The automated tracking of social insects, such as ants, could dramatically increase the fidelity and amount of analyzed data for studying complex group behaviours. Recently, data association based multiple object tracking methods have shown promise in improving handling of occlusions. However, the tracking of ants in a colony is still challenging as (1) their motion is often sporadic and irregular, (2) they often have highly similar appearance, and (3) they are mostly present the entire duration of video. My research focuses on reducing tracking errors (ID switches and Fragments) by introducing new features, improving association with machine learning, and exploiting unique characteristics of insect videos.