Simple Online and Realtime Tracking with a Deep Association Metric

Abstract

Simple Online and Realtime Tracking (SORT) is a pragmatic approach to multiple object tracking with a focus on simple, effective algorithms. In this paper, we integrate appearance information to improve the performance of SORT. Due to this extension we are able to track objects through longer periods of occlusions, effectively reducing the number of identity switches. In spirit of the original framework we place much of the computational complexity into an offline pre-training stage where we learn a deep association metric on a large-scale person re-identification dataset. During online application, we establish measurement-to-track associations using nearest neighbor queries in visual appearance space. Experimental evaluation shows that our extensions reduce the number of identity switches by 45%, achieving overall competitive performance at high frame rates.

arXiv comment5 pages, 1 figure

References in corpus (5)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Simple Online and Realtime Tracking
• MOT16: A Benchmark for Multi-Object Tracking
• MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
• A Multi-cut Formulation for Joint Segmentation and Tracking of Multiple Objects

Cited by in corpus (23)

• Deep Learning for UAV-based Object Detection and Tracking: A Survey
• 3D Multi-Object Tracking: A Baseline and New Evaluation Metrics
• Memory Based Online Learning of Deep Representations from Video Streams
• Exploit the Connectivity: Multi-Object Tracking with TrackletNet
• Multiple People Tracking Using Hierarchical Deep Tracklet Re-identification
• Joint Detection and Tracking in Videos with Identification Features
• GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning
• Frame-wise Motion and Appearance for Real-time Multiple Object Tracking
• PointIT: A Fast Tracking Framework Based on 3D Instance Segmentation
• 2rd Place Solutions in the HC-STVG track of Person in Context Challenge 2021
• Derivation of a Constant Velocity Motion Model for Visual Tracking
• The P-DESTRE: A Fully Annotated Dataset for Pedestrian Detection, Tracking, Re-Identification and Search from Aerial Devices
• Large Area 3D Human Pose Detection Via Stereo Reconstruction in Panoramic Cameras
• Grab: Fast and Accurate Sensor Processing for Cashier-Free Shopping
• Detecting and counting tiny faces
• Enhancing the Association in Multi-Object Tracking via Neighbor Graph
• GAKP: GRU Association and Kalman Prediction for Multiple Object Tracking
• Joint Learning Architecture for Multiple Object Tracking and Trajectory Forecasting
• Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation
• Smart Black Box 2.0: Efficient High-bandwidth Driving Data Collection based on Video Anomalies
• Traffic Danger Recognition With Surveillance Cameras Without Training Data
• Know Your Surroundings: Panoramic Multi-Object Tracking by Multimodality Collaboration
• Video Surveillance for Road Traffic Monitoring