SentiSight.ai vs PractiCal AR

The SentiSight.ai mobile app enables users to make image classification and object detection predictions using images from their phones. This is an accompanying app to the SentiSight.ai image labeling and recognition web platform. On the app, users can immediately make predictions using a range of ready-to-use pre-trained models: General Classification—. Use the General Classification pre-trained model to identify the content of your image. Classification is one of the primary uses of image recognition AI General Object Detection—Using the pre-trained general object detection model allows users to identify what objects are in your image, along with the location of the object within the image. Places Classification— Use the Places Classification pre-trained model to identify the place depicted in your image. The model provides a predicted score percentage. NSFW Classification—The NSFW classification model can be used to detect whether images contain nudity or not. The model provides a prediction of whether the image is safe or unsafe, by way of a predicted score percentage. Optical Character Recognition—The optical character recognition (OCR) pre-trained model can be used to detect and identify text within your image, and is supported for a wide variety of languages. Pose Estimation—The pose estimation model can be used to detect the poses of people in the image. It detects 15 joints and key points of the human body. Image Similarity Search—an image similarity search model is used to find visually similar images to one that is uploaded. The retrieved images are sorted by their similarity score. With the SentiSight.ai mobile app, users can also make predictions using the custom models that have been trained using the SentiSight.ai web interface. The app uses the same login credentials as the web version of SentiSight.ai. The app does not currently support the training of new models itself, but the mobile app can be used to upload images to your projects that can be later used for training custom models. The SentiSight.ai mobile app and web platform are developed by Neurotechnology. Neurotechnology is a developer of high-precision algorithms and software based on deep neural networks and other AI-related technologies. For more information about the company, please, visit the company’s website https://neurotechnology.com/

PractiCal AR helps FIRST® Robotics Competition teams calibrate and check practice field AprilTag placement using augmented reality and AprilTag detection. Use your device to detect AprilTags, build a field map, compare detected tag positions against an ideal field layout, and export the results for use in other tools. APRILTAG DETECTION Detect AprilTags in real time using your device’s camera and ARKit. Each detected tag is shown in the AR view with its 3D pose so you can see position and orientation while scanning . FIELD CALIBRATION Scan your practice field AprilTags and compare their detected positions against the official field layout. CALIBRATION REPORT View a table showing Ideal vs. Actual tag placement, then export the report as CSV, JSON, or Markdown. 3D FIELD MODEL View this season’s simplified field CAD model in a 3D viewer, or place it in your environment using AR. REVIEW MODE Review saved calibration data in the app without needing to be in front of the field. EXPORT YOUR DATA Export your field calibration data in WPILib JSON format and Limelight JSON format. AR GAME Use your a practice or competition field to play four AR mini-games — launch fuel balls at the hub targets on the field and track your scores. Play the games from the stands, no need to do any calibration of the field, other than using PractiCal to detect and pin a single tag, all from the stands. The included games are: - Quick Shot — Score as many as you can in 20 seconds - Hot Shot — Build the longest streak without missing - Long Shot — Go for distance — how far can you score from? - Top Shot — How good is your accuracy rate? The game features: - Real-time ball physics with adjustable launch speed and angle - Aim with your camera. NOTE: The game and scores are specific to REBUILT and will be removed at the beginning of the 2027 FRC season. Leaderboard participation is optional and only displays user provided 3 letters and FRC team #. Useful settings for calibrating tags from a distance is in Settings -> Calibration * Tap to recenter all tags * Snap tags to vertical The higher the resolutions and lower the decimation, the farther you can be. You can also detect closer and walk away, ARKit will know how fr you've gone. PractiCal AR is free, with no in-app purchases or ads. Built by an FRC mentor for the FRC community. Requires a device with ARKit support and a camera. Works best in a well-lit environment with clearly visible AprilTags. LEGAL & TRADEMARKS This app is an independent educational project developed by Eagle Evolution, FRC Team #3322. The 3D field models included are simplified derivative works created for reference purposes, based on the official 2026 FIRST® Robotics Competition season, REBUILT™ presented by Haas. FIRST®, the FIRST® logo, FIRST® Robotics Competition, and REBUILT™ are trademarks of For Inspiration and Recognition of Science and Technology (FIRST®), which is not overseeing, involved with, or responsible for this activity, product, or service. All original CAD data and field technical information are the sole property of FIRST®. Any reproduction of the original CAD, in part or as a whole, without written permission from FIRST® is prohibited. AprilTag detection is powered by the AprilTag 3 library, licensed under the BSD 2-Clause License.