Learning to Track: Online Multi-object Tracking by Decision Making
Yu Xiang,Alexandre Alahi,Silvio Savarese +2 more
- pp 4705-4713
Reads0
Chats0
TLDR
This work forms the online MOT problem as decision making in Markov Decision Processes (MDPs), where the lifetime of an object is modeled with a MDP, and a similarity function for data association is equivalent to learning a policy for the MDP.Abstract:
Online Multi-Object Tracking (MOT) has wide applications in time-critical video analysis scenarios, such as robot navigation and autonomous driving. In tracking-by-detection, a major challenge of online MOT is how to robustly associate noisy object detections on a new video frame with previously tracked objects. In this work, we formulate the online MOT problem as decision making in Markov Decision Processes (MDPs), where the lifetime of an object is modeled with a MDP. Learning a similarity function for data association is equivalent to learning a policy for the MDP, and the policy learning is approached in a reinforcement learning fashion which benefits from both advantages of offline-learning and online-learning for data association. Moreover, our framework can naturally handle the birth/death and appearance/disappearance of targets by treating them as state transitions in the MDP while leveraging existing online single object tracking methods. We conduct experiments on the MOT Benchmark [24] to verify the effectiveness of our method.read more
Citations
More filters
Proceedings ArticleDOI
Simple online and realtime tracking
TL;DR: In this article, a pragmatic approach to multiple object tracking where the main focus is to associate objects efficiently for online and real-time applications is explored, where changing the detector can improve tracking by up to 18.9%.
Posted Content
Virtual Worlds as Proxy for Multi-Object Tracking Analysis
TL;DR: This work proposes an efficient real-to-virtual world cloning method, and validate the approach by building and publicly releasing a new video dataset, called "Virtual KITTI", automatically labeled with accurate ground truth for object detection, tracking, scene and instance segmentation, depth, and optical flow.
Proceedings ArticleDOI
Simple Online and Realtime Tracking
TL;DR: Despite only using a rudimentary combination of familiar techniques such as the Kalman Filter and Hungarian algorithm for the tracking components, this approach achieves an accuracy comparable to state-of-the-art online trackers.
Book ChapterDOI
Tracking Objects as Points
TL;DR: CenterTrack as mentioned in this paper applies a detection model to a pair of images and detections from the prior frame, given this minimal input, localizes objects and predicts their associations with the previous frame.
Proceedings ArticleDOI
VirtualWorlds as Proxy for Multi-object Tracking Analysis
TL;DR: In this article, the authors proposed an efficient real-to-virtual world cloning method, and validated their approach by building and publicly releasing a new video dataset, called "Virtual KITTI" 1, automatically labeled with accurate ground truth for object detection, tracking, scene and instance segmentation, depth, and optical flow.
References
More filters
Proceedings ArticleDOI
A training algorithm for optimal margin classifiers
TL;DR: A training algorithm that maximizes the margin between the training patterns and the decision boundary is presented, applicable to a wide variety of the classification functions, including Perceptrons, polynomials, and Radial Basis Functions.
Posted Content
Playing Atari with Deep Reinforcement Learning
Volodymyr Mnih,Koray Kavukcuoglu,David Silver,Alex Graves,Ioannis Antonoglou,Daan Wierstra,Martin Riedmiller +6 more
TL;DR: This work presents the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning, which outperforms all previous approaches on six of the games and surpasses a human expert on three of them.
Journal ArticleDOI
Algorithms for the Assignment and Transportation Problems
TL;DR: In this paper, algorithms for the solution of the general assignment and transportation problems are presen, and the algorithm is generalized to one for the transportation problem.
Journal ArticleDOI
Tracking-Learning-Detection
TL;DR: A novel tracking framework (TLD) that explicitly decomposes the long-term tracking task into tracking, learning, and detection, and develops a novel learning method (P-N learning) which estimates the errors by a pair of “experts”: P-expert estimates missed detections, and N-ex Expert estimates false alarms.
Journal ArticleDOI
Algorithms for Inverse Reinforcement Learning
Andrew Y. Ng,Stuart Russell +1 more
TL;DR: Pharmacokinetics of ivermectin after IV administration were best described by a 2-compartment open model; values for main compartmental variables included volume of distribution at a steady state, area under the plasma concentration-time curve, and area underThe AUC curve.