Online multi-person tracking via robust collaborative model

Abstract

The past decade has witnessed significant progress in object detection and tracking in videos. In this paper, we present a model for collaboration between a pre-trained object detector and multiple single object trackers in the particle filter tracking framework. For each frame, we construct an association between the trackers and the detections, and when a tracker is successfully associated to a detection, we treat this detection as the key-sample for this tracker. We present a dual motion model that incorporates the associated detections with the object dynamics. Then, a likelihood function provides different weights for the propagated and the newly created particles, reducing the effect of false positives and missed detections in the tracking process. In addition, we use generative and discriminative appearance models to maximize the appearance variation among the targets. The performance of the proposed algorithm compares favorably with that of the state-of-the-art approaches on three public sequences.

Online multi-person tracking based on global sparse collaborative representations

“…Multi-object tracking can be performed either offline [1,2], using past and future frames usually in a batch setting, or online [3,4,5,6]. Online algorithms are more suitable for time critical applications and remain competitive with offline methods, as shown by some papers [7,8].…”

“…Even though the first trackers based on sparse representations could not fulfill real time constraints, this problem has been handled with compressed sensing techniques as shown in [12]. Inspired by these methods, sparse representations have been used recently in MOT for designing target-specific models [3].…”

Improving Multi-frame Data Association with Sparse Representations for Robust Near-online Multi-object Tracking

“…Our approach is inspired by [3,27,28], but instead of relying on sparse representations induced by the standard l 1 norm, we design a sparsity-inducing norm, based on a weighted l ∞,1 norm, more suited for a multi-frame data association problem.…”

“…In [28], such models are used in an online tracking method based on a particle filter. However, as many specific and independent models as the number of targets are necessary.…”

“…Each candidate for the new target location is then represented by a sparse linear combination of the dictionary elements, the best reconstruction error being used as the selection criterion. However, only a few recent methods have considered extending these models for online MOT systems [3,27,28].…”