Instance Segmentation and Tracking with Cosine Embeddings and Recurrent Hourglass Networks
This work addresses the problem of accurately tracking individual instances over time in video data, such as medical imaging and plant analysis, with incremental improvements in method integration.
The authors tackled instance segmentation and tracking in videos by proposing a recurrent fully convolutional network with a cosine embedding loss, achieving state-of-the-art performance on the ISBI celltracking challenge datasets and outperforming non-video methods in segmenting left ventricles in MR videos.
Different to semantic segmentation, instance segmentation assigns unique labels to each individual instance of the same class. In this work, we propose a novel recurrent fully convolutional network architecture for tracking such instance segmentations over time. The network architecture incorporates convolutional gated recurrent units (ConvGRU) into a stacked hourglass network to utilize temporal video information. Furthermore, we train the network with a novel embedding loss based on cosine similarities, such that the network predicts unique embeddings for every instance throughout videos. Afterwards, these embeddings are clustered among subsequent video frames to create the final tracked instance segmentations. We evaluate the recurrent hourglass network by segmenting left ventricles in MR videos of the heart, where it outperforms a network that does not incorporate video information. Furthermore, we show applicability of the cosine embedding loss for segmenting leaf instances on still images of plants. Finally, we evaluate the framework for instance segmentation and tracking on six datasets of the ISBI celltracking challenge, where it shows state-of-the-art performance.