SAFS: Object Tracking Algorithm Based on Self-Adaptive Feature Selection

Guo, Wenhua; Gao, Jiabao; Tian, Yanbin; Yu, Fan; Feng, Zuren

doi:10.3390/s21124030

Cited by 4 publications

(4 citation statements)

References 28 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Object tracking can reduce the missed detection in object detection. The main object tracking algorithms include correlation filter tracking [24][25][26][27][28][29] and non-correlation filter tracking [30][31][32][33][34]. For correlation filter tracking algorithms, Bolme et al [27] propose the minimum output sum of squared error (MOSSE) filter.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Moving Object Detection and Tracking by Event Frame from Neuromorphic Vision Sensors

Zhao

Cai

et al. 2022

Biomimetics

View full text Add to dashboard Cite

Fast movement of objects and illumination changes may lead to a negative effect on camera images for object detection and tracking. Event cameras are neuromorphic vision sensors that capture the vitality of a scene, mitigating data redundancy and latency. This paper proposes a new solution to moving object detection and tracking using an event frame from bio-inspired event cameras. First, an object detection method is designed using a combined event frame and a standard frame in which the detection is performed according to probability and color, respectively. Then, a detection-based object tracking method is proposed using an event frame and an improved kernel correlation filter to reduce missed detection. Further, a distance measurement method is developed using event frame-based tracking and similar triangle theory to enhance the estimation of distance between the object and camera. Experiment results demonstrate the effectiveness of the proposed methods for moving object detection and tracking.

show abstract

Section: Introductionmentioning

confidence: 99%

“…The structural sparse tracking (SST) algorithm [34] uses the inherent relationship between the local object patches and the global object to learn sparse representation together. The object location is estimated based on the object dictionary template and the corresponding block with the largest similarity score from all particles [30,32].…”

Section: Introductionmentioning

confidence: 99%

Moving Object Detection and Tracking by Event Frame from Neuromorphic Vision Sensors

Zhao

Cai

et al. 2022

Biomimetics

View full text Add to dashboard Cite

show abstract

“…In the target tracking task, the target being tracked is arbitrary, and the traditional trackers designed based on manual features [2] perform generally in target modeling. Thanks to the powerful generalization ability of depth features, which can model all kinds of targets well, depth feature-based trackers [3][4][5] have achieved excellent results in recent years.…”

Section: Introductionmentioning

confidence: 99%

Lightweight Target-Aware Attention Learning Network-Based Target Tracking Method

et al. 2022

View full text Add to dashboard Cite

Siamese network trackers based on pre-trained depth features have achieved good performance in recent years. However, the pre-trained depth features are trained in advance on large-scale datasets, which contain feature information of a large number of objects. There may be a pair of interference and redundant information for a single tracking target. To learn a more accurate target feature information, this paper proposes a lightweight target-aware attention learning network to learn the most effective channel features of the target online. The lightweight network uses a designed attention learning loss function to learn a series of channel features with weights online with no complex parameters. Compared with the pre-trained features, the channel features with weights can represent the target more accurately. Finally, the lightweight target-aware attention learning network is unified into a Siamese tracking network framework to implement target tracking effectively. Experiments on several datasets demonstrate that the tracker proposed in this paper has good performance.

show abstract

“…Most deep-learning-based trackers [17][18][19][20] take the target as a positive sample, and some randomly selected areas from around the target as negative samples, during training, and then use CNN networks to extract features from these samples to train and learn a classifier. Although some existing Siamese-based trackers achieved an excellent tracking performance, we note that pre-trained deep features are more effective for target recognition and do not perform well enough for target-tracking tasks.…”

Section: Introductionmentioning

confidence: 99%

Discriminative Siamese Tracker Based on Multi-Channel-Aware and Adaptive Hierarchical Deep Features

et al. 2021

View full text Add to dashboard Cite

Most existing Siamese trackers mainly use a pre-trained convolutional neural network to extract target features. However, due to the weak discrimination of the target and background information of pre-trained depth features, the performance of the Siamese tracker can be significantly degraded when facing similar targets or changes in target appearance. This paper proposes a multi-channel-aware and adaptive hierarchical deep features module to enhance the discriminative ability of the tracker. Firstly, through the multi-channel-aware deep features module, the importance values of feature channels are obtained from both the target details and overall information, to identify more important feature channels. Secondly, by introducing the adaptive hierarchical deep features module, the importance of each feature layer can be determined according to the response value of each frame, so that the hierarchical features can be integrated to represent the target, which can better adapt to changes in the appearance of the target. Finally, the proposed two modules are integrated into the Siamese framework for target tracking. The Siamese network used in this paper is a two-input branch symmetric neural network with two input branches, and they share the same weights, which are widely used in the field of target tracking. Experiments on some Benchmarks show that the proposed Siamese tracker has several points of improvement compared to the baseline tracker.

show abstract

SAFS: Object Tracking Algorithm Based on Self-Adaptive Feature Selection

Cited by 4 publications

References 28 publications

Moving Object Detection and Tracking by Event Frame from Neuromorphic Vision Sensors

Moving Object Detection and Tracking by Event Frame from Neuromorphic Vision Sensors

Lightweight Target-Aware Attention Learning Network-Based Target Tracking Method

Discriminative Siamese Tracker Based on Multi-Channel-Aware and Adaptive Hierarchical Deep Features

Contact Info

Product

Resources

About