scholarly journals Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Video

2021 ◽  
Author(s):  
Jie Wu ◽  
Wei Zhang ◽  
Guanbin Li ◽  
Wenhao Wu ◽  
Xiao Tan ◽  
...  
Keyword(s):  
Anomaly Detection ◽  
Contextual Information ◽  
Surveillance Video ◽  
Key Factors ◽  
Spatio Temporal ◽  
Weakly Supervised ◽  
Set Up ◽  
Bounding Boxes ◽  
Entity Relationships ◽  
Abnormal Behaviors

In this paper, we introduce a novel task, referred to as Weakly-Supervised Spatio-Temporal Anomaly Detection (WSSTAD) in surveillance video. Specifically, given an untrimmed video, WSSTAD aims to localize a spatio-temporal tube (i.e., a sequence of bounding boxes at consecutive times) that encloses the abnormal event, with only coarse video-level annotations as supervision during training. To address this challenging task, we propose a dual-branch network which takes as input the proposals with multi-granularities in both spatial-temporal domains. Each branch employs a relationship reasoning module to capture the correlation between tubes/videolets, which can provide rich contextual information and complex entity relationships for the concept learning of abnormal behaviors. Mutually-guided Progressive Refinement framework is set up to employ dual-path mutual guidance in a recurrent manner, iteratively sharing auxiliary supervision information across branches. It impels the learned concepts of each branch to serve as a guide for its counterpart, which progressively refines the corresponding branch and the whole framework. Furthermore, we contribute two datasets, i.e., ST-UCF-Crime and STRA, consisting of videos containing spatio-temporal abnormal annotations to serve as the benchmarks for WSSTAD. We conduct extensive qualitative and quantitative evaluations to demonstrate the effectiveness of the proposed approach and analyze the key factors that contribute more to handle this task.

scholarly journals Semi-Supervised Anomaly Detection in Video-Surveillance Scenes in the Wild

Sensors ◽  
2021 ◽  
Vol 21 (12) ◽  
pp. 3993
Author(s):  
Mohammad Ibrahim Sarker ◽  
Cristina Losada-Gutiérrez ◽  
Marta Marrón-Romera ◽  
David Fuentes-Jiménez ◽  
Sara Luengo-Sánchez
Keyword(s):  
Anomaly Detection ◽  
Video Surveillance ◽  
Learning Algorithm ◽  
Qualitative Evaluation ◽  
High Sensitivity ◽  
Fine Tuning ◽  
Surveillance Video ◽  
Emergency Situations ◽  
In The Wild ◽  
Spatio Temporal

Surveillance cameras are being installed in many primary daily living places to maintain public safety. In this video-surveillance context, anomalies occur only for a very short time, and very occasionally. Hence, manual monitoring of such anomalies may be exhaustive and monotonous, resulting in a decrease in reliability and speed in emergency situations due to monitor tiredness. Within this framework, the importance of automatic detection of anomalies is clear, and, therefore, an important amount of research works have been made lately in this topic. According to these earlier studies, supervised approaches perform better than unsupervised ones. However, supervised approaches demand manual annotation, making dependent the system reliability of the different situations used in the training (something difficult to set in anomaly context). In this work, it is proposed an approach for anomaly detection in video-surveillance scenes based on a weakly supervised learning algorithm. Spatio-temporal features are extracted from each surveillance video using a temporal convolutional 3D neural network (T-C3D). Then, a novel ranking loss function increases the distance between the classification scores of anomalous and normal videos, reducing the number of false negatives. The proposal has been evaluated and compared against state-of-art approaches, obtaining competitive performance without fine-tuning, which also validates its generalization capability. In this paper, the proposal design and reliability is presented and analyzed, as well as the aforementioned quantitative and qualitative evaluation in-the-wild scenarios, demonstrating its high sensitivity in anomaly detection in all of them.

scholarly journals Spatio-Temporal Hydrological Model Structure and Parametrization Analysis

2021 ◽  
Vol 9 (5) ◽  
pp. 467
Author(s):  
Mostafa Farrag ◽  
Gerald Corzo Perez ◽  
Dimitri Solomatine
Keyword(s):  
Hydrological Modeling ◽  
Model Building ◽  
Model Performance ◽  
Model Description ◽  
Generation Model ◽  
Model Structure ◽  
Runoff Generation ◽  
Spatial Sensitivity ◽  
Spatio Temporal ◽  
Set Up

Many grid-based spatial hydrological models suffer from the complexity of setting up a coherent spatial structure to calibrate such a complex, highly parameterized system. There are essential aspects of model-building to be taken into account: spatial resolution, the routing equation limitations, and calibration of spatial parameters, and their influence on modeling results, all are decisions that are often made without adequate analysis. In this research, an experimental analysis of grid discretization level, an analysis of processes integration, and the routing concepts are analyzed. The HBV-96 model is set up for each cell, and later on, cells are integrated into an interlinked modeling system (Hapi). The Jiboa River Basin in El Salvador is used as a case study. The first concept tested is the model structure temporal responses, which are highly linked to the runoff dynamics. By changing the runoff generation model description, we explore the responses to events. Two routing models are considered: Muskingum, which routes the runoff from each cell following the river network, and Maxbas, which routes the runoff directly to the outlet. The second concept is the spatial representation, where the model is built and tested for different spatial resolutions (500 m, 1 km, 2 km, and 4 km). The results show that the spatial sensitivity of the resolution is highly linked to the routing method, and it was found that routing sensitivity influenced the model performance more than the spatial discretization, and allowing for coarser discretization makes the model simpler and computationally faster. Slight performance improvement is gained by using different parameters’ values for each cell. It was found that the 2 km cell size corresponds to the least model error values. The proposed hydrological modeling codes have been published as open-source.

scholarly journals Towards Zero Emissions Noosa

2019 ◽  
Vol 11 (17) ◽  
pp. 4679
Author(s):  
Carina Anderson ◽  
Robert Passey ◽  
Jeremy De Valck ◽  
Rakibuzzaman Shah
Keyword(s):  
Community Engagement ◽  
Focal Point ◽  
Contextual Information ◽  
Renewable Electricity ◽  
Community Group ◽  
Course Of Action ◽  
Engagement Process ◽  
Set Up ◽  
External Consultant

This paper reports on a case study of the community group Zero Emissions Noosa, whose goal is for 100% renewable electricity in the Noosa Shire (Queensland, Australia) by 2026. Described within this paper are the processes used by Zero Emissions Noosa to set up their zero emissions plan, involving community engagement and the use of an external consultant. The external consultant was employed to produce a detailed report outlining how to successfully achieve zero emissions from electricity in the Noosa Shire by 2026. This paper explains how and why the community engagement process used to produce the report was just as important as the outcomes of the report itself. Modeling was undertaken, and both detailed and contextual information was provided. Inclusion of the community in developing the scenario parameters for the modeling had a number of benefits including establishing the context within which their actions would occur and focusing their efforts on options that were technically feasible, financially viable and within their capabilities to implement. This provided a focal point for the community in calling meetings and contacting stakeholders. Rather than prescribing a particular course of action, it also resulted in a toolbox of options, a range of possible solutions that is flexible enough to fit into whatever actions are preferred by the community. The approach and outcomes discussed in this paper should, therefore, be useful to other communities with similar carbon emission reduction goals.

scholarly journals Spatio-temporal expectile regression models

2019 ◽  
Vol 20 (4) ◽  
pp. 386-409
Author(s):  
Elmar Spiegel ◽  
Thomas Kneib ◽  
Fabian Otto-Sobotka
Keyword(s):  
Tensor Product ◽  
Least Squares Regression ◽  
Expectile Regression ◽  
Specific Distribution ◽  
Weighted Means ◽  
Temporal Models ◽  
Error Terms ◽  
Spatio Temporal ◽  
Set Up ◽  
Main Effects

Spatio-temporal models are becoming increasingly popular in recent regression research. However, they usually rely on the assumption of a specific parametric distribution for the response and/or homoscedastic error terms. In this article, we propose to apply semiparametric expectile regression to model spatio-temporal effects beyond the mean. Besides the removal of the assumption of a specific distribution and homoscedasticity, with expectile regression the whole distribution of the response can be estimated. For the use of expectiles, we interpret them as weighted means and estimate them by established tools of (penalized) least squares regression. The spatio-temporal effect is set up as an interaction between time and space either based on trivariate tensor product P-splines or the tensor product of a Gaussian Markov random field and a univariate P-spline. Importantly, the model can easily be split up into main effects and interactions to facilitate interpretation. The method is presented along the analysis of spatio-temporal variation of temperatures in Germany from 1980 to 2014.

RECOGNIZING HANDWRITTEN CHINESE CHARACTERS BY STROKE-SEGMENT MATCHING USING AN ITERATION SCHEME

1991 ◽  
Vol 05 (01n02) ◽  
pp. 175-197 ◽  
Author(s):  
SHENG-LIN CHOU ◽  
WEN-HSIANG TSAI
Keyword(s):  
Character Recognition ◽  
Contextual Information ◽  
Recognition Rate ◽  
Stable State ◽  
Evaluation Process ◽  
Iteration Scheme ◽  
Chinese Characters ◽  
Structure Information ◽  
Segment Matching ◽  
Set Up

The problem of handwritten Chinese character recognition is solved by matching character stroke segments using an iteration scheme. Length and orientation similarity properties, and coordinate overlapping ratios are used to define a measure of similarity between any two stroke segments. The initial measures of similarity between the stroke segments of the input and template characters are used to set up a match network which includes all the match relationships between the input and template stroke segments. Based on the concept of at-most-one to one mapping an iteration scheme is employed to adjust the match relationships, using the contextual information implicitly contained in the match network, so that the match relationships can get into a stable state. From the final match relationships, matched stroke-segment pairs are determined by a mutually-best match strategy and the degree of similarity between the input and each template character is evaluated accordingly. Certain structure information of Chinese characters is also used in the evaluation process. The experimental results show that the proposed approach is effective. For recognition of Chinese characters written by a specific person, the recognition rate is about 96%. If the characters of the first three ranks are checked in counting the recognition rate, the rate rises to 99.6%.

Efficient common objects localization based on deep hybrid Siamese network

2021 ◽  
pp. 1-10
Author(s):  
Mona M. Moussa ◽  
Rasha Shoitan ◽  
Mohamed S. Abdallah
Keyword(s):  
Distance Matrix ◽  
Multiple Objects ◽  
Siamese Network ◽  
Generation Stage ◽  
Pascal Voc ◽  
The Common ◽  
Conventional Methods ◽  
Weakly Supervised ◽  
Bounding Boxes ◽  
Two Stages

Finding the common objects in a set of images is considered one of the recent challenges in different computer vision tasks. Most of the conventional methods have proposed unsupervised and weakly supervised co-localization methods to find the common objects; however, these methods require producing a huge amount of region proposals. This paper tackles this problem by exploiting supervised learning benefits to localize the common object in a set of unlabeled images containing multiple objects or with no common objects. Two stages are proposed to localize the common objects: the candidate box generation stage and the matching and clustering stage. In the candidate box generation stage, the objects are localized and surrounded by the bounding boxes. The matching and clustering stage is applied on the generated bounding boxes and creates a distance matrix based on a trained Siamese network to reflect the matching percentage. Hierarchical clustering uses the generated distance matrix to find the common objects and create clusters for each one. The proposed method is trained on PASCAL VOC 2007 dataset; on the other hand, it is assessed by applying different experiments on PASCAL VOC 2007 6×2 and Object Discovery datasets, respectively. The results reveal that the proposed method outperforms the conventional methods by 8% to 40% in terms of corloc metric.

Spatio-Temporal AutoEncoder for Video Anomaly Detection

2017 ◽  
Author(s):  
Yiru Zhao ◽  
Bing Deng ◽  
Chen Shen ◽  
Yao Liu ◽  
Hongtao Lu ◽  
...  
Keyword(s):  
Anomaly Detection ◽  
Spatio Temporal
Sign in / Sign up

Export Citation Format

Share Document