TrackForward: Faster Frame-by-Frame Video Labeling

Plainsight streamlines the full computer vision lifecycle, empowering users of all experience levels and businesses of all types to train and deploy models for optimizing processes and answering industry-wide questions. Providing businesses with production-ready computer vision starts with making visual data faster and easier to label and jump-start model training.

What Is TrackForward? 

TrackForward is a Plainsight AI-powered labeling feature that can dramatically reduce the time and effort required for labeling video data. Using AI, TrackForward analyzes the labels in one frame of a video to predictively label objects in subsequent frames. By labeling an object with either a Bounding Box or Polygon and selecting the TrackForward tool, Plainsight users can quickly generate labels automatically for desired objects across entire videos. TrackForward successfully labels images even as they move from frame-to-frame, making it useful for monitoring objects in motion, such as vehicles traveling through intersections, shoppers entering stores, and items in the production processes. 

More Label Accelerators

TrackForward is just one of several Plainsight labeling features that accelerate dataset creation by 20X. These tools make data labeling faster and more efficient – often through the use of AI. Plainsight offers the flexible choice among common label types such as, Rectangles, Polygons, Point, Feature Points, Text, Class, or Multi-Class. Accelerated labeling features include:

  • CopyForward: Though it doesn’t involve AI, this feature reduces the tedium of repetitive labeling to a considerable degree. CopyForward automatically labels objects that remain stationary across multiple frames, eliminating the need to label the same object over and over again. It’s useful, for example, in instances where dwell time tracking is needed –how long a person or object remains in a specific location or within a video frame.
  • SmartPoly: Bounding boxes are a useful type of label, but many times for instance and semantic segmentation or to define important image and object features, users need labels that adhere to the outlines of relevant objects. SmartPoly eliminates the need for repetitive clicking by automatically transforming bounding boxes into accurate polygon labels.
  • AutoLabel: Using predictions from a machine learning model, AutoLabel can generate rectangle and polygon labels for and automatically apply them to images or videos. Labeling can be done using pre-trained models from the COCO dataset, a large dataset of common objects. Or, AutoLabel can be used with the Rectangle and Polygon label types and use a custom model to automatically customize object labeling.

Get Started Today

Register for a free Plainsight On-Demand account today and start labeling your images. All users can create free, unlimited labels withTrackForward and receive a $100 credit to spend on pay-as-you-go model training and deployment features. 

Looking to address complex computer vision challenges with dedicated support from Plainsight’s team? Schedule a demo to learn more about how enterprise solutions can help your business realize the full value of your visual data.

More Plainsight Blog Posts:

SmartML: Train Vision AI Models with One Click

SmartML: Train Vision AI Models with One Click

SmartML is Plainsight’s proprietary model training toolset. It is at the heart of Plainsight’s promise to make vision AI’s impressive capabilities more accessible to users of all experience levels and enterprises of all types. Thanks to SmartML, Plainsight users can use their labeled datasets to train vision AI models without the need for a single line of code.

Computer Vision and Retail’s Digital Transformation

Computer Vision and Retail’s Digital Transformation

When it comes to digital transformation, retailers are no longer asking, “What if?” They’re saying the time is now. For the retail industry in particular, integrating vision AI applications into traditional store operations can open up a world of fresh insights that empower better decision making.

Deep Learning Architecture for Skin Cancer Segmentation

Deep Learning Architecture for Skin Cancer Segmentation

In a recent skin cancer research study, Dr. Bülent Bayram and his team at Yildiz Technical University, Department of Geomatics in Istanbul, Turkey, used our vision AI platform to perform image segmentation for early detection and analysis of skin cancer.