Overview

We have captured and annotated photos of the popular board game, Boggle. Images are predominantly from 4x4 Boggle with about 30 images from Big Boggle (5x5). - 357 images - 7110 annotated letter cubes

These images are released for you to use in training your machine learning models.

Use Cases

We used this dataset to create BoardBoss, an augmented reality board game helper app. You can download BoardBoss in the App Store for free to see the end result! :fa-spacer: https://ph-files.imgix.net/468fa673-26c4-4458-8957-369cb72addcd?auto=format&auto=compress&codec=mozjpeg&cs=strip" alt="BoardBoss"> :fa-spacer: The model trained from this dataset was paired with some heuristics to recreate the board state and overlay it with an AR representation. We then used a traditional recursive backtracking algorithm to find and show the best words on the board.

Using this Dataset

We're releasing the data as public domain. Feel free to use it for any purpose. It's not required to provide attribution, but it'd be nice! :fal-smile-wink:

About Roboflow

Roboflow makes managing, preprocessing, augmenting, and versioning datasets for computer vision seamless.

Developers reduce 50% of their boilerplate code when using Roboflow's workflow, save training time, and increase model reproducibility. :fa-spacer:

Overview

This dataset contains 8,992 images of Uno cards and 26,976 labeled examples on various textured backgrounds.

This dataset was collected, processed, and released by Roboflow user Adam Crawshaw, released with a modified MIT license: https://firstdonoharm.dev/

https://i.imgur.com/P8jIKjb.jpg" alt="Image example">

Use Cases

Adam used this dataset to create an auto-scoring Uno application:

Getting Started

Fork or download this dataset and follow our How to train state of the art object detector YOLOv4 for more.

Annotation Guide

See here for how to use the CVAT annotation tool.

About Roboflow

Roboflow makes managing, preprocessing, augmenting, and versioning datasets for computer vision seamless. :fa-spacer: Developers reduce 50% of their boilerplate code when using Roboflow's workflow, save training time, and increase model reproducibility. :fa-spacer:

Overview

The Insect_Detect_detection dataset contains images of an artifical flower platform with different insects sitting on it or flying above it. All images were automatically recorded with the Insect Detect DIY camera trap, a hardware combination of the Luxonis OAK-1, Raspberry Pi Zero 2 W and PiJuice Zero pHAT for automated insect monitoring.

Classes

The following object classes were annotated in this dataset:

• wasp (mostly Vespula sp.)
• hbee (Apis mellifera)
• fly (mostly Brachycera)
• hovfly (various Syrphidae, e.g. Eupeodes corollae, Episyrphus balteatus, Scaeva pyrastri)
• other (all Arthropods with insufficient occurences, e.g. various Hymenoptera, true bugs, beetles)
• shadow (shadows of the recorded insects)

View the Health Check for more info on class balance.

Versions

Different dataset versions are available for export: - v7 insect_detect_320_1class - squashed to square (aspect ratio 1:1) - downscaled to 320x320 pixel - all classes merged into one class (insect) - use this version to train a YOLO insect detection model for the DIY camera trap - v4 insect_detect_416_1class - squashed to square (aspect ratio 1:1) - downscaled to 416x416 pixel - all classes merged into one class (insect) - slower inference speed compared to 320x320 px model input - v5 insect_detect_raw_4K - original images in 4K resolution (3840x2160 pixel) - v6 insect_detect_bbox_crop - contains the cropped bounding boxes and was used to generate the Insect_Detect_classification dataset

Deployment

You can use this dataset as starting point to train your own insect detection models. Take a look at the YOLO detection model training instructions for more information.

To deploy the YOLO object detection models for automated insect monitoring, check out the provided Python scripts, available in the insect-detect GitHub repo. More details about the processing pipeline can be found in the Insect Detect Docs.

License

This dataset is licensed under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0)

Citation

If you use this dataset, please cite our paper:

Sittinger M, Uhler J, Pink M, Herz A (2024) Insect detect: An open-source DIY camera trap for automated insect monitoring. PLoS ONE 19(4): e0295474. https://doi.org/10.1371/journal.pone.0295474

Here are a few use cases for this project:

1. Shooting Accuracy Analysis: The "project" model can be used by shooting instructors and trainees to evaluate their shooting precision and accuracy based on the placement of bullet holes on a target. This use could apply to military training, police force training, and individual gun owners who practice at shooting ranges.

2. Sports Competition Scoring: It can be used in sports shooting competitions to automatically score participants based on bullet holes' relative positions on the target. This would enable a more efficient, unbiased, and accurate scoring process.

3. Forensic Investigation: The model may be employed by forensic experts to analyze gunshot patterns or simulate specific shooting scenarios, facilitating their understanding of various criminal cases involving firearms.

4. Ballistics Research: The computer vision model can be useful for ballistics researchers testing the performance of different ammunition or firearm types. By recognizing and categorizing bullet holes, the model can provide valuable data regarding bullet trajectory, speed, and impact.

5. Automatic Damage Assessment: In military or defense applications, the model could be used to automatically assess damage in shooting tests on different types of armor or materials. Comparing the placement and number of holes could give insights into the effectiveness of the armor or material under testing.

This dataset contains images of an artifical flower platform with different insects sitting on it or flying above it. All images were automatically recorded with the Insect Detect DIY camera trap, a hardware combination of the Luxonis OAK-1, Raspberry Pi Zero 2 W and PiJuice Zero pHAT for automated insect monitoring (bioRxiv preprint).

Classes

The following object classes were annotated in this dataset:

• wasp (mostly Vespula sp.)
• hbee (Apis mellifera)
• fly (mostly Brachycera)
• hovfly (various Syrphidae, e.g. Episyrphus balteatus)
• other (all Arthropods with insufficient occurences, e.g. various Hymenoptera, true bugs, beetles)
• shadow (shadows of the recorded insects)

View the Health Check for more info on class balance.

Versions

• v4 insect_detect_416_1class
  • squashed to square (aspect ratio 1:1)
  • downscaled to 416x416 pixel
  • all classes merged into one class ("insect")
• v5 insect_detect_raw_4K
  • original images in 4K resolution (3840x2160 pixel)
• v7 insect_detect_320_1class
  • squashed to square (aspect ratio 1:1)
  • downscaled to 320x320 pixel
  • all classes merged into one class ("insect")

Deployment

You can use this dataset as starting point to train your own insect detection models. Check the model training instructions for more information.

Open source Python scripts to deploy the trained models can be found at the insect-detect GitHub repo.

Here are a few use cases for this project:

1. Inventory Management: Retailers can use the "Retail Coolers" model to monitor and manage their inventory by keeping track of stocked and empty spaces within the cooler. This will streamline the process of replenishment, reducing out-of-stock events, and improving overall customer experience.

2. Sales Analysis: Businesses can analyze customers' purchasing behavior using the "Retail Coolers" model to identify fast-moving or slow-moving products within coolers. This information can guide pricing, promotions, and product placement strategies to optimize sales and profit margins.

3. Automated Restocking Alerts: The "Retail Coolers" model can trigger automatic notifications to store staff or delivery partners when it detects empty spaces in the cooler. This will ensure timely restocking, ultimately improving customers' shopping experience and the store's revenue generation.

4. Space Optimization: The "Retail Coolers" model can help retailers optimize the use of cooler spaces by identifying popular products that frequently run out or empty spots. Data-driven insights can guide store layouts and product arrangements to maximize sales and cooler efficiency.

5. Customer Behavior Insights: By analyzing changes in cooler stock over time, businesses can gain insight into customer behavior, preferences, and consumption patterns. This information can guide targeted marketing, sales strategies, and category management to better serve customers and improve overall store performance.

Here are a few use cases for this project:

1. Casino Monitoring: The "Blackjack Cards" model can be used in a surveillance system for casinos to automatically monitor blackjack tables, ensure all rules are followed, and detect any cheating attempts.

2. Blackjack Training Apps: The model can be implemented in a blackjack training application to provide real-time advice to players based upon the cards they have or that have been dealt. It can help players practice and improve their decision-making.

3. Game Development: Developers of virtual card games could benefit from this model by using it to visualize real card game strategy and for developing a more realistic AI opponent.

4. Assistive Technology: For individuals with visual impairments, the model can be used in an app to narrate the cards in play, allowing them to participate in the game.

5. Gambling Research: Researchers studying gambling behavior and strategies can use the model to automatically analyze large amounts of game data accurately and efficiently.

Here are a few use cases for this project:

1. Solar Energy Management: The "PV Station Automation" model could be utilized in the management of solar energy stations. Its ability to identify different classes of buttons, knobs, and slots could assist in automating the control and adjustment of solar panels for optimal energy collection based on weather and time of day.

2. Industrial Automation: This model would be advantageous in industrial settings such as production lines or advanced manufacturing plants. Automated systems could use it to identify operation buttons and slots, optimizing process time and efficiency and reducing potential for human error.

3. ATM Maintenance: Maintenance teams for ATMs or similar heavy machinery could use the model to help automate common tasks like removing or installing specific parts and components based on the button or knob classes recognized by the model.

4. Quality Control Inspection: The model could be used to automatically inspect products and devices for potential defects or errors in assembly. It could check the placement and configuration of buttons, knobs, and slots, alerting human operators if discrepancies are found.

5. Virtual Reality Training: This model could be the base for a virtual reality training tool used to train employees on finding and interacting with specific buttons, knobs, and slots on equipment or machinery, thereby improving training efficiency and effectiveness while reducing the risk of damage to actual equipment.

Here are a few use cases for this project:

1. Waste Classification and Recycling: Industries or municipal bodies could employ this model to automatically sort waste into paper or plastic categories, facilitating more efficient recycling processes.

2. Environmental Protection: Various organizations or government departments might use the model for capturing and monitoring plastic waste in public areas or natural environments, helping to measure pollution levels.

3. Retail and Supermarkets: It could be integrated into self-service checkout systems to automatically identify the difference between plastic and paper packaging, allowing for potential pricing differences or recycling initiatives.

4. Education and Research: Teachers, students, and researchers can use it as a practical tool for exploring machine learning or environmental sciences and promoting the importance of waste separation.

5. Smart Home Integration: The model could be integrated into a smart home system to guide residents in sorting their trash accurately and educating them on recycling.

Here are a few use cases for this project:

1. Fire Emergency Identification: The model can be used in fire detection systems in public and private buildings. When it identifies fire or smoke and the presence of a human, it could trigger alarms and deploy necessary measures such as spraying fire retardant or auto-dialing emergency services.

2. Personal Safety Applications: In smart home systems, the model could provide real-time alerts to homeowners if fire or smoke is detected, especially if there's a human present, indicating potential danger.

3. Forest Fire Surveillance: The model can analyze drone or satellite imagery to identify forest fires and detect if anyone is trapped or injured within the vicinity, helping to strategize the response.

4. Industrial Safety: The model can be used in industries, particularly those with higher fire risk like oil and gas, chemical, and manufacturing, to monitor for fire or smoke and ensure the safety of the workers.

5. Disaster Response Training: The model can be used in simulations to train emergency response teams. For instance, the model would identify fire, smoke, and humans in various scenarios, providing realistic training opportunities for firefighters and rescue teams.

Here are a few use cases for this project:

1. "Wildlife Monitoring and Conservation": This use case involves deploying the model in wildlife reserves or national parks to automatically track and monitor the number of deer in the area. It can help in estimating population sizes for wildlife conservation efforts and detecting any irregularity in their appearance which can indicate a health issue or threat.

2. "Smart Traffic Systems": The model can be utilized by traffic authority systems or autonomous vehicles industry to detect deer crossings on roads, and give real-time alerts to prevent accidents, particularly in rural and semi-rural regions where such occurrences are typical.

3. "Video Surveillance": The computer vision model can be installed in private properties or forests to identify and alert owners about the presence of deer for either preventing property damage or for monitoring purposes in hunting season.

4. "Augmented Reality Hunting Games": In the gaming industry, this model can be used to create more realistic augmented reality hunting games, where players could search for deer in their surroundings.

5. "Educational Purposes": It can be applied in scientific or educational applications for animal recognition tasks, helping students or researchers to identify different deer classes reliably and facilitate their learning or research process.

Here are a few use cases for this project:

1. Agricultural Disease Diagnosis: MB Yellow Mosaic can be utilized by farmers and agricultural specialists to detect and diagnose diseases affecting plant leaves, including yellow mosaic and other similar conditions. Early detection and diagnosis can help them take appropriate measures to treat the plants and prevent the spread of diseases.

2. Plant Health Monitoring: Researchers, botanists, and horticulturists can use the model to monitor plant health in their fields, greenhouses, or botanical gardens. Tracking changes in leaf appearance over time allows them to quickly identify plants under stress or in need of intervention.

3. Biodiversity Studies and Conservation: Ecologists and conservationists can employ MB Yellow Mosaic to identify different plant species based on their leaves, which could improve record-keeping, facilitate biodiversity assessments, and help track species distribution and abundance over time.

4. Environmental Impact Analysis: Governments, environmental organizations, or scientific institutions can use this model to assess the impact of environmental factors, such as air quality or climate change, on vegetation by studying changes in the leaves' appearance, and guide policies for environmental remediation.

5. Smart Gardening: MB Yellow Mosaic can be integrated into gardening apps or IoT devices that assist gardeners in maintaining their plants by automatically detecting any signs of diseases, alerting users to take action, and providing recommendations on the optimal care for their specific plants based on leaf appearances.