AutoTrack: Towards High-Performance Visual Tracking for UAV with Automatic Spatio-Temporal Regularization

• URL: http://arxiv.org/abs/2003.12949v1
• Date: Sun, 29 Mar 2020 05:02:25 GMT
• Title: AutoTrack: Towards High-Performance Visual Tracking for UAV with Automatic Spatio-Temporal Regularization
• Authors: Yiming Li, Changhong Fu, Fangqiang Ding, Ziyuan Huang, Geng Lu
• Abstract summary: Most existing trackers based on discriminative correlation filters (DCF) try to introduce predefined regularization term to improve the learning of target objects. In this work, a novel approach is proposed to online and automatically adaptively learn-temporal regularization term. Experiments on four UAV benchmarks have proven the superiority of our method compared to the state-of-the-art CPU- and GPU-based trackers.
• Score: 19.379240684856423
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most existing trackers based on discriminative correlation filters (DCF) try to introduce predefined regularization term to improve the learning of target objects, e.g., by suppressing background learning or by restricting change rate of correlation filters. However, predefined parameters introduce much effort in tuning them and they still fail to adapt to new situations that the designer did not think of. In this work, a novel approach is proposed to online automatically and adaptively learn spatio-temporal regularization term. Spatially local response map variation is introduced as spatial regularization to make DCF focus on the learning of trust-worthy parts of the object, and global response map variation determines the updating rate of the filter. Extensive experiments on four UAV benchmarks have proven the superiority of our method compared to the state-of-the-art CPU- and GPU-based trackers, with a speed of ~60 frames per second running on a single CPU. Our tracker is additionally proposed to be applied in UAV localization. Considerable tests in the indoor practical scenarios have proven the effectiveness and versatility of our localization method. The code is available at https://github.com/vision4robotics/AutoTrack.

Related papers

• Exploring Dynamic Transformer for Efficient Object Tracking [58.120191254379854]
  We propose DyTrack, a dynamic transformer framework for efficient tracking. DyTrack automatically learns to configure proper reasoning routes for various inputs, gaining better utilization of the available computational budget. Experiments on multiple benchmarks demonstrate that DyTrack achieves promising speed-precision trade-offs with only a single model.
  arXiv  Detail & Related papers  (2024-03-26T12:31:58Z)
• Fast-Slow Test-Time Adaptation for Online Vision-and-Language Navigation [67.18144414660681]
  We propose a Fast-Slow Test-Time Adaptation (FSTTA) approach for online Vision-and-Language Navigation (VLN) Our method obtains impressive performance gains on four popular benchmarks.
  arXiv  Detail & Related papers  (2023-11-22T07:47:39Z)
• Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features [69.47588461101925]
  We propose a method to adapt 3D object detectors to new driving environments. Our approach enhances LiDAR-based detection models using spatial quantized historical features. Experiments on real-world datasets demonstrate significant improvements.
  arXiv  Detail & Related papers  (2023-09-21T15:00:31Z)
• Sparse Regularized Correlation Filter for UAV Object Tracking with adaptive Contextual Learning and Keyfilter Selection [20.786475337107472]
  correlation filter has been widely applied in unmanned aerial vehicle (UAV) tracking. It is fragile because of two inherent defects, i.e. boundary effect and filter corruption. We propose a novel $ell_1$ regularization correlation filter with adaptive contextual learning and keyfilter selection.
  arXiv  Detail & Related papers  (2022-05-07T10:25:56Z)
• Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyond [82.37430109152383]
  We show that, current pedestrian detectors poorly handle even small domain shifts in cross-dataset evaluation. We attribute the limited generalization to two main factors, the method and the current sources of data. We propose a progressive fine-tuning strategy which improves generalization.
  arXiv  Detail & Related papers  (2022-01-10T06:00:26Z)
• Learning Residue-Aware Correlation Filters and Refining Scale Estimates with the GrabCut for Real-Time UAV Tracking [12.718396980204961]
  Unmanned aerial vehicle (UAV)-based tracking is attracting increasing attention and developing rapidly in applications such as agriculture, aviation, navigation, transportation and public security. Recently, discriminative correlation filters (DCF)-based trackers have stood out in UAV tracking community for their high efficiency and robustness on a single CPU. In this paper, we explore using segmentation by the GrabCut to improve the wildly adopted discriminative scale estimation in DCF-based trackers.
  arXiv  Detail & Related papers  (2021-04-07T13:35:01Z)
• DR^2Track: Towards Real-Time Visual Tracking for UAV via Distractor Repressed Dynamic Regression [18.044423448896143]
  In this work, we exploit the local maximum points of the response map generated in the detection phase to automatically locate current distractors. Substantial experiments conducted on three challenging UAV benchmarks demonstrate both excellent performance and extraordinary speed.
  arXiv  Detail & Related papers  (2020-08-10T06:08:31Z)
• Learning Consistency Pursued Correlation Filters for Real-Time UAV Tracking [12.292672531693794]
  This work proposes a novel approach with dynamic consistency pursued correlation filters, i.e., the CPCF tracker. By minimizing the difference between the practical and the scheduled ideal consistency map, the consistency level is constrained to maintain temporal smoothness. The proposed tracker favorably surpasses the other 25 state-of-the-art trackers with real-time running speed ($sim$43FPS) on a single CPU.
  arXiv  Detail & Related papers  (2020-08-09T10:22:52Z)
• Fully Convolutional Online Tracking [47.78513247048846]
  We present a fully convolutional online tracking framework, coined as FCOT, for both classification and regression branches. Our key contribution is to introduce an online regression model generator (RMG) for initializing weights of the target filter with online samples. Thanks to the unique design of RMG, our FCOT can not only be more effective in handling target variation along temporal dimension thus generating more precise results.
  arXiv  Detail & Related papers  (2020-04-15T14:21:57Z)
• Tracking Performance of Online Stochastic Learners [57.14673504239551]
  Online algorithms are popular in large-scale learning settings due to their ability to compute updates on the fly, without the need to store and process data in large batches. When a constant step-size is used, these algorithms also have the ability to adapt to drifts in problem parameters, such as data or model properties, and track the optimal solution with reasonable accuracy. We establish a link between steady-state performance derived under stationarity assumptions and the tracking performance of online learners under random walk models.
  arXiv  Detail & Related papers  (2020-04-04T14:16:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.