UCF Crime Dataset in the most suitable structure. Contains 1900 videos from 13 different categories. To ensure the quality of this dataset, it is trained ten annotators (having different levels of computer vision expertise) to collect the dataset. Using videos search on YouTube and LiveLeak using text search queries (with slight variations e.g. “car crash”, “road accident”) of each anomaly.

Action recognition has received increasing attentions from the computer vision and machine learning community in the last decades. Ever since then, the recognition task has evolved from single view recording under controlled laboratory environment to unconstrained environment (i.e., surveillance environment or user generated videos). Furthermore, recent work focused on other aspect of action recognition problem, such as cross-view classification, cross domain learning, multi-modality learning, and action localization. Despite the large variations of studies, we observed limited works that explore the open-set and open-view classification problem, which is a genuine inherited properties in action recognition problem. In other words, a well designed algorithm should robustly identify an unfamiliar action as “unknown” and achieved similar performance across sensors with similar field of view. The Multi-Camera Action Dataset (MCAD) is designed to evaluate the open-view classification problem under surveillance environment.

In our multi-camera action dataset, different from common action datasets we use a total of five cameras, which can be divided into two types of cameras (StaticandPTZ), to record actions. Particularly, there are three Static cameras (Cam04 & Cam05 & Cam06) with fish eye effect and two PanTilt-Zoom (PTZ) cameras (PTZ04 & PTZ06). Static camera has a resolution of 1280×960 pixels, while PTZ camera has a resolution of 704×576 pixels and a smaller field of view than Static camera. What’s more, we don’t control the illumination environment. We even set two contrasting conditions (Daytime and Nighttime environment) which makes our dataset more challenge than many controlled datasets with strongly controlled illumination environment.The distribution of the cameras is shown in the picture on the right.

We identified 18 units single person daily actions with/without object which are inherited from the KTH, IXMAS, and TRECIVD datasets etc. The list and the definition of actions are shown in the table. These actions can also be divided into 4 types actions. Micro action without object (action ID of 01, 02 ,05) and with object (action ID of 10, 11, 12 ,13). Intense action with object (action ID of 03, 04 ,06, 07, 08, 09) and with object (action ID of 14, 15, 16, 17, 18). We recruited a total of 20 human subjects. Each candidate repeats 8 times (4 times during the day and 4 times in the evening) of each action under one camera. In the recording process, we use five cameras to record each action sample separately. During recording stage we just tell candidates the action name then they could perform the action freely with their own habit, only if they do the action in the field of view of the current camera. This can make our dataset much closer to reality. As a results there is high intra action class variation among different action samples as shown in picture of action samples.

URL: http://mmas.comp.nus.edu.sg/MCAD/MCAD.html

Resources:

• IDXXXX.mp4.tar.gz contains video data for each individual
• boundingbox.tar.gz contains person bounding box for all videos
• protocol.json contains the evaluation protocol
• img_list.txt contains the download URLs for the images version of the video data
• idt_list.txt contians the download URLs for the improved Dense Trajectory feature
• stip_list.txt contians the download URLs for the STIP feature

• Manual annotated 2D joints for selected camera view and action class (available via http://zju-capg.org/heightmap/)

How to Cite:

Please cite the following paper if you use the MCAD dataset in your work (papers, articles, reports, books, software, etc):

• Wenhui Liu, Yongkang Wong, An-An Liu, Yang Li, Yu-Ting Su, Mohan Kankanhalli
  Multi-Camera Action Dataset for Cross-Camera Action Recognition Benchmarking
  IEEE Winter Conference on Applications of Computer Vision (WACV), 2017.
  http://doi.org/10.1109/WACV.2017.28

This is a new benchmark we call the Smart-City CCTV Violence Detection dataset (SCVD). Current datasets such as the NTU CCTV-Fights dataset, Real-Life Violence Situations dataset (RLVS) and other currently used datasets for violence detection contain videos recorded from phone cameras that could alter the distribution and focus of the CCTV based Violence detection. Furthermore, our dataset contains a class for weapons detection in videos, making it the first weapons video dataset as other datasets for weapons detection are based on images of mostly guns and knives. This means that the SCVD dataset is tuned to the fact that any handheld object which could be used to harm humans and properties could be regarded as a weapon.

If you use this dataset, cite our paper: @InProceedings{ 10.1007/978-3-031-62269-4_2, author="Aremu, Toluwani and Zhiyuan, Li and Alameeri, Reem and Khan, Mustaqeem and Saddik, Abdulmotaleb El", editor="Arai, Kohei", title="SSIVD-Net: A Novel Salient Super Image Classification and Detection Technique for Weaponized Violence", booktitle="Intelligent Computing", year="2024", publisher="Springer Nature Switzerland", address="Cham", pages="16--35", isbn="978-3-031-62269-4" }

Multi Camera real scene video Dataset

A Real-World Multi-Camera Video Dataset for Generative Vision AI

📌 Overview

The MultiScene360 Dataset is designed to advance generative vision AI by providing synchronized multi-camera footage from real-world environments.

💡 Key Applications:
✔ Video generation & view synthesis
✔ 3D reconstruction & neural rendering
✔ Digital human animation systems
✔ Virtual/augmented reality development

📊 Dataset Specifications (Public Version)

Commercial version available with 200+ scenes and 6-8 camera angles

🌆 Complete Scene Specification

🎥 Camera Configuration

Physical Setup:
cam01──────cam02 \ / Subject /
cam04──────cam03

Technical Details:
- Cameras: DJI Osmo Action 5 Pro (4 identical units)
- Mounting: Tripod-stabilized at ~1.5m height
- Distance: 2-3m from subject center
- FOV Overlap: 20-30% between adjacent cameras

🔍 Suggested Research Directions

1. Cross-view consistency learning
2. Novel view synthesis from sparse inputs
3. Dynamic scene reconstruction
4. Human motion transfer between viewpoints

🚀 Access Information

🎯 Sample Download Here: https://madacode.file.core.windows.net/root/360/detaset_sample_part.zip?sv=2023-01-03&st=2025-05-06T08%3A56%3A56Z&se=2028-01-07T08%3A56%3A00Z&sr=f&sp=r&sig=5R2FrdBqw35HIF0r2TaUxAsr0mz5h7oKDUHFFpkD8ik%3D ✨ Free Public Download: https://maadaa.ai/multiscene360-Dataset
💼 Commercial Inquiries: contact@maadaa.ai
Usage Rights:
✔ Free for academic/commercial use
✔ License: Attribution-NonCommercial-ShareAlike 4.0 International

About maadaa.ai

Founded in 2015, maadaa.ai is a pioneering AI data service provider specializing in multimodal data solutions for generative AI development. We deliver end-to-end data services covering text, voice, image, and video datatypes – the core fuel for training and refining generative models. Our Generative AI Data Solution includes: ꔷ High-quality dataset collection & annotation tailored for LLMs and diffusion models ꔷ Scenario-based human feedback (RLHF/RLAIF) to enhance model alignment ꔷ One-stop data management through our MaidX platform for streamlined model training

Why Choose Us:
✓ Reduce real-world data collection costs by 70%+
✓ Generate perfectly labeled training data at scale
✓ API-first integration for synthetic pipelines

Empowering the next generation of interactive media and spatial computing*

Home Video Surveillance

## Overview

Home Video Surveillance is a dataset for object detection tasks - it contains Humans annotations for 1,701 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 [Public Domain license](https://creativecommons.org/licenses/Public Domain).

This dataset is a research work of https://xuange923.github.io/Surveillance-Video-Understanding

All the credits go to the researchers involved. I highly recommend you to read the research paper for a better and concrete understanding about the dataset and experiments performed by research on Temporal Sentence Grounding in Videos, Video Captioning, Dense Video Captioning, Multimodal Anomaly Detection.

The description I gave here are key takeaways about the dataset.

Need

Current surveillance video tasks mainly focus on classifying and localizing anomalous events. Surveillance video datasets lack sentence-level language annotations. The researchers involved propose a new research direction of surveillance video-and-language understanding by constructing the UCA (UCF-Crime Annotation) Dataset.

Description

The researchers manually annotated the event content and event occurrence time for 1,854 videos from UCF-Crime, called UCF-Crime Annotation (UCA).The dataset contains 23,542 sentences, with an average length of 20 words, and its annotated videos are as long as 110.7 hours.

![https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F15856017%2F8192ec392aa60fc988158fe52521d15c%2FScreenshot%202024-09-17%20225518.png?generation=1726593960412846&alt=media" alt="">]

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F15856017%2Fdf4c4398b869b62198d031d7b80c422a%2FScreenshot%202024-09-17%20225800.png?generation=1726594099581994&alt=media" alt="">

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F15856017%2Fb7280d2e2fb4820067b1a77a95744d4a%2FScreenshot%202024-09-17%20230159.png?generation=1726594362520024&alt=media" alt="">

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F15856017%2Fe2f8d67bc27aca4a837c6c46e6bb347f%2FScreenshot%202024-09-17%20230320.png?generation=1726594421676695&alt=media" alt="">

How did the researchers annotate the data?

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F15856017%2Ffceea2695b15324fed1b851d65e1606f%2FScreenshot%202024-09-12%20193832.png?generation=1726594522513630&alt=media" alt="">

Citation

@misc{yuan2023surveillance,
title={Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges}, 
author={Tongtong Yuan and Xuange Zhang and Kun Liu and Bo Liu and Chen Chen and Jian Jin and Zhenzhen Jiao},
year={2023},
eprint={2309.13925},
archivePrefix={arXiv},
primaryClass={cs.CV}
}    

Human Action Detection Video Surveillance

## Overview

Human Action Detection Video Surveillance is a dataset for object detection tasks - it contains Action annotations for 269 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).

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

Aggressive Behavior Video Classification, Object Detection dataset

WARNING: People in the videos exhibit aggressive behavior

The dataset with videos depicting people exhibiting aggressive and non-aggressive behavior is intended for classification purposes. It consists of a collection of video files that capture various individuals engaging in different activities and displaying distinct behavioral patterns and CSV-file with classification.

💴 For Commercial Usage: To discuss your requirements, learn about the price and buy the dataset, leave a request on our website to buy the dataset

Aggressive Behavior Video Classification Dataset can have multiple applications, such as surveillance systems, security modules, or social behavior analysis platforms.

https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F12421376%2F4c8444fb8ddba04b0b0191d3517af3c6%2Ffreecompress-ezgif.gif?generation=1697023398942461&alt=media" alt="">

Dataset structure

The dataset consists of: - files: folder with videos with people exhibiting aggressive and non-aggressive behaviour (subfolders "aggressive" and "non_aggressive" respectively), - .csv file: path of each video in the "files" folder and classification of the behavoir

People Behavior Video Classification might be made in accordance with your requirements.

🧩 This is just an example of the data. Leave a request here to learn more

🚀 You can learn more about our high-quality unique datasets here

keywords: violence detection, violence classification, violent activity, violent crimes, real life violence detection, biometric dataset, biometric data dataset, object detection, public safety, human video, deep learning dataset, human video dataset, video dataset, video classification, computer vision, machine learning, cctv, camera detection, surveillance, security camera, security camera object detection, video-based monitoring, smart city, smart city development, smart city vision, smart city deep learning, smart city management

The CCTV Human Pose Estimation Dataset from GTS.AI contains annotated CCTV video samples featuring diverse human activities and poses. Ideal for developing AI and ML models for surveillance analytics, behavior recognition, and smart city monitoring.

Faced with the growing population of seniors, developed countries need to develop new healthcare systems to help elderly people staying at home in a secure environment. Falls are one of the major risk for seniors living alone at home, causing severe injuries. Computer vision provides a new and promising solution for fall detection.

This is a unique video data set which will be very useful for the data science community to test their fall detection algorithms. The attached report provides an overview of the video data set acquired from a calibrated multi-camera system. This video data set contains simulated falls and normal daily activities acquired in realistic situations.

Context

Action Recognition in video is known to be more challenging than image recognition problems. Unlike image recognition models which use 2D convolutional neural blocks, action classification models require additional dimensionality to capture the spatio-temporal information in video sequences. This intrinsically makes video action recognition models computationally intensive and significantly more data-hungry than image recognition counterparts. Unequivocally, existing video datasets such as Kinetics, AVA, Charades, Something-Something, HMDB51, and UFC101 have had tremendous impact on the recently evolving video recognition technologies. Artificial Intelligence models trained on these datasets have largely benefited applications such as behavior monitoring in elderly people, video summarization, and content-based retrieval. However, this growing concept of action recognition has yet to be explored in Intelligent Transportation System (ITS), particularly in vital applications such as incidents detection. This is partly due to the lack of availability of annotated dataset adequate for training models suitable for such direct ITS use cases. In this paper, the concept of video action recognition is explored to tackle the problem of highway incident detection and classification from live surveillance footage. First, a novel dataset - HWID12 (Highway Incidents Detection) dataset is introduced. The HWAD12 consists of 11 distinct highway incidents categories, and one additional category for negative samples representing normal traffic. The proposed dataset also includes 2780+ video segments of 3 to 8 seconds on average each, and 500k+ temporal frames. Next, the baseline for highway accident detection and classification is established with a state-of-the-art action recognition model trained on the proposed HWID12 dataset. Performance benchmarking for 12-class (normal traffic vs 11 accident categories), and 2-class (incident vs normal traffic) settings is performed. This benchmarking reveals a recognition accuracy of up to 88% and 98% for 12-class and 2-class recognition setting, respectively.

Data Acquisition

The Proposed Highway Incidents Detection Dataset (HWID12) is the first of its kind dataset aimed at fostering experimentation of video action recognition technologies to solve the practical problem of real-time highway incident detections which currently challenges intelligent transportation systems. The lack of such dataset has limited the expansion of the recent breakthroughs in video action classification for practical uses cases in intelligent transportation systems.. The proposed dataset contains more than 2780 video clips of length varying between 3 to 8 seconds. These video clips capture moments leading to, up until right after an incident occurred. The clips were manually segmented from accident compilations videos sourced from YouTube and other videos data platforms.

Content

There is one main zip file available for download. The zip file contains 2780+ video clips. 1) 12 folders
2) each folder represents an incident category. One of the classes represent the negative sample class which simulates normal traffic.

Terms and Conditions

• Videos provided in this dataset are freely available for research and education purposes only. Please be sure to properly credit the authors by citing the article below.
• Be sure to upvote this dataset if you find it useful by scrolling up and clicking the up-Arrow ^ sign at the top banner of the page, next to "New Notebook" button.
• Be sure to blur out all plate numbers before publishing any of the contents available in this dataset.

Acknowledgements

Any publication using this database must reference to the following journal manuscript:

• Landry Kezebou, Victor Oludare, Karen Panetta, James Intriligator, and Sos Agaian "Highway accident detection and classification from live traffic surveillance cameras: a comprehensive dataset and video action recognition benchmarking", Proc. SPIE 12100, Multimodal Image Exploitation and Learning 2022, 121000M (27 May 2022); https://doi.org/10.1117/12.2618943

Note: if the link is broken, please use http instead of https.

In Chrome, use the steps recommended in the following website to view the webpage if it appears to be broken https://www.technipages.com/chrome-enabledisable-not-secure-warning

Other relevant datasets VCoR dataset: https://www.kaggle.com/landrykezebou/vcor-vehicle-color-recognition-dataset VRiV dataset: https://www.kaggle.com/landrykezebou/vriv-vehicle-recognition-in-videos-dataset

For any enquires regarding the HWID12 dataset, contact: landrykezebou@gmail.com

SCface is a database of static images of human faces. Images were taken in uncontrolled indoor environment using five video surveillance cameras of various qualities. Database contains 4160 static images (in visible and infrared spectrum) of 130 subjects. Images from different quality cameras mimic the real-world conditions and enable robust face recognition algorithms testing, emphasizing different law enforcement and surveillance use case scenarios.

SAIVT-Campus Dataset

Overview

The SAIVT-Campus Database is an abnormal event detection database captured on a university campus, where the abnormal events are caused by the onset of a storm. Contact Dr Simon Denman or Dr Jingxin Xu for more information.

Licensing

The SAIVT-Campus database is © 2012 QUT and is licensed under the Creative Commons Attribution-ShareAlike 3.0 Australia License.

Attribution

To attribute this database, please include the following citation: Xu, Jingxin, Denman, Simon, Fookes, Clinton B., & Sridharan, Sridha (2012) Activity analysis in complicated scenes using DFT coefficients of particle trajectories. In 9th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2012), 18-21 September 2012, Beijing, China. available at eprints.

Acknowledging the Database in your Publications

In addition to citing our paper, we kindly request that the following text be included in an acknowledgements section at the end of your publications: We would like to thank the SAIVT Research Labs at Queensland University of Technology (QUT) for freely supplying us with the SAIVT-Campus database for our research.

Installing the SAIVT-Campus database

After downloading and unpacking the archive, you should have the following structure:

SAIVT-Campus +-- LICENCE.txt +-- README.txt +-- test_dataset.avi +-- training_dataset.avi +-- Xu2012 - Activity analysis in complicated scenes using DFT coefficients of particle trajectories.pdf

Notes

The SAIVT-Campus dataset is captured at the Queensland University of Technology, Australia.

It contains two video files from real-world surveillance footage without any actors:

training_dataset.avi (the training dataset)
test_dataset.avi (the test dataset).

This dataset contains a mixture of crowd densities and it has been used in the following paper for abnormal event detection:

Xu, Jingxin, Denman, Simon, Fookes, Clinton B., & Sridharan, Sridha (2012) Activity analysis in complicated scenes using DFT coefficients of particle trajectories. In 9th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS 2012), 18-21 September 2012, Beijing, China. Available at eprints. 
This paper is also included with the database (Xu2012 - Activity analysis in complicated scenes using DFT coefficients of particle trajectories.pdf) Both video files are one hour in duration.

The normal activities include pedestrians entering or exiting the building, entering or exiting a lecture theatre (yellow door), and going to the counter at the bottom right. The abnormal events are caused by a heavy rain outside, and include people running in from the rain, people walking towards the door to exit and turning back, wearing raincoats, loitering and standing near the door and overcrowded scenes. The rain happens only in the later part of the test dataset.

As a result, we assume that the training dataset only contains the normal activities. We have manually made an annotation as below:

the training dataset does not have abnormal scenes
the test dataset separates into two parts: only normal activities occur from 00:00:00 to 00:47:16 abnormalities are present from 00:47:17 to 01:00:00. We annotate the time 00:47:17 as the start time for the abnormal events, as from this time on we have begun to observe people stop walking or turn back from walking towards the door to exit, which indicates that the rain outside the building has influenced the activities inside the building. Should you have any questions, please do not hesitate to contact Dr Jingxin Xu.

Security Footage Analysis

## Overview

Security Footage Analysis is a dataset for object detection tasks - it contains People annotations for 4,565 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 Traffic Vehicles Object Detection dataset is a valuable resource containing 1,201 images capturing the dynamic world of traffic, featuring 11,134 meticulously labeled objects. These objects are classified into seven distinct categories, including common vehicles like car, two_wheeler, as well as blur_number_plate, and other essential elements such as auto, number_plate, bus, and truck. The dataset's origins lie in the collection of training images from traffic scenes and CCTV footage, followed by precise object annotation and labeling, making it an ideal tool for object detection tasks in the realm of transportation and surveillance.

These are video datasets used for the research experiment of encryption and tampering

The original videos are stored in the Original_Videos folder, the encrypted videos are stored in the Encrypted_Videos folder, and the tampered videos are stored in the Tampering_on_encryption folder.

ORIGINAL VIDEOS These videos are classified into Two groups

Static videos Dynamic videos

STATIC VIDEOS: These are videos gotten from CCTV recordings that are fixed to a particular location, thus the background is static and the foreground is objects in motion.

DYNAMIC VIDEOS: These are aerial view videos gotten from drones, pan-tilt-zoom (PTZ), dashboard cams, and Unmanned Aerial Vehicles (UAV) recordings. The camera records while in motion which makes it look like the background is moving. The foreground is the actual objects in motion.

These videos were retrieved from

[1] Pexels, Pexels webpage, 2023. URL: https://www.pexels.com/ last accessed 2023-07-10

[2] Pixabay, Pixabay webpage, 2023. URL: https://pixabay.com/videos/ last accessed 2023-07-10

[3] Motchallenge, Motchallenge webpage, 2023. URL: https://motchallenge.net/data/MOT17/ last accessed 2023-07-10

ENCRYPTED VIDEOS

Motion detection was performed using some algorithms on the original videos to separate the objects in motion from the static objects. For the static camera the Gaussian mixture method (GMM) [4] was used and for the dynamic camera advance flow of motion (AFOM) [5] was used. After detection, global thresholding [6] was implemented to segment the foreground (FG) from the background (BG). FG are the objects in motion while BG are the static objects. After segmentation, Chacha20 [7] a stream cipher algorithm, was implemented on the FG objects and are stored securely.

[4] Gupta, T. Sortrakul, A Gaussian-mixture-based image segmentation algorithm, Pattern Recognition 31 (1998) 315–325.

[5] I. Aribilola, M. Naveed Asghar, N. Kanwal, M. Samar Ansari, B. Lee, Afom: Advanced flow of motion detection algorithm for dynamic camera videos, in: 2022 33rd Irish Signals and Systems Conference (ISSC), 2022, pp. 1–6. doi:10.1109/ISSC55427.2022.9826141.

[6] S. Ferrari, “Image segmentation Segmentation by thresholding Noise role in thresholding,” Image processing I, pp. 1–22, 2012

[7] Y. Nir, A. Langley, RFC 7539 - ChaCha20 and Poly1305 for IETF Protocols, 2015. URL: https://tools.ietf.org/html/rfc7539.

Tampered VIDEOS

Different types of tampering were simulated against the encrypted FG object.

The lowercase attack, uppercase attack, and random-insertion attack were launched against the FG-encrypted videos.

Different frames were tampered with in the video and the results were stored in the tampering_on_encrypted_videos folder for general usage.

The FG-tampered encrypted and tampered decrypted frames were stored in this repository.

Comparing the FG encrypted videos with tampering and the FG encrypted video without tampering has clear visibility. Likewise, after the decryption of the FG-encrypted videos, the attack was clearly visible on these videos.

Please, reference this repository if any of these frames are used by you.

DAWN (Detection in Adverse Weather Nature) dataset consists of real-world images collected under various adverse weather conditions. This dataset emphasizes a diverse traffic environment (urban, highway and freeway) as well as a rich variety of traffic flow. The DAWN dataset comprises a collection of 1000 images from real-traffic environments, which are divided into four sets of weather conditions: fog, snow, rain and sandstorms. The dataset is annotated with object bounding boxes for autonomous driving and video surveillance scenarios. This data helps interpreting effects caused by the adverse weather conditions on the performance of vehicle detection systems. Also, it is required by researchers work in autonomous vehicles and intelligent visual traffic surveillance systems fields. All the rights of the DAWN dataset are reserved and commercial use/distribution of this database is strictly prohibited.

The SmartBay Observatory in Galway Bay is an underwater observatory which uses cameras, probes and sensors to permit continuous and remote live underwater monitoring. It was installed in 2015 on the seafloor 1.5km off the coast of Spiddal, Co. Galway, Ireland at a depth of 20-25m. Underwater observatories allow ocean researchers unique real-time access to monitor ongoing changes in the marine environment. The Galway Bay Observatory is an important contribution by Ireland to the growing global network of real-time data capture systems deployed in the ocean. Data relating to the marine environment at the Galway Observatory site is transferred in real-time through a fibre optic telecommunications cable to the Marine Institute headquarters and then made publicly available on the internet. The data includes a live video stream, the depth of the observatory node, the water temperature and salinity, and estimates of the chlorophyll and turbidity levels in the water which give an indication of the volume of phytoplankton and other particles, such as sediment, in the water. Maintenance take place on the observatory every 18 to 24 months. Video data is streamed in near-real-time from the observatory and this dataset describes the video footage that is available for download. None

Traffic Camera Analytic PSM

## Overview

Traffic Camera Analytic PSM is a dataset for object detection tasks - it contains Objects annotations for 2,570 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).