檢測模型

陳瑩; 何丹丹

doi:10.11999/JEIT180429

基于貝葉斯融合的時空流異常行為檢測模型

doi: 10.11999/JEIT180429

陳瑩^,,
何丹丹

江南大學(xué)輕工過程先進控制教育重點實驗室 ??無錫 ??214122

基金項目: 國家自然科學(xué)基金(61573168)

詳細信息

作者簡介:
陳瑩：女，1976年生，教授，博士生導(dǎo)師，主要研究方向為信息融合、模式識別等

何丹丹：女，1993年生，碩士生，研究方向為異常行為檢測

通訊作者:
陳瑩　chenying@jiangnan.edu.cn

中圖分類號: TP391
計量
- 文章訪問數(shù): 4031
- HTML全文瀏覽量: 942
- PDF下載量: 105
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2018-05-07
- 修回日期: 2019-01-29
- 網(wǎng)絡(luò)出版日期: 2019-02-20
- 刊出日期: 2019-05-01

Spatial-temporal Stream Anomaly Detection Based on Bayesian Fusion

Ying CHEN^,,
Dandan HE

Key Laboratory of Advanced Control Education in Light Industry Process, Jiangnan University, Wuxi 214122, China

Funds: The National Natural Science Foundation of China (61573168)

摘要

摘要:
針對直接利用卷積自編碼網(wǎng)絡(luò)未考慮視頻時間信息的問題，該文提出基于貝葉斯融合的時空流異常行為檢測模型?？臻g流模型采用卷積自編碼網(wǎng)絡(luò)對視頻單幀進行重構(gòu)，時間流模型采用卷積長短期記憶(LSTM)編碼-解碼網(wǎng)絡(luò)對短期光流序列進行重構(gòu)。接著，分別計算空間流模型和時間流模型下每幀的重構(gòu)誤差，設(shè)計自適應(yīng)閾值對重構(gòu)誤差圖進行二值化，并基于貝葉斯準則對空間流和時間流下的重構(gòu)誤差進行融合，得到融合重構(gòu)誤差圖，并在此基礎(chǔ)上進行異常行為判斷。實驗結(jié)果表明，該算法在UCSD和Avenue視頻庫上的檢測效果優(yōu)于現(xiàn)有異常檢測算法。
- 異常行為檢測 /
- 貝葉斯融合 /
- 時空流
Abstract:
Focusing on the problem that convolutional auto-encoder network based anomaly detection ignores time information, a novel anomaly detection model based on Bayesian fusion of spatial-temporal stream is proposed. A convolution auto-encoder network is used in spatial stream model to reconstructs video frames, and a convolutional Long Short-Term Memory (LSTM) encoder-decoder network is used to reconstruct short-term optical sequence in the temporal stream model. Then, the reconstruction errors under spatial and temporal stream are calculated separately. Meanwhile, an adaptive thresholds is designed to obtain the reconstruction binary error maps. Finally, the Bayesian fusion strategy is developed to combine the reconstruction error of spatial and temporal stream to obtain the final fusion reconstruction error map based on which the abnormal behavior can be determined. Experimental results show that the proposed algorithm is superior to the existing anomaly detection algorithms in UCSD and Avenue datasets.
- Anomaly detection /
- Bayesian fusion /
- Spatial-temporal stream

HTML全文

圖 1 基于貝葉斯融合的時空流異常行為檢測整體框架

下載: 全尺寸圖片幻燈片

圖 2 空間流卷積網(wǎng)絡(luò)模型各層參數(shù)尺寸

下載: 全尺寸圖片幻燈片

圖 3 Conv-LSTM編碼-解碼過程

下載: 全尺寸圖片幻燈片

圖 4 基于貝葉斯的時空流融合圖

下載: 全尺寸圖片幻燈片

圖 5 重構(gòu)圖顯示

下載: 全尺寸圖片幻燈片

圖 6 可視化規(guī)則分數(shù)圖

下載: 全尺寸圖片幻燈片

圖 7 UCSD Ped1和Ped2數(shù)據(jù)庫基于規(guī)則分數(shù)的ROC曲線

下載: 全尺寸圖片幻燈片

表 1 基于規(guī)則分數(shù)的幀級別下的EER和AUC比較(%)

方法	UCSD Ped1		UCSD Ped2
方法	EER	AUC	EER	AUC
MPPCA+SF^[16]	32.0	74.2	36.0	61.3
HOFME^[19]	33.1	72.7	20.0	87.5
Conv-AE^[9]	27.9	76.8	21.7	90.0
ConvLSTM-AE^[20]	N/A	75.5	N/A	88.1
Unmasking^[21]	N/A	68.4	N/A	82.2
Stack RNN^[22]	N/A	N/A	N/A	92.2
BFSTS(間隔/連續(xù)采樣)	28/27.9	76.5/77.8	16.0/13.0	92.7/94.7

下載: 導(dǎo)出CSV

參考文獻(22)

LU Cewu, SHI Jianping, and JIA Jiaya. Abnormal event detection at 150 FPS in MATLAB[C]. Proceedings of 2013 IEEE International Conference on Computer Vision, Sydney, Australia, 2013: 2720–2727.

WEN Hui, GE Shiming, CHEN Shuixian, et al. Abnormal event detection via adaptive cascade dictionary learning[C]. Proceedings of 2015 IEEE International Conference on Image Processing, Quebec, Canada, 2015: 847–851.

GUO Huiwen, WU Xinyu, CAI Shibo, et al. Quaternion discrete cosine transformation signature analysis in crowd scenes for abnormal event detection[J]. Neurocomputing, 2016, 204: 106–115. doi: 10.1016/j.neucom.2015.07.153

SABOKROU M, FATHY M, HOSEINI M, et al. Real-time anomaly detection and localization in crowded scenes[C]. Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Boston, USA, 2015: 56–62.

SABOKROU M, FAYYAZ M, FATHY M, et al. Deep-anomaly: Fully convolutional neural network for fast anomaly detection in crowded scenes[J]. Computer Vision and Image Understanding, 2018, 172: 88–97. doi: 10.1016/j.cviu.2018.02.006

XU Dan, YAN Yan, RICCI E, et al. Detecting anomalous events in videos by learning deep representations of appearance and motion[J]. Computer Vision and Image Understanding, 2016, 156: 117–127. doi: 10.1016/j.cviu.2016.10.010

DIMOKRANITOU A. Adversarial autoencoders for anomalous event detection in images[D]. [Ph.D. dissertation], Purdue University, 2017.

袁靜, 章毓晉. 融合梯度差信息的稀疏去噪自編碼網(wǎng)絡(luò)在異常行為檢測中的應(yīng)用[J]. 自動化學(xué)報, 2017, 43(4): 604–610. doi: 10.16383/j.aas.2017.c150667

YUAN Jing and ZHANG Yujin. Application of sparse denoising auto encoder network with gradient difference information for abnormal action detection[J]. Acta Automatica Sinica, 2017, 43(4): 604–610. doi: 10.16383/j.aas.2017.c150667

HASAN M, CHOI J, NEUMANN J, et al. Learning temporal regularity in video sequences[C]. Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016: 733–742. doi: 10.1109/CVPR.2016.86.

CHONG Y S and YONG H T. Abnormal event detection in videos using spatiotemporal autoencoder[C]. Proceedings of the 14th International Symposium on Neural Networks, Hokkaido, Japan, 2017: 189–196.

FEICHTENHOFER C, PINZ A, and ZISSERMAN A. Convolutional two-stream network fusion for video action recognition[C]. Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016: 1933–1941. doi: 10.1109/CVPR.2016.213.

SHI Xingjian, CHEN Zhourong, WANG Hao, et al. Convolutional LSTM network: A machine learning approach for precipitation nowcasting[C]. Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, Canada, 2015: 802–810.

LIU Ce, FREEMAN W T, ADELSON E H, et al. Human-assisted motion annotation[C]. Proceedings of 2008 IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, USA, 2008: 1–8.

XIE Yulin, LU Huchuan, and YANG M H. Bayesian saliency via low and mid level cues[J]. IEEE Transactions on Image Processin, 2013, 22(5): 1689–1698. doi: 10.1109/TIP.2012.2216276

LI Xiaohui, LU Huchuan, ZHANG Lihe, et al. Saliency detection via dense and sparse reconstruction[C]. Proceedings of 2013 IEEE International Conference on Computer Vision, Sydney, Australia, 2013: 2976–2983.

MAHADEVAN V, LI Weixin, BHALODIA V, et al. Anomaly detection in crowded scenes[C]. Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, USA, 2010: 1975–1981.

DUCHI J, HAZAN E, and SINGER Y. Adaptive subgradient methods for online learning and stochastic optimization[J]. The Journal of Machine Learning Research, 2011, 12: 2121–2159.

GLOROT X and BENGIO Y. Understanding the difficulty of training deep feedforward neural networks[C]. Proceedings of the 13th International Conference on Arti?cial Intelligence and Statistics, Sardinia, Italy, 2010: 249–256.

WANG Tian and SNOUSSI H. Histograms of optical flow orientation for abnormal events detection[C]. Proceedings of 2013 IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, Clearwater, USA, 2013: 45–52.

LUO Weixin, LIU Wen, and GAO Shenghua. Remembering history with convolutional LSTM for anomaly detection[C]. Proceedings of 2017 IEEE International Conference on Multimedia and Expo, Hong Kong, China, 2017: 439–444.

IONESCU R T, SMEUREANU S, ALEXE B, et al. Unmasking the abnormal events in video[C]. Proceedings of 2017 IEEE International Conference on Computer Vision, Venice, Italy, 2017: 2895–2903.

LUO Weixin, LIU Wen, and GAO Shenghua. A revisit of sparse coding based anomaly detection in stacked RNN framework[C]. Proceedings of 2017 IEEE International Conference on Computer Vision, Venice, Italy, 2017: 341–349.

相關(guān)文章

施引文獻

資源附件(0)

訪問統(tǒng)計