Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking Trackers

• URL: http://arxiv.org/abs/2111.08954v3
• Date: Tue, 4 Apr 2023 06:43:35 GMT
• Title: Tracklet-Switch Adversarial Attack against Pedestrian Multi-Object Tracking Trackers
• Authors: Delv Lin, Qi Chen, Chengyu Zhou, Kun He
• Abstract summary: We propose a novel adversarial attack method called Tracklet-Switch (TraSw) against the complete tracking pipeline of Multi-Object Tracking (MOT) Experiments show that TraSw can achieve an extraordinarily high success attack rate of over 95% by attacking only four frames on average.
• Score: 14.135239008740173
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-Object Tracking (MOT) has achieved aggressive progress and derived many excellent deep learning trackers. Meanwhile, most deep learning models are known to be vulnerable to adversarial examples that are crafted with small perturbations but could mislead the model prediction. In this work, we observe that the robustness on the MOT trackers is rarely studied, and it is challenging to attack the MOT system since its mature association algorithms are designed to be robust against errors during the tracking. To this end, we analyze the vulnerability of popular MOT trackers and propose a novel adversarial attack method called Tracklet-Switch (TraSw) against the complete tracking pipeline of MOT. The proposed TraSw can fool the advanced deep pedestrian trackers (i.e., FairMOT and ByteTrack), causing them fail to track the targets in the subsequent frames by perturbing very few frames. Experiments on the MOT-Challenge datasets (i.e., 2DMOT15, MOT17, and MOT20) show that TraSw can achieve an extraordinarily high success attack rate of over 95% by attacking only four frames on average. To our knowledge, this is the first work on the adversarial attack against the pedestrian MOT trackers. Code is available at https://github.com/JHL-HUST/TraSw .

Related papers

• Comparative study of multi-person tracking methods [0.0]
  The purpose of this study is to discover the techniques used and to provide useful insights about these algorithms in the tracking pipeline. We trained our own Pedestrian Detection model using the MOT17Det dataset. We then present experimental results which shows that Tracktor++ is a better multi-person tracking algorithm than SORT.
  arXiv  Detail & Related papers  (2023-10-07T14:29:57Z)
• Immortal Tracker: Tracklet Never Dies [50.97679119367842]
  Previous online 3D Multi-Object Tracking(DMOT) methods terminate a tracklet when it is not associated with new detections for a few frames. We reveal that premature tracklet termination is the main cause of identity switches in modern 3DMOT systems. We propose Immortal Tracker, a simple tracking system that utilizes trajectory prediction to maintain tracklets for objects gone dark.
  arXiv  Detail & Related papers  (2021-11-26T18:53:18Z)
• Learning to Track Objects from Unlabeled Videos [63.149201681380305]
  In this paper, we propose to learn an Unsupervised Single Object Tracker (USOT) from scratch. To narrow the gap between unsupervised trackers and supervised counterparts, we propose an effective unsupervised learning approach composed of three stages. Experiments show that the proposed USOT learned from unlabeled videos performs well over the state-of-the-art unsupervised trackers by large margins.
  arXiv  Detail & Related papers  (2021-08-28T22:10:06Z)
• Split and Connect: A Universal Tracklet Booster for Multi-Object Tracking [33.23825397557663]
  Multi-object tracking (MOT) is an essential task in the computer vision field. In this paper, a tracklet booster algorithm is proposed, which can be built upon any other tracker. The motivation is simple and straightforward: split tracklets on potential ID-switch positions and then connect multiple tracklets into one if they are from the same object.
  arXiv  Detail & Related papers  (2021-05-06T03:49:19Z)
• Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking [83.75789829291475]
  We introduce a probabilistic autoregressive motion model to score tracklet proposals. This is achieved by training our model to learn the underlying distribution of natural tracklets. Our experiments demonstrate the superiority of our approach at tracking objects in challenging sequences.
  arXiv  Detail & Related papers  (2020-12-03T23:59:27Z)
• Efficient Adversarial Attacks for Visual Object Tracking [73.43180372379594]
  We present an end-to-end network FAN (Fast Attack Network) that uses a novel drift loss combined with the embedded feature loss to attack the Siamese network based trackers. Under a single GPU, FAN is efficient in the training speed and has a strong attack performance.
  arXiv  Detail & Related papers  (2020-08-01T08:47:58Z)
• ArTIST: Autoregressive Trajectory Inpainting and Scoring for Tracking [80.02322563402758]
  One of the core components in online multiple object tracking (MOT) frameworks is associating new detections with existing tracklets. We introduce a probabilistic autoregressive generative model to score tracklet proposals by directly measuring the likelihood that a tracklet represents natural motion.
  arXiv  Detail & Related papers  (2020-04-16T06:43:11Z)
• Cooling-Shrinking Attack: Blinding the Tracker with Imperceptible Noises [87.53808756910452]
  A cooling-shrinking attack method is proposed to deceive state-of-the-art SiameseRPN-based trackers. Our method has good transferability and is able to deceive other top-performance trackers such as DaSiamRPN, DaSiamRPN-UpdateNet, and DiMP.
  arXiv  Detail & Related papers  (2020-03-21T07:13:40Z)

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.