Yolov8 Pose

## Overview

Yolov8 Pose is a dataset for computer vision tasks - it contains Fall annotations for 474 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).

falling dataset for falling detection using yolov8 pose

Description:

👉 Download the dataset here

This dataset has been specifically curated for cow pose estimation, designed to enhance animal behavior analysis and monitoring through computer vision techniques. The dataset is annotated with 12 keypoints on the cow’s body, enabling precise tracking of body movements and posture. It is structured in the COCO format, making it compatible with popular deep learning models like YOLOv8, OpenPose, and others designed for object detection and keypoint estimation tasks.

Applications:

This dataset is ideal for agricultural tech solutions, veterinary care, and animal behavior research. It can be used in various use cases such as health monitoring, activity tracking, and early disease detection in cattle. Accurate pose estimation can also assist in optimizing livestock management by understanding animal movement patterns and detecting anomalies in their gait or behavior.

Download Dataset

Keypoint Annotations:

The dataset includes the following 12 keypoints, strategically marked to represent significant anatomical features of cows:

Nose: Essential for head orientation and overall movement tracking.

Right Eye: Helps in head pose estimation.

Left Eye: Complements the right eye for accurate head direction.

Neck (side): Marks the side of the neck, key for understanding head and body coordination.

Left Front Hoof: Tracks the front left leg movement.

Right Front Hoof: Tracks the front right leg movement.

Left Back Hoof: Important for understanding rear leg motion.

Right Back Hoof: Completes the leg movement tracking for both sides.

Backbone (side): Vital for posture and overall body orientation analysis.

Tail Root: Used for tracking tail movements and posture shifts.

Backpose Center (near tail’s midpoint): Marks the midpoint of the back, crucial for body stability and movement analysis.

Stomach (center of side pose): Helps in identifying body alignment and weight distribution.

Dataset Format:

The data is structure in the COCO format, with annotations that include image coordinates for each keypoint. This format is highly suitable for integration into popular deep learning frameworks. Additionally, the dataset includes metadata like bounding boxes, image sizes, and segmentation masks to provide detail context for each cow in an image.

Compatibility:

This dataset is optimize for use with cutting-edge pose estimation models such as YOLOv8 and other keypoint detection models like DeepLabCut and HRNet, enabling efficient training and inference for cow pose tracking. It can be seamlessly integrate into existing machine learning pipelines for both real-time and post-processed analysis.

This dataset is sourced from Kaggle.

This hand recognition dataset comprises a comprehensive collection of hand images from 65 individuals, including both left and right hands, annotated with YOLOv8 formatting.The dataset encompasses 17 distinct classes, denoted as L-L1 to L-L9 for the left hand and R-R1 to R-R8 for the right hand. These classes capture various hand gestures and poses.These images were captured using a standard mobile phone camera, offering a diverse set of images with varying angles and backgrounds. In total, the dataset comprises 405 high-quality images, with 222 representing left hands and 183 representing right hands. The left hand classes are distributed as follows: L-L1 (62 images), L-L2 (56 images), L-L3 (44 images), L-L4 (29 images), L-L5 (14 images), L-L6 (8 images), L-L7 (4 images), L-L8 (2 images), and L-L9 (3 images). Similarly, the right hand classes are distributed as R-R1 (53 images), R-R2 (48 images), R-R3 (38 images), R-R4 (24 images), R-R5 (14 images), R-R6 (4 images), R-R7 (1 image), and R-R8 (1 image).We welcome the machine vision research community to utilise and build upon this dataset to advance the field of hand recognition and its applications.

Mammoset Segmentation And Pose

## Overview

Mammoset Segmentation And Pose is a dataset for instance segmentation tasks - it contains Marmoset annotations for 5,315 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).

Ap values of different methods on the three datasets. AP values include four indicators: AP@50, AP@75, AP@M, and AP@L.

Worm Pose Estimation Segmentation

## Overview

Worm Pose Estimation Segmentation is a dataset for instance segmentation tasks - it contains Worms annotations for 2,040 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).

Shirt Pose Segmentation

## Overview

Shirt Pose Segmentation is a dataset for instance segmentation tasks - it contains Clothe annotations for 368 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).

FPS values of different methods on the three datasets.

AP values of three methods on the three datasets, including four indicators: AP @50, AP @75, AP @M, and AP @L. Experiment one is the baseline model without adding other modules, experiment two is the baseline model with the LKA module added, and experiment three is the baseline model with the SimDLKA module added.

Standing_Pose

## Overview

Standing_Pose is a dataset for instance segmentation tasks - it contains Sitting Pose annotations for 391 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 Insect Hotel Dataset is a photorealistic synthetic dataset designed for pose estimation and panoptic segmentation tasks. It contains 20,000 synthetically generated photorealistic images of objects used in a human-robot collaborative assembly scenario. The dataset was created using NViSII. It also includes the 3D object meshes and YOLOv8 model weights.

This dataset accompanies the following upcoming publication:

Juan Carlos Saborío, Marc Vinci, Oscar Lima, Sebastian Stock, Lennart Niecksch, Martin Günther, Joachim Hertzberg, and Martin Atzmüller (2025): “Uncertainty-Resilient Active Intention Recognition for Robotic Assistants”. (submitted)

File Structure

To facilitate easier downloading, the dataset has been split into 10 parts. Each part is further divided into three archives:

• RGB images + JSON annotations

• Depth images (optional)

• Instance segmentation images (optional)

To use the complete dataset, download all 30 archives and extract them into the same root folder, so that the depth and segmentation images are located alongside the corresponding RGB and JSON files.

The dataset format (coordinate systems, conventions, and JSON fields) follows the structure documented here.

Contents of the archives:

.
├── insect_hotel_20k_00.tgz # RGB images + annotation JSON files
│ └── 00 # archive index (00...09)
│ ├── 0000 # scene index (0000...0099), each with 20 images in front of the same background
│ │ ├── 00000.jpg # RGB image
│ │ ├── 00000.json # pose, bounding boxes, etc.
│ │ ├── [...]
│ │ ├── 00019.jpg
│ │ ├── 00019.json
│ │ ├── _camera_settings.json # camera intrinsics
│ │ └── _object_settings.json # object metadata
│ ├── [...]
│ └── 0099
├── insect_hotel_20k_00.depth.tgz # Depth images (.exr)
│ └── 00
│ └── 0000
│ ├── 00000.depth.exr
│ └── [...]
├── insect_hotel_20k_00.seg.tgz # Instance segmentation images (.exr)
│ └── 00
│ └── 0000
│ ├── 00000.seg.exr
│ └── [...]
└── insect_hotel_20k_01.tgz
└── 01
└── 0000
├── 00000.jpg
├── 00000.json
└── [...]

3D Meshes

The file meshes.tgz contains all object meshes used for training.

Insect hotel parts (used in the assembly task)

• bright_green_part

• dark_green_part

• magenta_part

• purple_part

• red_part

• yellow_part

Other objects

• klt — “Kleinladungsträger” (small load carrier / blue box)

• multimeter

• power_drill_with_grip

• relay

• screwdriver

Additionally, the images include various distractor objects from the Google Scanned Objects (GSO) dataset. The corresponding meshes are not included here but can be obtained directly from the GSO dataset.

YOLOv8 Model

The file yolov8_weights.tgz contains a YOLOv8 model that was trained on a subset of the object classes. The class index mapping is as follows:

0: bright_green_part
1: dark_green_part
2: magenta_part
3: purple_part
4: red_part
5: yellow_part
6: klt

Helper utilities for converting the DOPE format to YOLO format, along with scripts for training, inference, and visualization, are available via:

git clone -b insect_hotel https://github.com/DFKI-NI/yolo8_keypoint_utils.git

ABB_Pose_Estimation_Dataset

## Overview

ABB_Pose_Estimation_Dataset is a dataset for instance segmentation tasks - it contains Group2 annotations for 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).

This repository contains the Health&Gait dataset, the first that enables gait analysis using visual information without specific sensors, relying solely on cameras. The dataset includes multimodal features extracted from videos, and gait parameters and anthropometric measurements from each participant. This dataset is intended for use in health, sports and gait analysis research.

Health&Gait consists of 1,564 videos of 398 participants walking in a controlled closed environment, where each video has associated the following information:

• 2D pose estimation of their joints by AlphaPose (JSON format files).
• Semantic segmentation by DensePose (PNG images).
• Optical flow by TVL1 and GMFlow (PNG images).
• Silhouette by YOLOV8 (JPEG images).

Moreover, for each subject, the following data has been recorded:

• Anthropometric measurements.
• Gait parameters obtained from OptoGait and MuscleLAB.
• Gait parameters estimated from pose information.

Humanintentpose

## Overview

Humanintentpose is a dataset for instance segmentation tasks - it contains Intent annotations for 2,137 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).

Duplo 3.0

## Overview

Duplo 3.0 is a dataset for instance segmentation tasks - it contains Bricks Ss1h annotations for 556 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).

HumanPosition

## Overview

HumanPosition is a dataset for instance segmentation tasks - it contains People Pose annotations for 465 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).

Here are a few use cases for this project:

1. Forest Cleanup and Maintenance: This model could be used by park services or forest maintenance crews to identify areas with abundant fallen sticks, enabling the cleanup process and reducing the risk of forest fires.

2. Robotics & Automation: In a scenario where robots are efficient in picking up smaller objects, robots can be programmed to recognize sticks and gather them in a certain place for disposal or resource utilization, be it in commercial, outdoor, or home environments.

3. Construction Safety: Construction companies could use this model to identify sticks and other similar objects on construction sites that may pose a safety risk, creating a more secure working environment and preventing possible accidents.

4. Outdoor Games Tool: Some outdoor games or sports (like fetch with dogs or outdoor survival challenges) might require finding sticks. This model can be used in apps to aid players to locate sticks more efficiently.

5. Outdoor Wildlife Research: Researchers studying certain species might benefit from identifying areas with more stick/twig availability, as this may influence the habitation patterns of certain animals or insects.

Here are a few use cases for this project:

1. Infrastructure Maintenance: The model can be used by government agencies or private companies to assess the condition of roads, bridges, and buildings in real-time. Regular scans can help detect emerging cracks, and consequently, worrisome structural issues in their early stages - leading to preventive maintenance.

2. Construction Quality Assurance: Construction firms can use the model to check and ensure the integrity of their work. The model can be used to inspect walls, floors, and other structures for cracks that indicate possible construction faults.

3. Safety Inspections: The model can be useful for companies dealing with safety inspections, such as fire departments or safety regulators, to identify cracks in various types of infrastructure like pipelines, chemical plants, or nuclear facilities that may pose accident risks.

4. Geological Study: Geological or seismological researchers can use this model to identify and categorize cracks in geological structures for analysis, potentially aiding in predicting earthquakes or land shifts.

5. Art Restoration: Museums or art restoration firms can use the model to detect and monitor cracks in artwork over time, aiding in the preservation and restoration process.

A real-time stable multi-target tracking method based on the enhanced You Only Look Once-v8 (YOLOv8) and the optimized Simple Online and Realtime Tracking with a Deep association metric (DeepSORT) for real-time stable multi-target tracking (S-YOFEO) is proposed to address the issue of target ID transformation and loss caused by the increase of practical background complexity. The complexity of the real-world context poses a great challenge to multi-target tracking systems. Changes due to weather or lighting conditions, as well as the presence of numerous visually similar objects, can lead to target ID switching and tracking loss, thus affecting the system’s reliability. In addition, the unpredictability of pedestrian movement increases the difficulty of maintaining consistent and accurate tracking. For the purpose of further enhancing the processing capability of small-scale features, a small target detection head is first introduced to the detection layer of YOLOv8 in this paper with the aim of collecting more detailed information by increasing the detection resolution of YOLOv8 to ensure precise and fast detection. Secondly, the Omni-Scale Network (OSNet) feature extraction network is implemented to enable accurate and efficient fusion of the extracted complex and comparable feature information, taking into account the restricted computational power of DeepSORT’s original feature extraction network. Again, addressing the limitations of traditional Kalman filtering in nonlinear motion trajectory prediction, a novel adaptive forgetting Kalman filter algorithm (FSA) is devised to enhance the precision of model prediction and the effectiveness of parameter updates to adjust to the uncertain movement speed and trajectory of pedestrians in real scenarios. Following that, an accurate and stable association matching process is obtained by substituting Efficient-Intersection over Union (EIOU) for Complete-Intersection over Union (CIOU) in DeepSORT to boost the convergence speed and matching effect during association matching. Last but not least, One-Shot Aggregation (OSA) is presented as the trajectory feature extractor to deal with the various noise interferences in complex scenes. OSA is highly sensitive to information of different scales, and its one-time aggregation property substantially decreases the computational overhead of the model. According to the trial results, S-YOFEO has made some developments as its precision can reach 78.2% and its speed can reach 56.0 frames per second (FPS), which fully meets the demand for efficient and accurate tracking in actual complex traffic environments. Through this significant increase in performance, S-YOFEO can contribute to the development of more reliable and efficient tracking systems, which will have a profound impact on a wide range of industries and promote intelligent transformation and upgrading.