Tracking Objects with Higher Order Interactions using Delayed Column Generation
We study the problem of multi-target tracking and data association in video. We formulate this in terms of selecting a subset of high-quality tracks subject to the constraint that no pair of selected tracks is associated with a common detection (of an object). This objective is equivalent to the classic NP-hard problem of finding a maximum-weight set packing (MWSP) where tracks correspond to sets and is made further difficult since the number of candidate tracks grows exponentially in the number of detections. We present a relaxation of this combinatorial problem that uses a column generation formulation where the pricing problem is solved via dynamic programming to efficiently explore the space of tracks. We employ row generation to tighten the bound in such a way as to preserve efficient inference in the pricing problem. We show the practical utility of this algorithm for tracking problems in natural and biological video datasets.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Tracking People and Their Objects
Current pedestrian tracking approaches ignore important aspects of human behavior. Humans are not moving independently, but they closely interact with their environment, which includes not only other persons, but also di…
ObjectLearning Higher-order Object Interactions for Keypoint-based Video Understanding
Action recognition is an important problem that requires identifying actions in video by learning complex interactions across scene actors and objects. However, modern deep-learning based networks often require significa…
Action LocalizationAction RecognitionObjectVideo UnderstandingAttend and Interact: Higher-Order Object Interactions for Video Understanding
Human actions often involve complex interactions across several inter-related objects in the scene. However, existing approaches to fine-grained video understanding or visual relationship detection often rely on single o…
Action ClassificationAction RecognitionObjectRelationship Detection+6End-to-end Recurrent Multi-Object Tracking and Trajectory Prediction with Relational Reasoning
The majority of contemporary object-tracking approaches do not model interactions between objects. This contrasts with the fact that objects' paths are not independent: a cyclist might abruptly deviate from a previously …
Autonomous VehiclesMulti-Object TrackingObjectObject Tracking+2Capacity-Constrained Online Convex Optimization with Delayed Feedback
Online learning with delayed feedback typically assumes that the learner can track all pending rounds until their feedback arrives. In practice, tracking resources are finite, and feedback from untracked rounds is perman…