Cascaded Regression Tracking: Towards Online Hard Distractor Discrimination

• URL: http://arxiv.org/abs/2006.10336v1
• Date: Thu, 18 Jun 2020 07:48:01 GMT
• Title: Cascaded Regression Tracking: Towards Online Hard Distractor Discrimination
• Authors: Ning Wang, Wengang Zhou, Qi Tian, Houqiang Li
• Abstract summary: We propose a cascaded regression tracker with two sequential stages. In the first stage, we filter out abundant easily-identified negative candidates. In the second stage, a discrete sampling based ridge regression is designed to double-check the remaining ambiguous hard samples.
• Score: 202.2562153608092
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visual tracking can be easily disturbed by similar surrounding objects. Such objects as hard distractors, even though being the minority among negative samples, increase the risk of target drift and model corruption, which deserve additional attention in online tracking and model update. To enhance the tracking robustness, in this paper, we propose a cascaded regression tracker with two sequential stages. In the first stage, we filter out abundant easily-identified negative candidates via an efficient convolutional regression. In the second stage, a discrete sampling based ridge regression is designed to double-check the remaining ambiguous hard samples, which serves as an alternative of fully-connected layers and benefits from the closed-form solver for efficient learning. Extensive experiments are conducted on 11 challenging tracking benchmarks including OTB-2013, OTB-2015, VOT2018, VOT2019, UAV123, Temple-Color, NfS, TrackingNet, LaSOT, UAV20L, and OxUvA. The proposed method achieves state-of-the-art performance on prevalent benchmarks, while running in a real-time speed.

Related papers

• ConsistencyTrack: A Robust Multi-Object Tracker with a Generation Strategy of Consistency Model [20.259334882471574]
  Multi-object tracking (MOT) is a critical technology in computer vision, designed to detect multiple targets in video sequences and assign each target a unique ID per frame. Existed MOT methods excel at accurately tracking multiple objects in real-time across various scenarios. We propose a novel ConsistencyTrack, joint detection and tracking(JDT) framework that formulates detection and association as a denoising diffusion process on bounding boxes.
  arXiv  Detail & Related papers  (2024-08-28T05:53:30Z)
• Robust Visual Tracking via Iterative Gradient Descent and Threshold Selection [4.978166837959101]
  We introduce a novel robust linear regression estimator, which achieves favorable performance when the error vector follows i.i.d Gaussian-Laplacian distribution. In addition, we expend IGDTS to a generative tracker, and apply IGDTS-distance to measure the deviation between the sample and the model. Experimental results on several challenging image sequences show that the proposed tracker outperformance existing trackers.
  arXiv  Detail & Related papers  (2024-06-02T01:51:09Z)
• 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)
• ShaSTA: Modeling Shape and Spatio-Temporal Affinities for 3D Multi-Object Tracking [25.093138732809738]
  Multi-object tracking is a cornerstone capability of any robotic system. Detectors function in a low precision recall regime, ensuring a low number of false-negatives while producing a high rate of false-positives. We propose a method that learns shape andtemporal affinities between consecutive frames to better distinguish between true-positive and false-positive detections and tracks.
  arXiv  Detail & Related papers  (2022-11-08T00:20:38Z)
• Unsupervised Learning of Accurate Siamese Tracking [68.58171095173056]
  We present a novel unsupervised tracking framework, in which we can learn temporal correspondence both on the classification branch and regression branch. Our tracker outperforms preceding unsupervised methods by a substantial margin, performing on par with supervised methods on large-scale datasets such as TrackingNet and LaSOT.
  arXiv  Detail & Related papers  (2022-04-04T13:39:43Z)
• Unsupervised Noisy Tracklet Person Re-identification [100.85530419892333]
  We present a novel selective tracklet learning (STL) approach that can train discriminative person re-id models from unlabelled tracklet data. This avoids the tedious and costly process of exhaustively labelling person image/tracklet true matching pairs across camera views. Our method is particularly more robust against arbitrary noisy data of raw tracklets therefore scalable to learning discriminative models from unconstrained tracking data.
  arXiv  Detail & Related papers  (2021-01-16T07:31:00Z)
• 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)
• SADet: Learning An Efficient and Accurate Pedestrian Detector [68.66857832440897]
  This paper proposes a series of systematic optimization strategies for the detection pipeline of one-stage detector. It forms a single shot anchor-based detector (SADet) for efficient and accurate pedestrian detection. Though structurally simple, it presents state-of-the-art result and real-time speed of $20$ FPS for VGA-resolution images.
  arXiv  Detail & Related papers  (2020-07-26T12:32:38Z)
• 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)

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.