Correlation Filter Selection for Visual Tracking Using Reinforcement Learning

Xie, Yanchun; Xiao, Jimin; Huang, Kaizhu; Thiyagalingam, Jeyarajan; Zhao, Yao

doi:10.1109/tcsvt.2018.2889488

Cited by 24 publications

(11 citation statements)

References 50 publications

(95 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Semantic segmentation is an important task in computer vision (Wei et al 2018;Xiao et al 2019;Xie et al 2018), which requires to predict pixel-level classification. Long et al (Long, Shelhamer, and Darrell 2015) proposed the first fully convolutional network for semantic segmentation.…”

Section: Related Workmentioning

confidence: 99%

Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach

Zhang

Xiao

Wei

et al. 2020

AAAI

Self Cite

181

140

View full text Add to dashboard Cite

Weakly supervised semantic segmentation is a challenging task as it only takes image-level information as supervision for training but produces pixel-level predictions for testing. To address such a challenging task, most recent state-of-the-art approaches propose to adopt two-step solutions, i.e. 1) learn to generate pseudo pixel-level masks, and 2) engage FCNs to train the semantic segmentation networks with the pseudo masks. However, the two-step solutions usually employ many bells and whistles in producing high-quality pseudo masks, making this kind of methods complicated and inelegant. In this work, we harness the image-level labels to produce reliable pixel-level annotations and design a fully end-to-end network to learn to predict segmentation maps. Concretely, we firstly leverage an image classification branch to generate class activation maps for the annotated categories, which are further pruned into confident yet tiny object/background regions. Such reliable regions are then directly served as ground-truth labels for the parallel segmentation branch, where a newly designed dense energy loss function is adopted for optimization. Despite its apparent simplicity, our one-step solution achieves competitive mIoU scores (val: 62.6, test: 62.9) on Pascal VOC compared with those two-step state-of-the-arts. By extending our one-step method to two-step, we get a new state-of-the-art performance on the Pascal VOC (val: 66.3, test: 66.5).

show abstract

Section: Related Workmentioning

confidence: 99%

Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach

Zhang

Xiao

Wei

et al. 2020

AAAI

Self Cite

181

140

View full text Add to dashboard Cite

show abstract

“…Shadow detection methods are based on shadow features and geometric models. Among them, the detection method based on shadow feature is to process the image by detecting the geometric feature, color, and brightness of shadow [ 14 ]. Because the existence of shadows only affects the brightness of pixels, it does not have much influence on the color of pixels.…”

Section: Target Tracking Algorithmmentioning

confidence: 99%

“…The mean-shift algorithm is a semi-automatic tracking method, which selects the moving target by manually determining the search window in the initial tracking frame [ 15 ]. The histogram distribution of the search window weighted by the kernel function is calculated, and the histogram distribution of the corresponding window of the current frame is calculated by the same method.…”

Section: Target Tracking Algorithmmentioning

confidence: 99%

Visual Sequence Algorithm for Moving Object Tracking and Detection in Images

Ren

Liu

Yu³

2021

Contrast Media & Molecular Imaging

View full text Add to dashboard Cite

Objective. The effects of different algorithms on detecting and tracking moving objects in images based on computer vision technology are studied, and the best algorithm scheme is confirmed. Methods. An automatic moving target detection and tracking algorithm based on the improved frame difference method and mean-shift was proposed to test whether the improved algorithm has improved the detection and tracking effect of moving targets. The algorithm improves the traditional three-frame difference method and introduces a single Gaussian background model to participate in target detection. The improved frame difference method is used to detect the target, and the position window and center of the target are determined. Combined with the mean-shift algorithm, it is determined whether the template needs to be updated according to whether it exceeds the set threshold so that the algorithm can automatically track the moving target. Results. The position and size of the search window change as the target location and size change. The Bhattacharyya similarity measure ρ (y) exceeds the threshold r, and the target detection algorithm is successfully restarted. Conclusion. The algorithm for automatic detection and tracking of moving objects based on the improved frame difference method and mean-shift is fast and has high accuracy.

show abstract

“…Robot [147,151,156,184] Computer vision [185][186][187][188][189][190] Game [191][192][193] Autonomous driving [185,186]…”

Section: Learningmentioning

confidence: 99%

Object Detection Recognition and Robot Grasping Based on Machine Learning: A Survey

Bai

Yang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

With the rapid development of machine learning, its powerful function in the machine vision field is increasingly reflected. The combination of machine vision and robotics to achieve the same precise and fast grasping as that of humans requires high-precision target detection and recognition, location and reasonable grasp strategy generation, which is the ultimate goal of global researchers and one of the prerequisites for the large-scale application of robots. Traditional machine learning has a long history and good achievements in the field of image processing and robot control. The CNN (convolutional neural network) algorithm realizes training of large-scale image datasets, solves the disadvantages of traditional machine learning in large datasets, and greatly improves accuracy, thereby positioning CNNs as a global research hotspot. However, the increasing difficulty of labeled data acquisition limits their development. Therefore, unsupervised learning, self-supervised learning and reinforcement learning, which are less dependent on labeled data, have also undergone rapid development and achieved good performance in the fields of image processing and robot capture. According to the inherent defects of vision, this paper summarizes the research achievements of tactile feedback in the fields of target recognition and robot grasping and finds that the combination of vision and tactile feedback can improve the success rate and robustness of robot grasping. This paper provides a systematic summary and analysis of the research status of machine vision and tactile feedback in the field of robot grasping and establishes a reasonable reference for future research.

show abstract

Correlation Filter Selection for Visual Tracking Using Reinforcement Learning

Cited by 24 publications

References 50 publications

Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach

Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach

Visual Sequence Algorithm for Moving Object Tracking and Detection in Images

Object Detection Recognition and Robot Grasping Based on Machine Learning: A Survey

Contact Info

Product

Resources

About