Graph Neural Based End-to-end Data Association Framework for Online Multiple-Object Tracking

Abstract

In this work, we present an end-to-end framework to settle data association in online Multiple-Object Tracking (MOT). Given detection responses, we formulate the frame-by-frame data association as Maximum Weighted Bipartite Matching problem, whose solution is learned using a neural network. The network incorporates an affinity learning module, wherein both appearance and motion cues are investigated to encode object feature representation and compute pairwise affinities. Employing the computed affinities as edge weights, the following matching problem on a bipartite graph is resolved by the optimization module, which leverages a graph neural network to adapt with the varying cardinalities of the association problem and solve the combinatorial hardness with favorable scalability and compatibility. To facilitate effective training of the proposed tracking network, we design a multi-level matrix loss in conjunction with the assembled supervision methodology. Being trained end-to-end, all modules in the tracker can co-adapt and co-operate collaboratively, resulting in improved model adaptiveness and less parameter-tuning efforts. Experiment results on the MOT benchmarks demonstrate the efficacy of the proposed approach.

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• Semi-Supervised Classification with Graph Convolutional Networks
• Geometric deep learning: going beyond Euclidean data
• MOT16: A Benchmark for Multi-Object Tracking
• Person Re-identification: Past, Present and Future
• MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
• MolGAN: An implicit generative model for small molecular graphs
• Few-Shot Learning with Graph Neural Networks
• Relational Deep Reinforcement Learning
• Discovering objects and their relations from entangled scene representations
• End-to-End Tracking and Semantic Segmentation Using Recurrent Neural Networks
• PeerNets: Exploiting Peer Wisdom Against Adversarial Attacks
• Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependencies

Cited by in corpus (9)

• TripletTrack: 3D Object Tracking using Triplet Embeddings and LSTM
• SimpleTrack: Understanding and Rethinking 3D Multi-object Tracking
• GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization
• Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking
• Learnable Graph Matching: A Practical Paradigm for Data Association
• Enhancing the Association in Multi-Object Tracking via Neighbor Graph
• Foresight of Graph Reinforcement Learning Latent Permutations Learnt by Gumbel Sinkhorn Network
• A Survey of Fish Tracking Techniques Based on Computer Vision
• AutoSelect: Automatic and Dynamic Detection Selection for 3D Multi-Object Tracking