Whereas the action recognition community has focused mostly on detecting simple actions like clapping, walking or jogging, the detection of fights or in general aggressive behaviors has been comparatively less studied. Such capability may be extremely useful in some video surveillance scenarios like in prisons, psychiatric or elderly centers or even in camera phones. After an analysis of previous approaches we test the well-known Bag-of-Words framework used for action recognition in the specific problem of fight detection, along with two of the best action descriptors currently available: STIP and MoSIFT. For the purpose of evaluation and to foster research on violence detection in video we introduce a new video database containing 1000 sequences divided in two groups: fights and non-fights. Experiments on this database and another one with fights from action movies show that fights can be detected with near 90% accuracy.

Fight Detection

## Overview

Fight Detection is a dataset for object detection tasks - it contains Fight DuOD annotations for 1,252 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Whereas the action recognition community has focused mostly on detecting simple actions like clapping, walking or jogging, the detection of fights or in general aggressive behaviors has been comparatively less studied. Such capability may be extremely useful in some video surveillance scenarios like in prisons, psychiatric or elderly centers or even in camera phones. After an analysis of previous approaches we test the well-known Bag-of-Words framework used for action recognition in the specific problem of fight detection, along with two of the best action descriptors currently available: STIP and MoSIFT. For the purpose of evaluation and to foster research on violence detection in video we introduce a new video database containing 1000 sequences divided in two groups: fights and non-fights. Experiments on this database and another one with fights from action movies show that fights can be detected with near 90% accuracy.

Assault

Fall Fight Detection

## Overview

Fall Fight Detection is a dataset for object detection tasks - it contains Fall Fight annotations for 703 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Dataset

The Bus Violence dataset is a large-scale collection of videos depicting violent and non-violent situations in public transport environments. This benchmark was gathered from multiple cameras located inside a moving bus where several people simulated violent actions, such as stealing an object from another person, fighting between passengers, etc. It contains 1,400 video clips manually annotated as having or not violent scenes, making it one of the biggest benchmarks for video violence detection in the literature.

Specifically, videos are recorded from three cameras at 25 Frames Per Second (FPS) --- two cameras located in the corners of the bus (with resolution 960x540 px) and one fisheye in the middle (1280x960 px). The clips have a minimum length of 16 frames and a maximum of 48 frames, capturing a very precise action (either violence or non-violence). The dataset is perfectly balanced, containing 700 videos of violence and 700 videos of non-violence.

The Bus Violence dataset is intended as a test data benchmark. However, for researchers interested in using our data also for training purposes, we provide training and test splits.

In this repository, we provide

• the 1,400 video clips divided into two folders named Violence /NoViolence, containing clips of violent situations and non-violent situations, respectively;

• two txt files containing the names of the videos belonging to the training and test splits, respectively.

Citing our work

If you found this dataset useful, please cite the following paper

@inproceedings{bus_violence_dataset_2022,
  title = {Bus Violence: An Open Benchmark for Video Violence Detection on Public Transport},
  doi = {10.3390/s22218345},
  url = {https://doi.org/10.3390%2Fs22218345},
  year = 2022,
  month = {oct},
  publisher = {{MDPI} {AG}},
  volume = {22},
  number = {21},
  pages = {8345},
  author = {Luca Ciampi and Pawe{\l} Foszner and Nicola Messina and Micha{\l} Staniszewski and Claudio Gennaro and Fabrizio Falchi and Gianluca Serao and Micha{\l} Cogiel and Dominik Golba and Agnieszka Szcz{\k{e}}sna and Giuseppe Amato},
  journal = {Sensors}
}

and this Zenodo Dataset

@dataset{pawel_bus_violence_zenodo,
  author    = {Paweł Foszner, Michał Staniszewski, Agnieszka Szczęsna, Michał Cogiel, Dominik Golba, Luca Ciampi, Nicola Messina, Claudio Gennaro, Fabrizio Falchi, Giuseppe Amato, Gianluca Serao},
  title    = {{Bus Violence: a large-scale benchmark for video violence detection in public transport}},
  month    = sep,
  year     = 2022,
  publisher  = {Zenodo},
  version   = {1.0.0},
  doi     = {10.5281/zenodo.7044203},
  url     = {https://doi.org/10.5281/zenodo.7044203}
}

Contact Information

Blees Sp. z o.o., Gliwice, Poland
mstaniszewski@blees.co

Acknowledgments

The presented dataset was supported by: European Union funds awarded to Blees Sp. z o.o. under grant POIR.01.01.01-00-0952/20-00 “Development of a system for analysing vision data captured by public transport vehicles interior monitoring, aimed at detecting undesirable situations/behaviours and passenger counting (including their classification by age group) and the objects they carry”); EC H2020 project "AI4media: a Centre of Excellence delivering next generation AI Research and Training at the service of Media, Society and Democracy" under GA 951911; research project INAROS (INtelligenza ARtificiale per il mOnitoraggio e Supporto agli anziani), Tuscany POR FSE CUP B53D21008060008.

License

The Bus Violence dataset was acquired by Blees Sp. z o.o. and is released under a Creative Commons Attribution license for non-commercial use.

The CHU Surveillance Violence Dataset (CSVD) is a collection of CCTV footage of violent and non-violent actions aiming to characterize the composition of violent actions into more specific actions. We produced several simple action classes for violent and non-violent actions do add variety and better distribution among simple and complex action classes for RGB and Action Silhouette Videos (enhanced Optical Flow Images) with their localized actions.

To address the limitations of current datasets used for training automated crime and violence detection systems, we have created a new, balanced dataset consisting of 3,000 video clips. The dataset, which includes an equal number of violent and non-violent real-world scenarios recorded by non-professional actors, provides a more comprehensive and representative source for the development and assessment of these systems. Security and law enforcement professionals can use this comprehensive approach to analyze surveillance footage and identify pertinent incidents more efficiently.

Realtime Violence Detection

## Overview

Realtime Violence Detection is a dataset for object detection tasks - it contains Violence Nonviolence annotations for 2,657 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

e.g.

Violence

## Overview

Violence is a dataset for object detection tasks - it contains Violence annotations for 1,201 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

Violence Detection Through CCTV

## Overview

Violence Detection Through CCTV is a dataset for object detection tasks - it contains Objects annotations for 6,264 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

The curated and extracted videos are sourced from various Sports videos, Hollywood, Korean, and Bollywood movie action scenes, Social media platforms, including YouTube, and some videos are taken from HockeyFights (HF) and SCVD datasets to compile the Extended Automatic Violence Detection Dataset (EAVDD). Videos representing different classes are meticulously labeled and organized into distinct directories, each named in alignment with the specific video type.

EAVDD is distinguished for its comprehensive and unbiased representation of violent activities, spanning various individuals and scenarios, mitigating biases. Specifically, our dataset features two categories, Violence and NonViolence, comprising 1530 videos. Only some samples are provided here.

WARNING: The dataset with videos depicting people exhibiting violence and non violent behavior is only intended for research and recognition purposes.

The dataset will be provided quarterly in several phases throughout the year.

Contact: avdataset@gmail.com to get more information about the Dataset.

Dataset Card for "violence-detection-dataset"

More Information needed

Real-world Anomaly Detection in Surveillance Videos

Surveillance videos are able to capture a variety of realistic anomalies. In this paper, we propose to learn anomalies by exploiting both normal and anomalous videos. To avoid annotating the anomalous segments or clips in training videos, which is very time consuming, we propose to learn anomaly through the deep multiple instance ranking framework by leveraging weakly labeled training videos, i.e. the training labels (anomalous or normal) are at video-level instead of clip-level. In our approach, we consider normal and anomalous videos as bags and video segments as instances in multiple instance learning (MIL), and automatically learn a deep anomaly ranking model that predicts high anomaly scores for anomalous video segments. Furthermore, we introduce sparsity and temporal smoothness constraints in the ranking loss function to better localize anomaly during training. We also introduce a new large-scale first of its kind dataset of 128 hours of videos. It consists of 1900 long and untrimmed real-world surveillance videos, with 13 realistic anomalies such as fighting, road accident, burglary, robbery, etc. as well as normal activities. This dataset can be used for two tasks. First, general anomaly detection considering all anomalies in one group and all normal activities in another group. Second, for recognizing each of 13 anomalous activities. Our experimental results show that our MIL method for anomaly detection achieves significant improvement on anomaly detection performance as compared to the state-of-the-art approaches. We provide the results of several recent deep learning baselines on anomalous activity recognition. The low recognition performance of these baselines reveals that our dataset is very challenging and opens more opportunities for future work.

Problem & Motivation

One critical task in video surveillance is detecting anomalous events such as traffic accidents, crimes or illegal activities. Generally, anomalous events rarely occur as compared to normal activities. Therefore, to alleviate the waste of labor and time, developing intelligent computer vision algorithms for automatic video anomaly detection is a pressing need. The goal of a practical anomaly detection system is to timely signal an activity that deviates normal patterns and identify the time window of the occurring anomaly. Therefore, anomaly detection can be considered as coarse level video understanding, which filters out anomalies from normal patterns. Once an anomaly is detected, it can further be categorized into one of the specific activities using classification techniques. In this work, we propose an anomaly detection algorithm using weakly labeled training videos. That is we only know the video-level labels, i.e. a video is normal or contains anomaly somewhere, but we do not know where. This is intriguing because we can easily annotate a large number of videos by only assigning video-level labels. To formulate a weakly-supervised learning approach, we resort to multiple instance learning. Specifically, we propose to learn anomaly through a deep MIL framework by treating normal and anomalous surveillance videos as bags and short segments/clips of each video as instances in a bag. Based on training videos, we automatically learn an anomaly ranking model that predicts high anomaly scores for anomalous segments in a video. During testing, a longuntrimmed video is divided into segments and fed into our deep network which assigns anomaly score for each video segment such that an anomaly can be detected.

Method

Our proposed approach (summarized in Figure 1) begins with dividing surveillance videos into a fixed number of segments during training. These segments make instances in a bag. Using both positive (anomalous) and negative (normal) bags, we train the anomaly detection model using the proposed deep MIL ranking loss. https://www.crcv.ucf.edu/projects/real-world/method.png

UCF-Crime Dataset

We construct a new large-scale dataset, called UCF-Crime, to evaluate our method. It consists of long untrimmed surveillance videos which cover 13 realworld anomalies, including Abuse, Arrest, Arson, Assault, Road Accident, Burglary, Explosion, Fighting, Robbery, Shooting, Stealing, Shoplifting, and Vandalism. These anomalies are selected because they have a significant impact on public safety. We compare our dataset with previous anomaly detection datasets in Table 1. For more details about the UCF-Crime dataset, please refer to our paper. A short description of each anomalous event is given below. Abuse: This event contains videos which show bad, cruel or violent behavior against children, old people, animals, and women. Burglary: This event contains videos that show people (thieves) entering into a building or house with the intention to commit theft. It does not include use of force against people. Robbery: This event contains videos showing thieves taking money unlawfully by force or threat of force. These videos do not include shootings. Stealing: This event contains videos showing people taking property or money without permission. They do not include shoplifting. Shooting: This event contains videos showing act of shooting someone with a gun. Shoplifting: This event contains videos showing people stealing goods from a shop while posing as a shopper. Assault: This event contains videos showing a sudden or violent physical attack on someone. Note that in these videos the person who is assaulted does not fight back. Fighting: This event contains videos displaying two are more people attacking one another. Arson: This event contains videos showing people deliberately setting fire to property. Explosion: This event contains videos showing destructive event of something blowing apart. This event does not include videos where a person intentionally sets a fire or sets off an explosion. Arrest: This event contains videos showing police arresting individuals. Road Accident: This event contains videos showing traffic accidents involving vehicles, pedestrians or cyclists. Vandalism: This event contains videos showing action involving deliberate destruction of or damage to public or private property. The term includes property damage, such as graffiti and defacement directed towards any property without permission of the owner. Normal Event: This event contains videos where no crime occurred. These videos include both indoor (such as a shopping mall) and outdoor scenes as well as day and night-time scenes. https://www.crcv.ucf.edu/projects/real-world/dataset_table.png https://www.crcv.ucf.edu/projects/real-world/method.png

Violence And Weapons Detection 2

## Overview

Violence And Weapons Detection 2 is a dataset for object detection tasks - it contains Violence NonViolence Violence NonViolence Knife Gun JiWK annotations for 9,974 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

Dataset for the paper "Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervision". The dataset is downloaded from the authors' website (https://roc-ng.github.io/XD-Violence/). Hosting this dataset on HuggingFace is just to make it easier for my own project to use this dataset. Please cite the original paper if you use this dataset.

A dataset with violent and non-violent scenes was collected from movies.

This dataset contains 11,230 videos capturing fight behaviors, includes indoor scenes (dining room, living room, boxing room, etc.) and outdoor scenes (road, crosswalk, lawn, etc.). The data covers multiple scenes, multiple races, multiple types of fighting. The data can be used for tasks such as fight behavior detection, fight behavior recognition, human altercation recognition and other tasks.

11,230 Videos - Fight Behavior Data. The data includes indoor scenes (dining room, living room, boxing room, etc.), outdoor scenes (road, crosswalk, lawn, etc.). The data covers multiple scenes, multiple races, multiple types of fighting. The data can be used for tasks such as fight behavior detection, fight behavior recognition and other tasks.