Tracking multiple ants in a colony

Fasciano, Thomas; Nguyen, Hong-Thu; Shin, Min Chul

doi:10.1109/wacv.2013.6475065

Cited by 12 publications

(19 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A key part of the MAP framework is the affinity model which measures the likelihood that two tracklets should be linked and often composed of appearance, motion and temporal features. Appearance modeling between tracklets has been improved using both online and offline training methods [17,18], as well as modeling the motion [6]. Although these methods can improve the quality of tracking around occlusions, the similarity in appearance and motion between nearby objects may still cause even these advanced appearance models to confuse two or more objects.…”

Section: Related Workmentioning

confidence: 99%

“…Next, we briefly describe implementation details that differ from those used in the tracking framework of [6]. In the following subsection, we describe the methods used for foreground blob detection.…”

Section: Experiments Setupmentioning

confidence: 99%

“…We use the tracking framework of [6] with our occlusion sub-tunnels. We follow the first three parts of the framework (detection, tracklet building, and tracklet matching) as these are the stages affected by our proposed occlusion sub-tunnel method and the fourth step of gap filling is a post processing step to estimate positions during occlusion.…”

Section: Implementation Detailsmentioning

confidence: 99%

See 2 more Smart Citations

Multiple Insect Tracking with Occlusion Sub-tunnels

Fasciano

Dornhausy

Shin

2015

2015 IEEE Winter Conference on Applications of Computer Vision

Self Cite

View full text Add to dashboard Cite

Automated tracking methods greatly expedite the collection of data for studying social insects. However, due to the frequency of occlusions (due to interactions) and similarity in appearance and motion features, tracking could easily drift to the incorrect object as the affinity model is unable to discern between similar objects. Recently, a method to filter incorrect associations based on areas of occlusion was proposed. This method only filtered based on entrance and exit within a specific occlusion. In this paper, we propose to improve the tracking of multiple insects involving frequent occlusion by modeling the paths of possible movement within the occlusion tunnel which we call occlusion sub-tunnels. Using two datasets consisting of ants and termites, we demonstrate that the method filters 8% more incorrect associations on average resulting in a reduction of ID switches by 19% over all datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Experiments Setupmentioning

confidence: 99%

Section: Implementation Detailsmentioning

confidence: 99%

See 1 more Smart Citation

Multiple Insect Tracking with Occlusion Sub-tunnels

Fasciano

Dornhausy

Shin

2015

2015 IEEE Winter Conference on Applications of Computer Vision

Self Cite

View full text Add to dashboard Cite

show abstract

“…Pairs of tracklets z n = (T i , T j ) are said to be linkable if the frame gap between the tail of T i and the head of T j , π(T i , T j ), is no more than the upper bound ξ k for the current level k. Each of the tracklet pairs z n has an associated feature vectorf = (f 1 , f 2 , ..., f d ). In practice, we use the same set of features as described in [2]. Figure 2 illustrates how a set a queries can be generated from the current set of tracklets.…”

Section: Creating Training Examplesmentioning

confidence: 99%

“…The fraction of queries to be labeled in the semi-supervised weak labeling process, λ, was set to 0.8 over η = 30 weak labeling iterations. We use the same set of features as described in [2].…”

Section: Experimental Evaluationmentioning

confidence: 99%

Efficient Training of Multiple Ant Tracking

Rice

Dornhausy

Shin

2015

2015 IEEE Winter Conference on Applications of Computer Vision

Self Cite

View full text Add to dashboard Cite

The applicability of automated motion analysis is immense and continues to grow as our ability to record objects of interest becomes easier and less expensive. In the case of multi-object tracking, data association methods have been proposed to improve handling of occlusions. These methods are strongly affected by their ability to measure association affinities between fragmented object trajectories. Obtaining labeled training examples for learning how to measure these associations can be expensive and time-consuming. We propose an interactive training framework that utilizes an uncertainty based active sampling approach in combination with semi-supervised learning in order to reduce the number of labeled examples needed for training. Additionally, an affinity scoring function is learned with Random Forest to speed up learning affinity measures in order to make the interactive training framework possible. Experimental results on two 10,000 frame video sequences of ant colonies demonstrates a significant reduction in the amount of labeled examples needed over random sampling.

show abstract

anTraX: high throughput video tracking of color-tagged insects

Gal

Saragosti

Kronauer

2020

Preprint

View full text Add to dashboard Cite

Recent years have seen a surge in methods to track and analyze animal behavior. Nevertheless, tracking individuals in closely interacting, group-living organisms remains a challenge. Here we present anTraX, an algorithm and software package for high-throughput video tracking of color-tagged insects. anTraX combines neural network classification of animals with a novel approach for representing tracking data as a graph, enabling individual tracking even in cases where it is difficult to segment animals from one another, or where tags are obscured. The use of color tags, a well-established and robust method for marking individual insects in groups, relaxes requirements for image size and quality, and makes the software broadly applicable. anTraX is readily integrated into existing tools and methods for automated image analysis of behavior to further augment its output. anTraX can handle large-scale experiments with minimal human involvement, allowing researchers to simultaneously monitor many social groups over long time periods.

show abstract

Tracking multiple ants in a colony

Cited by 12 publications

References 13 publications

Multiple Insect Tracking with Occlusion Sub-tunnels

Multiple Insect Tracking with Occlusion Sub-tunnels

Efficient Training of Multiple Ant Tracking

anTraX: high throughput video tracking of color-tagged insects

Contact Info

Product

Resources

About