Loopy

Image processing and behavioral analysis.

Loopy is revolutionary approach to video analysis. There is no software or updates to install on your PC, no limitations of only one-user-at-a-time, and no expensive and infrequent updates. Loopy provides all you need for behavioral video processing - in your web browser. Loopy supports the following image processing operations

  • single or multiple object tracking in videos
  • analysis of animal motion in videos and between groups
  • scoring / coding of animal behavior
  • annotation of videos for training deep learning object detectors

Apply for an online beta test now

  • Online or on Premise versions available. Depending on the volume of data you expect to process, and how regularly you perform experiments, either version may be the most convenient and economic for you.
  • Centralized. One place to gather all your videos, tracking results, metadata and plots.
  • Video tracking. Track the position on an animal. A wide variety of tracking algorithms work on videos collected in diverse laboratory and field environments.
  • Video scoring. Score animal behavior in any video. Mark events or calculate the duration of behaviors.
  • Concentrate your data in one place. No need for managing and distributing licenses to dedicated lab computers.
  • Flexible plans. Pay only for what you need. Expand your subscription to get access to more features.
  • Streamlined workflow. Predefined processing pipelines get you great data from day one.

Animal Tracking and Detection in Natural Environments Using Deep Learning

Do you need to detect and track animals in a video? Have conventional image processing techniques been insufficient for your needs due to difficult or changing video conditions? Deep-learning approaches have taken computer vision by storm and at loopbio we make them available to you, creating state of the art deep-learning based object detectors customized to your scientific needs.

Conventional image processing requires tedious hand tuning of parameters and strong visual differences between the animal and the background, usually resulting in poor solutions. In the meanwhile, deep-learning models learn how to locate the animals when provided with a small fraction of the videos annotated. Our solution empowers comfortable and efficient video annotation, includes in-house improvements to tackle problems like crowding and varying light conditions, and works well even on challenging recordings, like those obtained in natural environments.

This video shows the representative performance of a neural-network deep learning based raven detector. Using our loopy software, the user annotated a small percentage of their videos and then was able to detect Ravens in wild and varying lighting conditions.

Example Detections from Two Custom Animal Detectors

Example Application: Multiple Fish Tracking

Tracking multiple fish is fully supported in loopy. Upload your movie and select the "multiple individual" tracker, adapt the parameters to your specific setup and start tracking. After the tracking is finished you can do several things:

  • Review the results. A video-montage version of you original movie with the tracked objects colored and traces is drawn.
  • Directly generate general and summary statistics, such as heatmaps and activity plots.
  • Plot fish specific measures. For example, inter-individual distance and main vector of motion.
  • Download the raw tracking data.