IOU – Siamtrack: IOU Guided Siamese Network For Visual Object Tracking

Dasari, Mohana Murali; Gorthi, Rama Krishna Sai Subrahmanyam

doi:10.1109/icip40778.2020.9191188

Cited by 10 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other trackers such as [25], [30], we do incorporate IOU loss term L iou as in Eq-( 2) into the proposed framework. In the baseline, Siamese RPN++ tracker learning relies only on the regression bounding box, in addition to the classification scores, but does not explicitly employ the bbox IOU information as in the other state-of-the-art trackers [25], [26], [27]. We note that trackers learning using IOU of the ground truth and the predicted boxes had effective localization capability and better tracking performance.…”

Section: Iou Guided Bounding Box Regressionmentioning

confidence: 99%

“…Inspired by the recent developments in SiamRPN variants [26], [27]. Other trackers such as [25], [30], we do incorporate IOU loss term L iou as in Eq-( 2) into the proposed framework.…”

Section: Iou Guided Bounding Box Regressionmentioning

confidence: 99%

“…SiamFC [29] 0.597 0.809 SiamFC-SD [17] 0.610 0.808 SiamMFA [37] 0.618 0.818 OAPT [21] 0.624 0.851 SiamBAN [27] 0.624 0.853 IOU-SiamTrack [26] 0.635 0.862 SiamON [20] 0.644 0.854 SiamRPN++ [1] 0.647 0.855 GOA-Net (RPN) 0.664 0.874 ATOM [25] 0.669 0.883 TransT [4] 0.675 0.879 GOA-Net (TED) 0.679 0.883 ECO [35] 0.693 0.913 SiamRCNN [15] 0.703 0.894 GOA-Net on the OTB2015 dataset is reported in Table 4. It can be noted that GOA-Net (RPN) has a 2% improvement in both Success and Precision metrics compared to the base tracker.…”

Section: Tracker Success↑ Precision↑mentioning

confidence: 99%

“…Success↑ Precision↑ ECO [35] 0.525 0.741 SiamFC [29] 0.523 0.731 SiamFC-SD [17] 0.535 0.736 IOU-SiamTrack [26] 0.549 0.748 SiamON [20] 0.568 0.774 SiamBAN [27] 0.584 0.772 SiamRPN++ [1] 0.584 0.780 DaSiamRPN [3] 0.585 0.795 GOA-Net (RPN) 0.598 0.791 SiamRCNN [15] 0.649 0.834 TransT [4] 0.663 0.860 TMSDA [38] 0.676 -GOA-Net (TED) 0.678 0.875 respectively. This table reiterates the substantial performance improvement of both GOA-Net frameworks over the existing Siamese Occlusion Network (SiamON) [20] framework.…”

Section: Trackermentioning

confidence: 99%

See 3 more Smart Citations

GOA-Net: Generic Occlusion Aware Networks for Visual Tracking

Dasari,

Gorthi

2023

Preprint

Self Cite

View full text Add to dashboard Cite

Occlusionis a frequent phenomenon that hinders the task of visual object tracking. Since occlusion can be from any object and in any shape, data augmentation techniques will not greatly help identify or mitigate the tracker loss. Some of the existing works deal with occlusion only in an unsupervised manner. This paper proposes a generic deep learning framework for identifying occlusion in a given frame by formulating it as a supervised classification task for the first time. The proposed architecture introduces an ''occlusion classification" branch into supervised trackers. This branch helps in the effective learning of features and also provides occlusion status for each frame. A metric is proposed to measure the performance of trackers under occlusion at frame level. The efficacy of the proposed framework is demonstrated on two supervised tracking paradigms: One is from the most commonly used Siamese region proposal class of trackers, and another from the emerging Transformer-based trackers. This framework is tested on six diverse datasets (GOT-10k, LaSOT, OTB2015, TrackingNet, UAV123, and VOT2018), and it achieved significant improvements in performance over the corresponding baselines while performing on par with the state-of-the-art trackers. The contributions in this work are more generic, as any supervised tracker can easily adopt them.

show abstract

Section: Iou Guided Bounding Box Regressionmentioning

confidence: 99%

“…Inspired by the recent developments in SiamRPN variants [26], [27]. Other trackers such as [25], [30], we do incorporate IOU loss term L iou as in Eq-( 2) into the proposed framework.…”

Section: Iou Guided Bounding Box Regressionmentioning

confidence: 99%

Section: Tracker Success↑ Precision↑mentioning

confidence: 99%

Section: Trackermentioning

confidence: 99%

See 2 more Smart Citations

GOA-Net: Generic Occlusion Aware Networks for Visual Tracking

Dasari,

Gorthi

2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In addition to the characteristic attributes of the commodity itself, the generated commodity location-related information is extracted in the case of commodity occlusion and is imported into the scale-adaptive module. The detection frame is generated adaptively through K-means++ clustering, following which the distance measurement loss regression of the intersection over union (IOU) [18]- [20] is used to reduce the impact of the redundant features. The commodity detection frame is constructed using the channel correlation of the attention mechanism [21].…”

Section: Introductionmentioning

confidence: 99%

Detection of Commodities Based on Multi-Feature Fusion and Attention Screening by Entropy Function Guidance

Xie,

Dong

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Although traditional convolutional neural networks (CNN) have been significantly improved for target detection, they cannot be completely applied to objects with occlusions in commodity detection. Therefore, we propose a target detection method based on an improved YOLOv5 model and an improved attention mechanism algorithm is proposed to solve the commodity occlusion problem. This method improves the traditional YOLO deep convolution network, features a more detailed BiFPN layer, and performs lightweight two-way feature fusion, where the multidimensional features of the commodities are convolved and fused, thus improving the overall detection speed and accuracy of the YOLO-R algorithm. Feature entropy is introduced to the attention channel to restrict the threshold value and obtain the global information of the occlusion target. The global information obtained is fused with a bidirectional feature pyramid layer to enhance the robustness of the features. This method could accurately and quickly detect the occluded commodities and the detection accuracy has been greatly improved. Experiments show that the improved YOLO-R model can improve the accuracy and speed of commodity detection, and can achieve good results in objective evaluation. The average accuracy of commodity detection on the selfmade product dataset is up to 97.80%, and the detection rate is 22.72F/s. Therefore, the method in this paper has high detection accuracy and fast detection speed.INDEX TERMS Lightweight feature fusion, attention channel, feature entropy, bidirectional feature.

show abstract

GOA-net: generic occlusion aware networks for visual tracking

Dasari,

Gorthi

2024

Machine Vision and Applications

View full text Add to dashboard Cite

IOU – Siamtrack: IOU Guided Siamese Network For Visual Object Tracking

Cited by 10 publications

References 13 publications

GOA-Net: Generic Occlusion Aware Networks for Visual Tracking

GOA-Net: Generic Occlusion Aware Networks for Visual Tracking

Detection of Commodities Based on Multi-Feature Fusion and Attention Screening by Entropy Function Guidance

GOA-net: generic occlusion aware networks for visual tracking

Contact Info

Product

Resources

About