Recurrent Autoregressive Networks for Online Multi-Object Tracking
arXiv:1711.02741
Abstract
The main challenge of online multi-object tracking is to reliably associate object trajectories with detections in each video frame based on their tracking history. In this work, we propose the Recurrent Autoregressive Network (RAN), a temporal generative modeling framework to characterize the appearance and motion dynamics of multiple objects over time. The RAN couples an external memory and an internal memory. The external memory explicitly stores previous inputs of each trajectory in a time window, while the internal memory learns to summarize long-term tracking history and associate detections by processing the external memory. We conduct experiments on the MOT 2015 and 2016 datasets to demonstrate the robustness of our tracking method in highly crowded and occluded scenes. Our method achieves top-ranked results on the two benchmarks.
arXiv comment10 pages, 3 figures, 6 tables
References in corpus (9)
- Adam: A Method for Stochastic Optimization
- 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
- MOT16: A Benchmark for Multi-Object Tracking
- Dynamic Memory Networks for Visual and Textual Question Answering
- MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
- Tracklet Association by Online Target-Specific Metric Learning and Coherent Dynamics Estimation
- Multi-Class Multi-Object Tracking using Changing Point Detection
Cited by in corpus (6)
- Integrated Object Detection and Tracking with Tracklet-Conditioned Detection
- Multiple People Tracking Using Hierarchical Deep Tracklet Re-identification
- Joint Detection and Tracking in Videos with Identification Features
- End-to-End Learning Deep CRF models for Multi-Object Tracking
- TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model
- Know Your Surroundings: Panoramic Multi-Object Tracking by Multimodality Collaboration