Deep Similarity Metric Learning for Real-Time Pedestrian Tracking
arXiv:1806.07592
Abstract
Tracking by detection is a common approach to solving the Multiple Object Tracking problem. In this paper we show how learning a deep similarity metric can improve three key aspects of pedestrian tracking on a multiple object tracking benchmark. We train a convolutional neural network to learn an embedding function in a Siamese configuration on a large person re-identification dataset. The offline-trained embedding network is integrated in to the tracking formulation to improve performance while retaining real-time performance. The proposed tracker stores appearance metrics while detections are strong, using this appearance information to: prevent ID switches, associate tracklets through occlusion, and propose new detections where detector confidence is low. This method achieves competitive results in evaluation, especially among online, real-time approaches. We present an ablative study showing the impact of each of the three uses of our deep appearance metric.
References in corpus (12)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Simple Online and Realtime Tracking
- In Defense of the Triplet Loss for Person Re-Identification
- MOT16: A Benchmark for Multi-Object Tracking
- Multiple Object Tracking: A Literature Review
- MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
- Siamese Instance Search for Tracking
- Real-Time Multiple Object Tracking - A Study on the Importance of Speed
- DeNet: Scalable Real-time Object Detection with Directed Sparse Sampling
- POI: Multiple Object Tracking with High Performance Detection and Appearance Feature
- SOT for MOT