MP-LN: motion state prediction and localization network for visual object tracking

Fan, Chunxiao; Zhang, Runqing; Ming, Yue

doi:10.1007/s00371-021-02296-y

Cited by 8 publications

(4 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also conduct experiments to verify the effectiveness of the proposed M‐model further. We calculate the centre pixel error between the estimated search region and the ground‐truth [18] on the LaSOT test dataset, as shown in Figure 5.…”

Section: Methodsmentioning

confidence: 99%

“…We also conduct experiments to verify the effectiveness of the proposed M-model further. We calculate the centre pixel error between the estimated search region and the groundtruth [18] on the LaSOT test dataset, as shown in Figure 5. The baseline method depends on the motion state in the last frame, but occlusion makes the motion state stay at the location where the target disappears, leading to an inaccurate search region.…”

Section: Ablation Studymentioning

confidence: 99%

“…Methods based on the Markov Chain: To complement incomplete appearance information with a continuous motion state, tracking methods [18][19][20] use motion state prediction to estimate the target motion trend. However, using a convolution network for motion state prediction increases the computational load.…”

Section: Motion Modelmentioning

confidence: 99%

See 2 more Smart Citations

M‐CoTransT: Adaptive spatial continuity in visual tracking

Fan

Zhang

Ming

2022

IET Computer Vision

Self Cite

View full text Add to dashboard Cite

Visual tracking is an important area in computer vision. Based on the Siamese network, current tracking methods employ the self-attention block in convolutional networks to extract semantic features containing the image structure information of an object. However, spatial continuity is a point of contradiction between two seemingly unrelated challenges, that is, occlusion and similar distractor, in tracking methods. At the same time, it is a spatially discontinuous task to locate a target reappearing after occlusion accurately. The prediction of bounding boxes should be constrained by spatial continuity to prevent them from jumping into similar distractors. This study proposes a novel tracking method for introducing spatial continuity in visual tracking called M-CoTransT; the novel tracking method is developed through the confidence-based adaptive Markov motion model (M-model) and a novel correlation-based feature fusion network (CoTransT). In particular, the M-model provides confidence for the nodes of the Markov motion model to estimate the motion state continuity. It also predicts a more accurate search region for CoTransT, which then adds a cross-correlation branch into the self-attention tracking network to enhance the continuity of target appearance in the feature space. Extensive experiments on five challenging datasets (LaSOT, GOT-10k, TrackingNet, OTB-2015 and UAV123) demonstrated the effectiveness of the proposed M-CoTransT in visual tracking.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Ablation Studymentioning

confidence: 99%

See 1 more Smart Citation

M‐CoTransT: Adaptive spatial continuity in visual tracking

Fan

Zhang

Ming

2022

IET Computer Vision

Self Cite

View full text Add to dashboard Cite

show abstract

“…One of the main components of a VOT algorithm is its motion model, which generates search zones to look for target [46,47] in future frames. For the moving targets, some 2D motion models assume a completely fixed camera [48,49], while some others suppose a stationary but rotating one [50].…”

Section: Related Workmentioning

confidence: 99%

Probabilistic 3D motion model for object tracking in aerial applications

Mirtajadini,

Amiri Atashgah,

Shahbazi

2024

IET Image Processing

View full text Add to dashboard Cite

Visual object tracking, crucial in aerial applications such as surveillance, cinematography, and chasing, faces challenges despite AI advancements. Current solutions lack full reliability, leading to common tracking failures in the presence of fast motions or long‐term occlusions of the subject. To tackle this issue, a 3D motion model is proposed that employs camera/vehicle states to locate a subject in the inertial coordinates. Next, a probability distribution is generated over future trajectories and they are sampled using a Monte Carlo technique to provide search regions that are fed into an online appearance learning process. This 3D motion model incorporates machine‐learning approaches for direct range estimation from monocular images. The model adapts computationally by adjusting search areas based on tracking confidence. It is integrated into DiMP, an online and deep learning‐based appearance model. The resulting tracker is evaluated on the VIOT dataset with sequences of both images and camera states, achieving a 68.9% tracking precision compared to DiMP's 49.7%. This approach demonstrates increased tracking duration, improved recovery after occlusions, and faster motions. Additionally, this strategy outperforms random searches by about 3.0%.

show abstract

Learning Local Features of Motion Chain for Human Motion Prediction

Liu,

Chen,

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

MP-LN: motion state prediction and localization network for visual object tracking

Cited by 8 publications

References 46 publications

M‐CoTransT: Adaptive spatial continuity in visual tracking

M‐CoTransT: Adaptive spatial continuity in visual tracking

Probabilistic 3D motion model for object tracking in aerial applications

Learning Local Features of Motion Chain for Human Motion Prediction

Contact Info

Product

Resources

About