Multi-Target Tracking with Transferable Convolutional Neural Networks
This addresses the problem of scaling multi-target tracking for signal processing applications, though it is incremental by applying deep learning to a classical task.
The paper tackled multi-target tracking by recasting it as an image-to-image prediction task using a convolutional neural network, achieving a 29% performance improvement when transferring from 10 to 250 targets without re-training.
Multi-target tracking (MTT) is a classical signal processing task, where the goal is to estimate the states of an unknown number of moving targets from noisy sensor measurements. In this paper, we revisit MTT from a deep learning perspective and propose a convolutional neural network (CNN) architecture to tackle it. We represent the target states and sensor measurements as images and recast the problem as an image-to-image prediction task. Then we train a fully convolutional model at small tracking areas and transfer it to much larger areas with numerous targets and sensors. This transfer learning approach enables MTT at a large scale and is also theoretically supported by our novel analysis that bounds the generalization error. In practice, the proposed transferable CNN architecture outperforms random finite set filters on the MTT task with 10 targets and transfers without re-training to a larger MTT task with 250 targets with a 29% performance improvement.