Online CNN-based multiple object tracking with enhanced model updates and identity association

Gan, Weihao; Wang, Shuo; Lei, Xuejing; Lee, Ming-Sui; Kuo, C.-C. Jay

doi:10.1016/j.image.2018.05.008

Cited by 25 publications

(10 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Appearance Variations, Drifting and Identity Switching CNN + Data Association [30] Joint inference network [66] cross correlation CNN + scale aware attention network [31] LSTM + Bayesian filtering network [67] CNN + LSTM + Attention network [32] CNN [4] Distance and Long Occlusions Handling CNN [68] CNN [69] Detection and Target Association Kalman Filter + Hungarian Algorithm [33] CNN [70] CNN + GMPHD [71] Affinity…”

Section: Methodology Deep Learning Algorithms + Network Yearmentioning

confidence: 99%

“…There are two approaches the distance and long occlusion handling. Based on single CNNs, Gan et al combined cues of multiple features to assign IDs to tracked targets and stores them [68] in memory for model updates. If the object is missing, the target is removed, and the target is tracked until target-out.…”

Section: Distance and Long Occlusions Handlingmentioning

confidence: 99%

“…For the MOT16 benchmark dataset, RelationTrack [56] [68], which obtained IDSw of 560, FP of 7912, and Frag of 1212.…”

Section: Evaluation Of Multiple Objects Tracking Benchmark Datasetsmentioning

confidence: 99%

“…Figure13. The model proposed in the paper of category distance and long occlusion handling[68] using the MOT15 Benchmark[8].…”

mentioning

confidence: 99%

See 3 more Smart Citations

Multiple Object Tracking in Deep Learning Approaches: A Survey

et al. 2021

View full text Add to dashboard Cite

Object tracking is a fundamental computer vision problem that refers to a set of methods proposed to precisely track the motion trajectory of an object in a video. Multiple Object Tracking (MOT) is a subclass of object tracking that has received growing interest due to its academic and commercial potential. Although numerous methods have been introduced to cope with this problem, many challenges remain to be solved, such as severe object occlusion and abrupt appearance changes. This paper focuses on giving a thorough review of the evolution of MOT in recent decades, investigating the recent advances in MOT, and showing some potential directions for future work. The primary contributions include: (1) a detailed description of the MOT’s main problems and solutions, (2) a categorization of the previous MOT algorithms into 12 approaches and discussion of the main procedures for each category, (3) a review of the benchmark datasets and standard evaluation methods for evaluating the MOT, (4) a discussion of various MOT challenges and solutions by analyzing the related references, and (5) a summary of the latest MOT technologies and recent MOT trends using the mentioned MOT categories.

show abstract

Section: Methodology Deep Learning Algorithms + Network Yearmentioning

confidence: 99%

Section: Distance and Long Occlusions Handlingmentioning

confidence: 99%

See 2 more Smart Citations

Multiple Object Tracking in Deep Learning Approaches: A Survey

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The RNN network forms the connections between nodes in different frames to create a directed graph over a sequence to generate the trajectories. Convolutional neural networks (CNNs) have been recently used for multiple object detection and tracking purposes [16,17]. The CNN is a class of deep feedforward artificial neural networks, trending classifiers for MOT and other computer vision applications due to comparatively less preprocessing requirements compared to other image classification algorithms.…”

Section: Introductionmentioning

confidence: 99%

Low-cost multiple object tracking for embedded vision applications

Shehzad¹,

Karam²,

Azmat³

2019

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

This paper presents a low-cost multiple object tracking (MOT) technique by employing a novel appearance update model for object appearance modeling using K-means. The state-of-the-art work has attained a very high accuracy without considering the real-time aspects necessitated by currently trending embedded vision platforms. The major research on multiple object tracking is used to update the appearance model in every frame while discounting its persistent nature. The proposed appearance update model reduces the computational cost of the state-of-the-art MOT 6-fold by exploiting this facet of persistent appearance over the sequence of frames. To ensure accuracy, the proposed model is tested on different publicly available standard datasets with challenging situations for both indoor and outdoor scenarios. The experimental results illustrate that our model successfully achieves multiple object tracking while coping with long-term and complete occlusion. The proposed method achieves the same accuracy in comparison with the state-of-the-art baseline methods. Moreover, and most importantly, the proposed method is cost-effective in terms of computing and/or memory requirements in comparison to the state-of-the-art techniques. All these traits make our design very suitable for real-time and embedded video surveillance applications with low computing/memory resources.

show abstract

Multiple frequency–spatial network for RGBT tracking in the presence of motion blur

Fan,

Chen,

et al. 2023

Neural Comput & Applic

View full text Add to dashboard Cite

Online CNN-based multiple object tracking with enhanced model updates and identity association

Cited by 25 publications

References 25 publications

Multiple Object Tracking in Deep Learning Approaches: A Survey

Multiple Object Tracking in Deep Learning Approaches: A Survey

Low-cost multiple object tracking for embedded vision applications

Multiple frequency–spatial network for RGBT tracking in the presence of motion blur

Contact Info

Product

Resources

About