Multi-target tracking by on-line learned discriminative appearance models

By Cheng-Hao Kuo, Chang Huang, Ramkant Nevatia. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010

333 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/f719c5418cce7c142bc46db9bf2c60f63dbfacad

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

People reidentification in surveillance and forensics (2013, neutral): “Indoor/Outdoor Single Color [several], Shape, Texture, Position 2D - grids Viper, p.v. [Kuo et al. 2010] Same Calib.”
Part-based multiple-person tracking with partial occlusion handling (2012, methodology): “Therefore, several techniques [23, 13, 3, 5] were proposed to tackle multi-target tracking by optimizing detection assignments over a temporal window, given certain global constraints.”
Context tracker: Exploring supporters and distracters in unconstrained environments (2011, methodology): “In MTT, most methods employ an object detector [21, 17] or background subtraction [29] to find possible object responses, whereas in our case, we automat-”
Multi-target tracking by learning local-to-global trajectory models (2015, background): “Please cite this article as: S. Zhang, et al., Multi-target tracking by learning local-to-global trajectory models, Pattern Recognition (2014), http://dx.doi.org/10.1016/j.patcog.2014.08.013i approaches can do better to overcome errors by detections and association.”
Deep Affinity Network for Multiple Object Tracking (2018, background): “The appearance models focus on computing easy-to-track object features that encode appearances of local regions of objects or their bounding boxes [20], [21], [22].”
Multiobject tracking as maximum weight independent set (2011, background): “, color, posture, speed, direction) [13, 1, 23, 11, 14], as well as spatiotemporal context [15], supporting evidence from neighboring tracks [9], and estimates of an occluder map [10] and 3D scene layout [4].”
Multiple object tracking: A literature review (2014, methodology): “Other examples of this strategy are [1], [7], [58], [59], [60], [99].”
The Way They Move: Tracking Multiple Targets with Similar Appearance (2013, background): “However, these algorithms do not perform as well when targets have similar appearance, do not move with the assumed dynamics, or come out in the middle of the field of view as in the example shown in Figure 1.”
An online learned CRF model for multi-target tracking (2012, methodology): “The human detection results are the same as used in [19, 7, 8], and are provided by courtesy of authors of [8].”
Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor (2015, background): “Due to the limited amount of observation, the tracking algorithm may produce an erroneous association at t2.”
Learning to Track: Online Multi-object Tracking by Decision Making (2015, methodology): “Recently, there is a trend on learning to track that advocates the concept of injecting learning capabilities to MOT [38, 25, 22, 20, 4].”
Crowded Scene Analysis: A Survey (2015, methodology): “In previous works [62]–[64], tracklets have been mainly used”
Continuous Energy Minimization for Multitarget Tracking (2014, background): “ignored [2], [4], [7], or addressed only in the discrete setting [26], [34], [43].”
Deep Network Flow for Multi-object Tracking (2017, background): “Association problems in MOT: Recent works on multi-object tracking (MOT) mostly follow the tracking-by-detection paradigm [3, 7, 10, 15, 26, 33, 41], where objects are ﬁrst detected in each frame and then associated over time to form trajectories for each object instance.”
Visual Tracking: an Experimental Survey (2013, neutral): “The selection in [30] is restricted to 28 different videos.”
GSM: Graph Similarity Model for Multi-Object Tracking (2020, background): “Many early works extracted hand-craft appearance feature such as raw pixel template [ Yamaguchi et al. , 2011; Pellegrini et al. , 2009 ] , color histogram [ Izadinia et al. , 2012; Xiang et al. , 2015 ] , HOG [ Izadinia et al. , 2012; Kuo et al. , 2010 ] and so on.”
Multiple Hypothesis Tracking Revisited (2015, background): “In tracklet association, several works [2, 42, 21, 22] train discriminative appearance models of tracklets in order to design a better affinity score function.”
Online Multiperson Tracking-by-Detection from a Single, Uncalibrated Camera (2011, methodology): “In contrast, our method exploits the classifiers in each time step similarly to the very recent work of Kuo et al. [23], using it both for data association and for the observation model.”
Sparse coding based visual tracking: Review and experimental comparison (2013, methodology): “Kuo et al. [14] proposed an AdaBoost based algorithm to learn a discriminative appearance model for multi-target tracking, which allows the model to adapt to target appearance variations over time.”