Hierarchical abnormal event detection by real time and semi-real time multi-tasking video surveillance system

The problem of sequential detection of anomalies in multimodal data is considered. The objective is to observe physical sensor data from CCTV cameras, and social media data from Twitter and Instagram to detect anomalous behaviors or events. Data from each modality is transformed to discrete time count data by using an artificial neural network to obtain counts of objects in CCTV images and by counting the number of tweets or Instagram posts in a geographical area. The anomaly detection problem is then formulated as a problem of quickest detection of changes in count statistics. The quickest detection problem is then solved using the framework of partially observable Markov decision processes (POMDP), and structural results on the optimal policy are obtained. The resulting optimal policy is then applied to real multimodal data collected from New York City around a 5K race to detect the race. The count data both before and after the change is found to be nonstationary in nature. The proposed mathematical approach to this problem provides a framework for event detection in such nonstationary environments and across multiple data modalities.

show abstract

“…Let the rows of the matrixP in (2), and hence the corresponding elements of P 2 in (1), be identical. Also, let a 1 = a N +1 = 0.5 in P 2 .…”

Section: Theorem 43mentioning

confidence: 99%

Sequential Event Detection Using Multimodal Data in Nonstationary Environments

Banerjee

Whipps

Gurram

et al. 2018

2018 21st International Conference on Information Fusion (FUSION)

View full text Add to dashboard Cite

show abstract

“…Deep Learning consider to be the form of more structured artificial neural network that uses the deep architecture of neurons which are linked together to replicate the human brain [6]. The apprehension behind this is the wherewithal of image segmentation pixel-wise as segmentation at pixellevelnecessitate more fine-grained alignment than bounding boxes which may further outlined to the regions of the original image more precisely and in better way.…”

Section: Deep Learning Techniquesmentioning

confidence: 99%

Scene Illustration of Terrestrial Animals with Its Monitoring, Tracking and Recognizing Through Deep Learning in Relation with Granular Computing

Rawat,

Sodhi,

Tyagi

2019

IJEAT

View full text Add to dashboard Cite

Combining Deep Learning Technique with Granular Computing employs an inductive paradigm for the terrestrial animal’s elucidation. The proposed method frames the object (terrestrial animal) in arbitrary-shaped and sized granules rather than fixed and rectangular shaped, so that object can effectively mine and recognized. The goal is to present a formal model which automatically focus only on representative pixel of each granule rather than converting pixels from entire image through scanning. Thus, this work entails the process of recognizing not only the static animal in the background, but also depicts moving animal in foreground separately.

show abstract

“…Hierarchical abnormal event detection [8] was proposed for detection of abnormal human activities in the outdoor. A trajectory based abnormal event detection method was processed in the real time outdoor videos.…”

Section: Literature Surveymentioning

confidence: 99%

An Enhanced Human Activity Prediction at Rainy and Night Times

D*¹,

Radha²

2019

IJRTE

View full text Add to dashboard Cite

Human activity prediction aims to recognize an unfinished activity with limited motion and appearance information. A generalized activity prediction framework was proposed for human activity prediction where Probabilistic Suffix Tree (PST) was introduced to model casual relationships between constituent actions. Then, each kind of activity in videos was predicted by modeling interactive object information through Spatial Pattern Mining (SPM). This framework mined the temporal sequence patterns. For efficient human activity prediction a Spatio-Temporal Frequent Object Mining (STOM) was proposed in which the spatial, size and motion correlation among objects information were collected along with the temporal information. After the collection of this information, the objects were identified by using Modified Histogram Of Gradient (MHOG) and then the objects were tracked by particle filter technique. The frequent action of detected objects were identified by using Frequent Pattern-growth (FP-growth) which predicted the infrequent action as abnormal human activity in videos. However, MHOG based Object Detection and Tracking-STOM (MHOGODT-STFOM) based human activity prediction is not more effective at night time and rainy time. So in this paper, Enhanced Object Detection and Tracking- STFOM (EODTSTFOM) and Removing Rain Streaks-EODT-STFOM (RSREODT-STFOM) are proposed for human activity prediction even at night time and rainy time. In EODT, a modified Contrast Model is used which combined the contrast information and local entropy information to detect object contents present in the current image frame. Then, the objects are tracked by Kalman filter. In RSR-EODT, the rain streaks in the images are removed based on the deep Convolutional Neural Network (CNN). Then the objects are detected and tracked by modified Contrast Model and Kalman filter respectively. After the object detection and object tracking by EODT and RSR-EODT, the frequent actions are obtained by applying STFOM. The frequent actions are considered as normal activities and the infrequent actions are considered as abnormal activities. Thus the proposed EODTSTFOM and RSR-EODT- STFOM methods predict the human activities even at night time and rainy time.

show abstract

Hierarchical abnormal event detection by real time and semi-real time multi-tasking video surveillance system

Cited by 46 publications

References 12 publications

Sequential Event Detection Using Multimodal Data in Nonstationary Environments

Sequential Event Detection Using Multimodal Data in Nonstationary Environments

Scene Illustration of Terrestrial Animals with Its Monitoring, Tracking and Recognizing Through Deep Learning in Relation with Granular Computing

An Enhanced Human Activity Prediction at Rainy and Night Times

Contact Info

Product

Resources

About