Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
Here are a few use cases for this project:
Digital Inventory Management: The Segmentation computer vision model could be used to identify the specific labels (QR Codes, Barcodes, or digits) on boxes within a warehouse. When boxes are stacked in different orientations, this identification can ensure optimal tracking and warehouse management.
Parcel Sorting in Logistic Companies: The model could be employed in automatic parcel sorting systems. It can recognize different types of coded information, aiding in the process of classifying and sorting packages more efficiently, improving overall logistics operations.
Retail Checkout Systems: A use case can be found in retail checkout systems where the model can help in real-time identification and processing of product codes, be it barcodes or QR codes, making the checkout process quicker and more efficient.
Automated Library Systems: The model can be used to identify the labels on books in various orientations to update the library's database and streamline book tracking, lending, and inventory operations.
Mass Transport Systems: In transport hubs or stations (airports, train stations), this kind of model can be used to identify and sort luggage or cargo based on tags, speeding up the loading/unloading process and reducing errors.
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
Here are a few use cases for this project:
Urban Planning and Development: Utilizing the "Buildings Instance Segmentation" model to analyze aerial images of a city, urban planners can identify different types of buildings and their distribution to make informed decisions about zoning, infrastructure, and future developments.
Damage Assessment and Emergency Response: In the aftermath of natural disasters, the model can be used to analyze aerial images to quickly identify damaged or destroyed buildings, helping emergency responders prioritize rescue efforts and allocate resources more efficiently.
Real Estate Market Analysis: Real estate professionals can use the model to analyze aerial views of neighborhoods, identifying different types of buildings and their locations to offer better insights into neighborhood characteristics and trends for potential property buyers.
Energy Efficiency and Environmental Impact Analysis: By identifying different building classes and their distribution, researchers can evaluate energy consumption patterns and develop strategies for improving energy efficiency and reducing the environmental impact in urban areas.
Historical Preservation and Cultural Heritage: The model can be employed to identify and track the presence of culturally significant or historically important buildings for preservation efforts, ensuring their protection and integration into urban development plans.
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
Here are a few use cases for this project:
Infrastructure Maintenance: The segmentation model can be used to identify and classify different types of cracks in public infrastructure like buildings, bridges, roads, and railways. This could assist in early detection and maintenance, preventing costly repairs or accidents.
Geology and Environmental Studies: The model could be used to analyze cracks in the ice in the polar regions, assisting in climate research by monitoring the melting rate of glaciers and its impact on sea levels.
Automotive Industry: The model can be used in the analysis of wear and tear in vehicles, particularly in tires where cracks could lead to potentially dangerous blowouts.
Aerospace Industry: The model can be used to detect cracks in aircraft fuselage or wings during routine maintenance checks. Early detection will reduce the risk of catastrophic failure during flights.
Energy Industry: In wind turbine maintenance, the model could be used to detect cracks in turbine blades. Early detection can prevent failures, prolonging the lifespan of the turbines and increasing efficiency.
Recent advances in language-image pre-training has witnessed the emerging field of building transferable systems that can effortlessly adapt to a wide range of computer vision & multimodal tasks in the wild. This also poses a challenge to evaluate the transferability of these models due to the lack of easy-to-use evaluation toolkits and public benchmarks. "Segmentation in the Wild (SegInW)" Challenge is a part of X-Decoder, that proposed a new benchmark to evaluate the transfer ability of pre-trained vision models. This benchmark presents a diverse set of downstream segmentation datasets, measuring the ability of pre-training models on both the segmentation accuracy and their transfer efficiency in a new task, in terms of training examples and trainable parameters. This SegInW Challenge consists of 25 free public Segmentation datasets, crowd-sourced on roboflow.com. For more details about the challenge submission format, please refer to X-Decoder for SGinW.
CC0 1.0 Universal Public Domain Dedicationhttps://creativecommons.org/publicdomain/zero/1.0/
License information was derived automatically
The material segmentation dataset comprises 3817 images gathered from the Virginia Department of Transportation (VDOT) Bridge Inspection Reports. There were four classes of material in the dataset: [concrete, steel, metal decking, and background]. The data was randomly sorted into training and testing using a custom script. 10% percent were reserved as the test set, and 90% were used as the training set. Therefore, there were 381 images in the test set and 3436 images in the training set. The original and the rescaled images used for training have been included. The images were resized to 512x512 for training and testing the DeeplabV3+ model. After training with the DeeplabV3+ model (DOI: 10.7294/16628620), we were able to achieve an F1-score of 94.2%. Details of the dataset, training process, and code can be referenced by reading the associated journal article. The GitHub repository information may be found in the journal article.If you are using the dataset in your work, please include both the journal article and the dataset citation.
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
The dataset includes 458 hi-res images together with their alpha maps (BW) indicating the crack presence. The ground truth for semantic segmentation has two classes to conduct binary pixelwise classification. The photos are captured in various buildings located in Middle East Technical University.
You can access a larger dataset containing images with 227x227 px dimensions for classification which are produced from this dataset from http://dx.doi.org/10.17632/5y9wdsg2zt.1 .
CC0 1.0 Universal Public Domain Dedicationhttps://creativecommons.org/publicdomain/zero/1.0/
License information was derived automatically
Unsupervised Learning Online Retail Customer Segmentation
Attribution-NonCommercial 4.0 (CC BY-NC 4.0)https://creativecommons.org/licenses/by-nc/4.0/
License information was derived automatically
Video object segmentation dataset than contains 150 video sequences. Each sequence contains multiple objects and their high quality segmentation mask in each of the frames.
The Medical Segmentation Decathlon is a collection of medical image segmentation datasets. It contains a total of 2,633 three-dimensional images collected across multiple anatomies of interest, multiple modalities and multiple sources. Specifically, it contains data for the following body organs or parts: Brain, Heart, Liver, Hippocampus, Prostate, Lung, Pancreas, Hepatic Vessel, Spleen and Colon.
CC0 1.0 Universal Public Domain Dedicationhttps://creativecommons.org/publicdomain/zero/1.0/
License information was derived automatically
The data was collected from the Virginia Department of Transportation (VDOT) Bridge Inspection Reports. The data was semantically annotated following the corrosion condition state guidelines stated in the American Association of State Highway and Transportation Officials (AASHTO) and Bridge Inspector's Reference Manual (BIRM). There were four corrosion class categories: [good, fair, poor, severe]. The dataset consisted of 440 finely annotated images and was randomly split into 396 training images and 44 testing images. The images were resized to 512x512 for training and testing the DeeplabV3+ model. The original and resized images are included. After training with the DeeplabV3+ model (DOI: 10.7294/16628668), we were able to receive an F1 score of 86.67. More details of the training, the results, the dataset, and the code may be referenced in the journal article. The GitHub repository information may be found in the journal article.If you are using the dataset in your work, please include both the journal article and the dataset citation.
MIT Licensehttps://opensource.org/licenses/MIT
License information was derived automatically
Collection of rust segmentation images. Sources include:
https://universe.roboflow.com/faisal-hazry-orm7q/yolov8corrosion
https://spdx.org/licenses/https://spdx.org/licenses/
Person Segmentation is a dataset for a semantic segmentation task. Possible applications of the dataset could be in the surveillance industry. The dataset consists of 21011 images with 21011 labeled objects belonging to 1 single class (person)
Attribution-NonCommercial-NoDerivs 4.0 (CC BY-NC-ND 4.0)https://creativecommons.org/licenses/by-nc-nd/4.0/
License information was derived automatically
This dataset comprises a collection of images captured through DVRs (Digital Video Recorders) showcasing roads. Each image is accompanied by segmentation masks demarcating different entities (road surface, cars, road signs, marking and background) within the scene.
The dataset can be utilized for enhancing computer vision algorithms involved in road surveillance, navigation, and intelligent transportation systemsand and in autonomous driving systems.
https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F12421376%2Fb0789a0ec8075d9c7abdb0aa9faced59%2FFrame%2012.png?generation=1694606364403023&alt=media" alt="">
Each image from images
folder is accompanied by an XML-annotation in the annotations.xml
file indicating the coordinates of the polygons and labels . For each point, the x and y coordinates are provided.
https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F12421376%2Fa74a4214f4dd89a35527ef008abfc151%2Fcarbon.png?generation=1694608637609153&alt=media" alt="">
keywords: road surface, road scene, off-road, vehicle segmentation dataset, semantic segmentation for self driving cars, self driving cars dataset, semantic segmentation for autonomous driving, car segmentation dataset, car dataset, car images, car parts segmentation, self-driving cars deep learning, cctv, image dataset, image classification, semantic segmentation
https://www.kaggle.com/datasets/intelecai/car-segmentationhttps://www.kaggle.com/datasets/intelecai/car-segmentation
Car Segmentation dataset encompasses 211 car side view images, meticulously annotated into four distinct classes: car, wheel, lights, and window. The dataset creation process involved a comprehensive approach, including image gathering through various methods and detailed mask annotation using VoTT, ultimately culminating in a valuable resource for training and developing object recognition models. For those interested in utilizing the dataset without manual annotation, a pre-annotated dataset has been thoughtfully provided by the creator for use in training models.
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
Here are a few use cases for this project:
Agricultural Monitoring: The chili segmentation model can be used in agriculture for monitoring and analyzing chili plant health, enabling farmers to track the growth of leaves and fruit-chilies, and make data-driven decisions regarding crop management, fertilization, and pesticide application.
Precision Harvesting: The model can be incorporated into automated harvesting systems, helping to differentiate between mature fruit-chilies and leaves or identify ripe fruit only. This ensures a more efficient and selective harvest, reducing labor costs and contributing to sustainable farming practices.
Sorting & Grading: Post-harvest, the chili segmentation model can be used by food processing industries to sort and grade chili peppers based on visual features such as color and size. This can facilitate better quality control and help meet specific customer or market demands.
Pests and Disease Detection: The chili segmentation model can help identify abnormalities in leaf-chili and fruit-chili growth patterns, which could indicate the presence of pests or diseases. Early detection and targeted treatment can lead to a reduction in crop loss and higher yields.
Food Industry Applications: The model can be used for managing inventory and quality control in supermarkets, restaurants, and other food-related businesses. By identifying and categorizing different types of chili peppers, it can enable more efficient stock management and ensure the quality of products for customers.
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
Here are a few use cases for this project:
Traffic Management: This model could be used by traffic management authorities to analyze current road patterns and help optimize traffic flow. They could identify roads and their types in different areas, which would be crucial for implementing traffic signals, determining road capacities and planning traffic routes.
Autonomous Vehicles: Autonomous vehicles use computer vision technology constantly, key among them being the recognition of paths and roadways. With this image segmentation model, self-driving cars could accurately identify left roads, right roads, and U-turn roads, enhancing their navigation capacities and safety.
City Planning: Urban and city planners could use this technology to assess the infrastructure of both existing and developing cities. By identifying the types and layouts of roads, they can make better decisions about zoning, infrastructure development and renovation.
Virtual Map Development: Companies like Google, Apple, and Microsoft, which provide map services, could leverage the model to provide more detailed and accurate road information on their maps. This can improve user navigation experience.
Traffic Simulation Games: Game developers could use this image segmentation model in the development of hyper-realistic traffic or city simulation games. It could be used to create virtual environments with realistic road structures.
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
Here are a few use cases for this project:
Aircraft Maintenance and Safety Checks: This computer vision model could be used for conducting routine inspections of aircrafts for potential damages such as dents, scratches, or missing bolts. It could help eliminate human error and allow for much more detailed and accurate assessments.
Auto Repair and Inspection: The model could come in handy in auto repair shops to automate the process of identifying specific car damages. It can be employed for both pre and post-service inspection, ensuring that all missing bolts are replaced and dents repaired.
Quality Assurance in Painting Industries: Industries that deal with painting can apply this model to ensure quality in their painting process. The vision model can detect any paint-off from the object, notifying potential flaws that need correcting.
Automated Industrial Inspection: This model could be utilized in various industries during production, ensuring machines, and equipment are properly installed and not damaged. This could help mitigate potential accidents or operational disruptions in the manufacturing line.
Railway and Infrastructure Maintenance: The model can have its use in maintaining the safety of bridges, railways, and other constructed infrastructure by identifying any cracks, scratches or wear. This preemptive measure might prevent potential catastrophes caused by such infrastructure failures.
Attribution 4.0 (CC BY 4.0)https://creativecommons.org/licenses/by/4.0/
License information was derived automatically
Here are a few use cases for this project:
'Mask Compliance Monitoring': By using the Lips Segmentation model, businesses can track whether their employees are appropriately wearing masks in the workplace, potentially feeding into public health initiatives for pandemic control.
'Cosmetic Testing and Augmentation': The system could be used in beauty apps or virtual platforms which allow users to experiment with different shades of lipstick or other lip cosmetics. It can display accurate virtual results on the user's lips, taking into account dynamic elements such as wrinkles or hair around the lip area.
'Virtual Reality and Game Development': This model can help designers create more realistic characters by accurately mapping and detecting lip features, including the complex effects of aging, like wrinkles. It can be further used to improve lip-syncing of characters according to the dialogues and expressions.
'Medical Diagnostics Aid': The 'Lips Segmentation' model can be used in the medical field for diagnostics and treatment planning for cases involving oral diseases, facial reconstructions, or maxillofacial surgeries.
'Video Conferencing Enhancement': For better video chat conferencing experiences, the model could provide real-time filters, like blurring the background but keeping the user's face, namely the lips, in focus. This would be of interest in professional or social virtual meetings.
Image data described by high-level numeric-valued attributes, 7 classes# Source: Creators: Vision Group, University of Massachusetts Donor: Vision Group (Carla Brodley, brodley '@' cs.umass.edu)
The instances were drawn randomly from a database of 7 outdoor images. The images were handsegmented to create a classification for every pixel. Each instance is a 3x3 region.
Please refer to the Machine Learning Repository's citation policy. [1] Papers were automatically harvested and associated with this data set, in collaborationwith Rexa.info
Source: http://archive.ics.uci.edu/ml/datasets/Image+Segmentation
CC0 1.0 Universal Public Domain Dedicationhttps://creativecommons.org/publicdomain/zero/1.0/
License information was derived automatically
This is an Instance Segmentation project for visualizing detected cracks on concrete. This dataset is usable for those doing transportation and public safety studies, creating self-driving car models, or testing out computer vision models for fun. * Featured Transportation Projects
Check out this example guide from Augmented Startups to see the model in action and learn how the dataset came together: https://medium.com/augmented-startups/yolov7-segmentation-on-crack-using-roboflow-dataset-f13ae81b9958
https://miro.medium.com/max/720/1*BvZk2Sck6cucZ416zgbzMg.jpeg" alt="Inferred Image from YOLOv7">
The Medical Segmentation Decathlon is a collection of medical image segmentation datasets. It contains a total of 2,633 three-dimensional images collected across multiple anatomies of interest, multiple modalities and multiple sources. Specifically, it contains data for the following body organs or parts: Brain, Heart, Liver, Hippocampus, Prostate, Lung, Pancreas, Hepatic Vessel, Spleen and Colon.