2019 · 39 citations · 39 references
ComputingAutonomous SystemsComputer ScienceAutonomous VehiclesComputer VisionMachine LearningAction RecognitionDeep LearningGraph-based LearningMotion AnalysisRepresentation LearningVisual TrackingConvolutional Neural NetworksDeep Learning-based TrackingGraph Data StructuresGraph Neural NetworksGraph Structure LearningMotion FeaturesNetwork Flow ModelsObject Association
Multiple Object Tracking (MOT) has a wide range of applications in surveillance retrieval and autonomous driving. The majority of existing methods focus on extracting features by deep learning and hand-crafted optimizing bipartite graph or network flow. In this paper, we proposed an efficient end-to-end model, Deep Association Network (DAN), to learn the graph-based training data, which are constructed by spatial-temporal interaction of objects. DAN combines Convolutional Neural Network (CNN), Motion Encoder (ME) and Graph Neural Network (GNN). The CNNs and Motion Encoders extract appearance features from bounding box images and motion features from positions respectively, and then the GNN optimizes graph structure to associate the same object among frames together. In addition, we presented a novel end-to-end training strategy for Deep Association Network. Our experimental results demonstrate the effectiveness of DAN up to the state-of-the-art methods without extra-dataset on MOT16 and DukeMTMCT.
39
Scalable Person Re-identification: A Benchmark
Liang Zheng, Liyue Shen, Lu Tian et al. · 2015 · 4.6K citations
Social LSTM: Human Trajectory Prediction in Crowded Spaces
Alexandre Alahi, Kratarth Goel, Vignesh Ramanathan et al. · 2016 · 3.5K citations · Full text