Siamese Contour Segmentation Network for Multi-State Object Tracking
Open Access
- 7 November 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 126634-126642
Abstract
Tracking multiple states of the target simultaneously is currently a research hotspot in object tracking. Existing methods obtain the initial bounding box with multi-scale search, anchor-based regression, or anchor-free regression. Then, each pixel within bounding box is classified and the mask of target is used to fit a fine bounding box for accurate tracking. However, their computation complexity is high and the accuracy of mask and fine bounding box is limited by initial bounding box. Based on SiamMask, the Siamese contour segmentation network (SiamCS) is proposed for multi-state object tracking to address these issues. This end-to-end network eliminates need to pre-define anchor based on prior knowledge, and reduces hyperparameters. With SiamCS, multi-state object tracking method formulates object tracking as region classification and contour regression to obtain bounding box, contour, and mask of target at the same time. Moreover, according to geometric meaning of definite integral and difficulty of sample, difficulty sensitive contour-intersection over union loss function is proposed to solve the problem of independent regression of contour parameters. Extensive experiments on OTB100 (92.5%Precision), UAV123 (83.5%Precision), LaSOT (64.8%AUC), TrackingNet (81.5%AUC), GOT-10K (66.3%AO), and VOT2020 (53.5%EAO) show that SiamCS outperforms many state-of-the-art trackers and achieves leading performance.Keywords
This publication has 46 references indexed in Scilit:
- Hierarchical spatial-aware Siamese network for thermal infrared object trackingKnowledge-Based Systems, 2019
- Fully Convolutional Siamese Fusion Networks for Object Tracking2018
- High Performance Visual Tracking with Siamese Region Proposal Network2018
- Fast and Accurate Online Video Object Segmentation via Tracking Parts2018
- YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video2017
- Siamese Instance Search for Tracking2016
- UnitBox2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Object Tracking BenchmarkIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- A Decision-Theoretic Generalization of On-Line Learning and an Application to BoostingJournal of Computer and System Sciences, 1997