Home » Video Analysis

Category: Video Analysis

OpenMonkeyStudio

February 27, 2020

OpenMonkeyStudio is an amazing new tool for tracking movements by and interactions among freely moving monkeys. Ben Hayden and Jan Zimmerman kindly sent along this summary of the project:

Tracking animal pose (that is, identifying the positions foo their major joints) is a major frontier in neuroscience. When combined with neural recordings, pose tracking allows for identifying the relationship between neural activity and movement, and decision-making inferred from movement. OpenMonkeyStudio is a system designed to allow tracking of rhesus macaques in large freely moving environments.

Tracking monkeys is at least an order of magnitude more difficult than tracking mice, flies, and worms. Monkeys are, basically, large furry blobs; they don’t have clear body segmentations. And their movements are much richer and more complex. For these reasons, out of the box systems don’t work with monkeys.

The major innovation of our OpenMonkeyStudio is how it tackles the annotation problem. Deep learning systems aren’t very good at generalization. They can replicate things they have seen before or things that are kind fo similar to what they have seen. So the important thing is giving them a sufficiently large training set. We ideally want to have about a million annotated images. That would cost about $10 million and we don’t have that kind of money. So we use several cool tricks, which we describe in our paper, to augment a small dataset and turn it into a large one. Doing that works very well, and results in a system that can track one or even two interacting monkeys.


Check out the preprint:

OpenMonkeyStudio: Automated Markerless Pose Estimation in Freely Moving Macaques

Praneet C. Bala, Benjamin R. Eisenreich, Seng Bum Michael Yoo, Benjamin Y. Hayden, Hyun Soo Park, Jan Zimmermann

https://www.biorxiv.org/content/10.1101/2020.01.31.928861v1

Camera Control

February 6, 2020

The Adaptive Motor Control Lab at Harvard recently posted their project, Camera Control, a python based camera software GUI, to Github.


Camera Control is an open-source software package written by postdoctoral fellow Gary Kane that allows video to be recorded in sync with behavior. The python GUI and scripts allows investigators to record from multiple imaging source camera feeds with associated timestamps for each frame. When used in combination with a NIDAQ card, timestamps from a behavioral task can also be recorded on the falling edge of a TTL signal. This allows video analysis to be paired with physiological recording which can be beneficial in assessing behavioral results. This package requires Windows 10, Anaconda, and Git, and is compatible with Imaging Source USB3 cameras. The software package is accessible for download from the lab’s github and instructions for installation and video recording are provided.

Find more on Github.


Kane, G. & Mathis, M. (2019). Camera Control: record video and system timestamps from Imaging Source USB3 cameras. GitHub. https://zenodo.org/badge/latestdoi/200101590

SimBA

JANUARY 23, 2020

Simon Nilsson from Sam Golden’s lab at the University of Washington recently shared their project SimBA (Simple Behavioral Analysis), an open source pipeline for the analysis of complex social behaviors:


“The manual scoring of rodent social behaviors is time-consuming and subjective, impractical for large datasets, and can be incredibly repetitive and boring. If you spend significant time manually annotating videos of social or solitary behaviors, SimBA is an open-source GUI that can automate the scoring for you. SimBA does not require any specialized equipment or computational expertise.

SimBA uses data from popular open-source tracking tools in combination with a small amount of behavioral annotations to create supervised machine learning classifiers that can then rapidly and accurately score behaviors across different background settings and lighting conditions. Although SimBA is developed and validated for complex social behaviors such as aggression and mating, it has the flexibility to generate classifiers in different environments and for different behavioral modalities. SimBA takes users through a step-by-step process and we provide detailed installation instructions and tutorials for different use case scenarios online. SimBA has a range of in-built tools for video pre-processing, accessing third-party tracking models, and evaluating the performance of machine learning classifiers. There are also several methods for in-depth visualizations of behavioral patterns. Because of constraints in animal tracking tools, the initial release of SimBA is limited to processing social interactions of differently coat colored animals, recorded from a top down view, and future releases will advance past these limitations. SimBA is very much in active development and a manuscript is in preparation. Meanwhile, we are very keen to hear from users about potential new features that would advance SimBA and help in making automated behavioral scoring accessible to more researchers in behavioral neuroscience.”


For more information on SimBA, you can check out the project’s Github page here.

For those looking to contribute or try out SimBA and are looking for feedback, you can interact on the project’s Gitter page.

Plus, take a look at their recent twitter thread detailing the project.

If you would like to be added to the project’s listserv for updates, fill out this form here.

 

B-SOiD

January 16, 2020

Eric Yttri from Carnegie Mellon University has shared the following about B-SOiD, an open source unsupervised algorithm for discovery of spontaneous behaviors:


“Capturing the performance of naturalistic behaviors remains a tantalizing but prohibitively difficult field of study – current methods are difficult, expensive, low temporal resolution, or all of the above. Recent machine learning applications have enabled localization of limb position; however, position alone does not yield behavior. To provide a high temporal resolution bridge from positions to actions and their kinematics, we developed Behavioral Segmentation of Open-field In DeepLabCut, or B-SOiD. B-SOiD is an unsupervised learning algorithm that discovers and classifies actions based on the inherent statistics of the data points of the data points provided (including any marker or markerless system, not just deeplabcut). Our algorithm enables the automated segregation of different, sub-second behaviors with a single bottom-up perspective video camera – and does so without considerable effort or potential bias from the user. This open-source platform opens the door to the efficient study of spontaneous behavior and its neural mechanisms. It also readily provides critical behavioral metrics that historically have been difficult to quantify, such as grooming and stride-length in OCD and stroke research.”


Code available: https://github.com/YttriLab/B-SOID
Preprint available: https://www.biorxiv.org/content/10.1101/770271v1.full


Oat: online animal tracker

December 5, 2019

Jonathan Newman of the Wilson Lab at Massachusetts Institute of Technology has developed and shared a set of programs for processing video.


The only thing you’ll enjoy more than an oat milk latte from your favorite coffeeshop is the Oat collection of video processing components designed for use with Linux! Developed by Jonathan Newman of Open Ephys, this set of programs is useful for processing video, extracting object position information, and streaming data. While it was designed for use with real-time animal position tracking, it can be used in multiple applications that require real-time object tracking. The individual Oat components each have a standard interface that can be chained together to create complex dataflow networks for capturing  processing, and recording video streams.

Read more about Oat on the Open Ephys website, or check out more on Github!


https://open-ephys.org/oat

The OpenMV project: Machine Vision with Python

November 14, 2019

OpenMV – Better, Stronger, Faster and only $65 USD


Recent updates to the firmware for the OpenMV H7 Camera have brought some new functionality to this device, which is popular for open source neuroscience projects (e.g. Rodent Arena Tracker, or RAT: https://hackaday.io/project/162481-rodent-arena-tracker-rat). The new firmware allows for use of the popular TensorFlow library for machine learning on this MicroPython-based device. It’s small (1.5 by 1.75 inches), consumes only a max of 140 mA when processing data, has 1 MB of RAM and 2 MB of flash, and runs 64-bits computations at 4800 MHz (3.84 GB/s bandwidth). OpenMV is capable of frame differencing, color tracking, marker tracking, face detection, eye tracking, person detection (with TensorFlow Lite), and more. The project supports a very easy to use GUI, the OpenMV IDE. It’s intuitive to use, and offers a number of ready to go applications. Arduino users will feel right at home, despite the code being Python based.

Check out the project here: https://openmv.io/.

Updates on LocoWhisk and ART

OCTOBER 3, 2019

Dr Robyn Grant from Manchester Metropolitan University in Manchester, UK has shared her group’s most recent project called LocoWhisk, which is a hardware and software solution for measuring rodent exploratory, sensory and motor behaviours:


In describing the project, Dr Grant writes, “Previous studies from our lab have shown that that analysing whisker movements and locomotion allows us to quantify the behavioural consequences of sensory, motor and cognitive deficits in rodents. Independent whisker and feet trackers existed but there was no fully-automated, open-source software and hardware solution, that could measure both whisker movements and gait.

We developed the LocoWhisk arena and new accompanying software, that allows the automatic detection and measurement of both whisker and gait information from high-speed video footage. The arena can easily be made from low-cost materials; it is portable and incorporates both gait analysis (using a pedobarograph) and whisker movements (using high-speed video camera and infrared light source).

The software, ARTv2 is freely available and open source. ARTv2 is also fully-automated and has been developed from our previous ART software (Automated Rodent Tracker).

ARTv2 contains new whisker and foot detector algorithms. On high-speed video footage of freely moving small mammals (including rat, mouse and opossum), we have found that ARTv2 is comparable in accuracy, and in some cases significantly better, than readily available software and manual trackers.

The LocoWhisk system enables the collection of quantitative data from whisker movements and locomotion in freely behaving rodents. The software automatically records both whisker and gait information and provides added statistical tools to analyse the data. We hope the LocoWhisk system and software will serve as a solid foundation from which to support future research in whisker and gait analysis.”

For more details on the ARTv2 software, check out the github page here.

Check out the paper that describes LocoWhisk and ARTv2, which has recently been published in the Journal of Neuroscience Methods.

LocoWhisk was initially shared and developed through the NC3Rs CRACK IT website here.


SpikeGadgets

AUGUST 22, 2019

We’d like to highlight groups and companies that support an open-source framework to their software and/or hardware in behavioral neuroscience. One of these groups is SpikeGadgets, a company co-founded by Mattias Karlsson and Magnus Karlsson.


SpikeGadgets is a group of electrophysiologists and engineers who are working to develop neuroscience hardware and software tools. Their open-source software, Trodes, is a cross-platform software suite for neuroscience data acquisition and experimental control, which is made up of modules that communicate with a centralized GUI to visualize and save electrophysiological data. Trodes has a camera module and a StateScript module, which is a state-based scripting language that can be used to program behavioral tasks through using lights, levels, beam breaks, lasers, stimulation sources, audio, solenoids, etc. The camera module can be used to acquire video that can synchronize to neural recordings; the camera module can track the animal’s position in real-time or play it back after the experiment. The camera module can work with USB webcams or GigE cameras.

Paired with the Trodes software and StateScript language is the SpikeGadgets hardware that can be purchased on their website. The hardware is used for data acquisition (Main Control Unit, used for electrophysiology) and behavioral control (Environmental Control Unit).  SpikeGadgets also provides both Matlab and Python toolboxes on their site that can be used to analyze both behavioral and electrophysiological data. Trodes can be used on Windows, Linux, or Mac, and there are step-by-step instructions for how to install and use Trodes on the group’s bitbucket page.

Spikegadgets mission is “to develop the most advanced neuroscience tools on the market, while preserving ease of use and science-driven customization.”

 


For more information on SpikeGadgets or to download or purchase their software or hardware, check out their website here.

There is additional documentation on their BitBucket Wiki, with a user manual, instructions for installation, and FAQ.

Check out their entire list of collaborators, contributors, and developers here.

Pathfinder

AUGUST 8, 2019

Matthew Cooke and colleagues from Jason Snyder’s lab at University of British Columbia recently developed open source software to detect spatial navigation behavior in animals called Pathfinder:


Spatial navigation is studied across several different paradigms for different purposes in animals; through analyzing spatial behaviors we can gain insight into how an animal learns a task, how they change their approach strategy, and generally observing goal-directed behaviors. Pathfinder is an open source software that can analyze rodent navigation. The software intends to automatically classify patterns of navigation as a rodent performs in a task. Pathfinder can analyze subtle patterns in spatial behavior that simple analysis measures may not always be able to pick up on. Specifically, many water maze analyses use escape latency or path length as an analysis measure, but the authors point out that the time it takes to reach the platform may not differ while the strategy does, so using latency may not be the most optimal measure for analyzing an animal’s strategy and therefore experimenters may miss out on key differences in behavior. Therefore, Pathfinder aims to analyze more subtle aspects of the task to determine differences in spatial navigation and strategy.

Originally intended for water maze navigation, pathfinder can also be used to analyze many other spatial behaviors across different tasks, mazes, and species. The software takes x-y coordinates from behavior tracking software (for example, it can open files from Noldus Ethovision, ActiMetrics’ Watermaze, Stoelting’s Anymaze, and the open-source project ezTrack from Denise Cai’s lab), and then calculates the best-fit search strategy for each rodent’s trial. For the morris water maze task, trials are fit into several categories: Direct Swim, Directed Search, Focal Search, Spatial indirect, Chaining, Scanning, Thigmotaxis, and Random Search.

Pathfinder runs in Python and has an easy-to-use GUI; many aspects and parameters can be adjusted to analyze different tasks or behaviors.

For more details, check out their BioRxiV preprint here.

There’s a nice (humorous!) writeup of the project on the Snyder Lab website.

You can also download the project and view more details on their github:
https://matthewbcooke.github.io/Pathfinder/

https://github.com/MatthewBCooke/Pathfinder/


MouseMove

July 18, 2019

In a 2015 Scientific Reports article, Andre Samson and colleagues shared their project MouseMove, an open-source software for quantifying movement in the open field test:


The Open Field (OF) test is a commonly used assay for monitoring exploratory behavior and locomotion in rodents. Most research groups use commercial systems for recording and analyzing behavior in the OF test, but these commercial systems can be expensive and lack flexibility. A few open-source OF systems have been developed, but are limited in the movement parameters that can be collected and analyzed. MouseMove is the first open-source software capable of providing qualitative and quantitative information on mouse locomotion in a semi-automated and high-throughput approach. With the aim of providing a freely available program for analyzing OF test data, these researchers developed a software that accurately quantifies numerous parameters of movement.

In their manuscript, Samson et al. describe the design and implementation of MouseMove. Their OF system allows for the measurement of distance, speed, and laterality with >96% accuracy. They use MouseMove as a method to analyze OF behavior of mice after experimental stroke to show reduced locomotor activity and quantify laterality deficits. The system is used in combination with the open source program ImageJ and the MTrack2 plugin to analyze pre-recorded OF test video.

The system has two downloadable components, the ImageJ macro and a separate program with the custom-built MouseMove GUI. ImageJ is used to subtract the background video from the experiment and create an image of the animals total trajectory. The MouseMove GUI then completes a detailed analysis of the movement patterns, measuring the fractional time spent stationary, the distance traveled, speed mean and various details of laterality. The results are depicted in both a visual/graphical form and as a saveable text file. In the manuscript, they provide step-wise instructions of how to use Mousemove. The authors additionally highlight the defined region-of-interest (ROI) ability of the software that makes it suitable for analysis of cognitive tests such as Novel Object Recognition. This tool offers relatively fast video-processing of motor cognitive behaviors and has many applications for the study of rodent models of brain injury/stimulation to measure altered locomotion.

 

More information on MouseMove can be found in their manuscript here.


Samson, A. L., Ju, L., Ah Kim, H., Zhang, S. R., Lee, J. A. A., Sturgeon, S. A., … Schoenwaelder, S. M. (2015). MouseMove: an open source program for semi-automated analysis of movement and cognitive testing in rodents. Scientific Reports, 5, 16171.  doi: 10.1038/srep16171