ToxTrac: a fast and robust software for tracking organisms (1706.02577v1)

Abstract: 1. Behavioral analysis based on video recording is becoming increasingly popular within research fields such as; ecology, medicine, ecotoxicology, and toxicology. However, the programs available to analyze the data, which are; free of cost, user-friendly, versatile, robust, fast and provide reliable statistics for different organisms (invertebrates, vertebrates and mammals) are significantly limited. 2. We present an automated open-source executable software (ToxTrac) for image-based tracking that can simultaneously handle several organisms monitored in a laboratory environment. We compare the performance of ToxTrac with current accessible programs on the web. 3. The main advantages of ToxTrac are: i) no specific knowledge of the geometry of the tracked bodies is needed; ii) processing speed, ToxTrac can operate at a rate >25 frames per second in HD videos using modern desktop computers; iii) simultaneous tracking of multiple organisms in multiple arenas; iv) integrated distortion correction and camera calibration; v) robust against false positives; vi) preservation of individual identification if crossing occurs; vii) useful statistics and heat maps in real scale are exported in: image, text and excel formats. 4. ToxTrac can be used for high speed tracking of insects, fish, rodents or other species, and provides useful locomotor information. We suggest using ToxTrac for future studies of animal behavior independent of research area. Download ToxTrac here: https://toxtrac.sourceforge.io

• The paper introduces ToxTrac, a free open-source tool that delivers fast and accurate automated tracking of organisms in complex experimental setups.
• It achieves high performance using advanced methods, recording a 99.2% detection rate and 99.6% identity preservation for long tracks.
• The software’s multi-arena tracking and versatile output options offer practical benefits for behavioral, ecological, and toxicological research.

An Overview of ToxTrac: Software for Automated Tracking of Organisms

The computational paper of animal behavior stands at the intersection of technology and biology, with applications spanning ecology, ecotoxicology, toxicology, and beyond. Traditional tools for video-based behavior analysis are often costly, slow, or complex, requiring significant programming expertise. Thus, the introduction of ToxTrac, a free, open-source software for organism tracking, represents a pragmatic step forward in providing accessible tools for researchers in these fields. Developed by Alvaro Rodriquez and colleagues, ToxTrac embodies a user-friendly platform capable of high-speed, accurate tracking of various organisms without necessitating specialized understanding of geometry or movement patterns.

Key Features and Advantages

ToxTrac differentiates itself through several key features that enhance its utility:

1. Multi-Organism and Multi-Arena Tracking: Capabilities include simultaneous tracking of multiple organisms across separate arenas, which is crucial for laboratory settings involving complex experimental designs.
2. Performance: The software achieves a processing speed of over 25 frames per second with HD videos on modern desktop systems, making it suitable for real-time applications.
3. Advanced Detection Methods: It incorporates the Kalman filter for basic tracking, complemented by post-processing routines that preserve organism identity even during occlusions—an essential feature for studies requiring long-term observation of individual animals.
4. Robust Output Options: Users can export results in image, text, and Excel formats, facilitating data integration with other analytical tools. This is particularly useful for researchers analyzing various behavioral parameters such as locomotion and anxiety-related behaviors.

Evaluation and Results

ToxTrac's performance was rigorously evaluated against existing software tools, including IdTracker and BioTrack. Notably, ToxTrac demonstrated an average detection rate of 99.2% in non-occluded settings compared to 95.9% by IdTracker. Its ability to maintain animal identity was further highlighted by its efficiency in processing times and accuracy, achieving 99.6% identity preservation for longer tracks (greater than 50 frames). This places ToxTrac among the leading software, particularly when factoring its speed and ease of use.

Practical and Theoretical Implications

Practically, ToxTrac provides a potent tool for researchers conducting behavioral assays, enabling non-invasive, accurate behavioral analysis across multiple experimental conditions. The software's flexibility extends its application potential beyond laboratories to field studies, enhancing ecological research's prospects.

Theoretically, ToxTrac enriches opportunities for increased accuracy in research outputs, lending robustness to studies examining environmental influences on behavioral traits. Future improvements in tracking algorithms could refine these capabilities further, reducing reliance on Gaussian mixtures or Kalman filtering.

Future Prospects

The ongoing development of ToxTrac entails promising enhancements such as the integration of machine learning frameworks to improve detection accuracy and robustness, particularly under occlusion conditions. As computational power increases and algorithmic complexity becomes more manageable, ToxTrac may become a model template for open-source development in behavioral studies.

In conclusion, ToxTrac emerges as a crucial development in animal tracking software, combining ease of access with advanced capabilities to support detailed behavioral research in various species. Its wide-ranging applications and adaptability make it an invaluable tool for current and emerging research needs. This establishes a foundation for future developments aiming to incorporate more sophisticated analytical techniques.