Learning by Tracking: Siamese CNN for Robust Target Association

Citations Over TimeTop 10% of 2016 papers

Abstract

This paper introduces a novel approach to the task of data association within the context of pedestrian tracking, by introducing a two-stage learning scheme to match pairs of detections. First, a Siamese convolutional neural network (CNN) is trained to learn descriptors encoding local spatio-temporal structures between the two input image patches, aggregating pixel values and optical flow information. Second, a set of contextual features derived from the position and size of the compared input patches are combined with the CNN output by means of a gradient boosting classifier to generate the final matching probability. This learning approach is validated by using a linear programming based multi-person tracker showing that even a simple and efficient tracker may outperform much more complex models when fed with our learned matching probabilities. Results on publicly available sequences show that our method meets state-of-the-art standards in multiple people tracking.

Related Papers

• → Joint Learning of Convolutional Neural Networks and Temporally Constrained Metrics for Tracklet Association(2016)114 cited
• → Online Learned Siamese Network with Auto-Encoding Constraints for Robust Multi-Object Tracking(2019)15 cited
• → Multi-classifier Guided Discriminative Siamese Tracking Network(2020)1 cited
• → Online Unsupervised Feature Learning for Visual Tracking(2013)2 cited