English
Related papers

Related papers: F-Siamese Tracker: A Frustum-based Double Siamese …

200 papers

Single Object Tracking in LiDAR point cloud is one of the most essential parts of environmental perception, in which small objects are inevitable in real-world scenarios and will bring a significant barrier to the accurate location.…

Computer Vision and Pattern Recognition · Computer Science 2024-01-25 Shengjing Tian , Yinan Han , Xiuping Liu , Xiantong Zhao

Siamese network based trackers develop rapidly in the field of visual object tracking in recent years. The majority of siamese network based trackers now in use treat each channel in the feature maps generated by the backbone network…

Computer Vision and Pattern Recognition · Computer Science 2023-03-23 Jiahao Bao , Kaiqiang Chen , Xian Sun , Liangjin Zhao , Wenhui Diao , Menglong Yan

3D single object tracking within LIDAR point clouds is a pivotal task in computer vision, with profound implications for autonomous driving and robotics. However, existing methods, which depend solely on appearance matching via Siamese…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Shaoyu Sun , Chunyang Wang , Xuelian Liu , Chunhao Shi , Yueyang Ding , Guan Xi

In this work, we propose a novel method termed \emph{Frustum ConvNet (F-ConvNet)} for amodal 3D object detection from point clouds. Given 2D region proposals in an RGB image, our method first generates a sequence of frustums for each region…

Computer Vision and Pattern Recognition · Computer Science 2019-08-15 Zhixin Wang , Kui Jia

In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to input scene size is significantly smaller compared to 2D detection cases. Overlooking this difference, many 3D detectors directly follow the common…

Computer Vision and Pattern Recognition · Computer Science 2021-12-14 Lue Fan , Ziqi Pang , Tianyuan Zhang , Yu-Xiong Wang , Hang Zhao , Feng Wang , Naiyan Wang , Zhaoxiang Zhang

In this paper we illustrate how to perform both visual object tracking and semi-supervised video object segmentation, in real-time, with a single simple approach. Our method, dubbed SiamMask, improves the offline training procedure of…

Computer Vision and Pattern Recognition · Computer Science 2019-05-07 Qiang Wang , Li Zhang , Luca Bertinetto , Weiming Hu , Philip H. S. Torr

High computational power and significant time are usually needed to train a deep learning based tracker on large datasets. Depending on many factors, training might not always be an option. In this paper, we propose a framework with two…

Computer Vision and Pattern Recognition · Computer Science 2024-10-16 Ali Sekhavati , Won-Sook Lee

Obviously, the object is the key factor of the 3D single object tracking (SOT) task. However, previous Siamese-based trackers overlook the negative effects brought by randomly dropped object points during backbone sampling, which hinder…

Computer Vision and Pattern Recognition · Computer Science 2023-01-31 Kaijie Zhao , Haitao Zhao , Zhongze Wang , Jingchao Peng , Zhengwei Hu

In this paper the research on optimisation of visual object tracking using a Siamese neural network for embedded vision systems is presented. It was assumed that the solution shall operate in real-time, preferably for a high resolution…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Dominika Przewlocka , Mateusz Wasala , Hubert Szolc , Krzysztof Blachut , Tomasz Kryjak

In this paper we introduce SiamMask, a framework to perform both visual object tracking and video object segmentation, in real-time, with the same simple method. We improve the offline training procedure of popular fully-convolutional…

Computer Vision and Pattern Recognition · Computer Science 2022-07-06 Weiming Hu , Qiang Wang , Li Zhang , Luca Bertinetto , Philip H. S. Torr

3D single object tracking in LiDAR point clouds (LiDAR SOT) plays a crucial role in autonomous driving. Current approaches all follow the Siamese paradigm based on appearance matching. However, LiDAR point clouds are usually textureless and…

Computer Vision and Pattern Recognition · Computer Science 2023-10-13 Chaoda Zheng , Xu Yan , Haiming Zhang , Baoyuan Wang , Shenghui Cheng , Shuguang Cui , Zhen Li

Current 3D single object tracking methods primarily rely on the Siamese matching-based paradigm, which struggles with textureless and incomplete LiDAR point clouds. Conversely, the motion-centric paradigm avoids appearance matching, thus…

Computer Vision and Pattern Recognition · Computer Science 2024-09-10 Yuxiang Yang , Yingqi Deng , Jing Zhang , Hongjie Gu , Zhekang Dong

Recently, there have been a plethora of classification and detection systems from RGB as well as 3D images. In this work, we describe a new 3D object detection system from an RGB-D or depth-only point cloud. Our system first detects objects…

Computer Vision and Pattern Recognition · Computer Science 2023-05-26 Xiaoke Shen , Ioannis Stamos

Offline Siamese networks have achieved very promising tracking performance, especially in accuracy and efficiency. However, they often fail to track an object in complex scenes due to the incapacity in online update. Traditional updaters…

Computer Vision and Pattern Recognition · Computer Science 2021-05-03 Xinglong Sun , Guangliang Han , Lihong Guo , Tingfa Xu , Jianan Li , Peixun Liu

As the perception range of LiDAR expands, LiDAR-based 3D object detection contributes ever-increasingly to the long-range perception in autonomous driving. Mainstream 3D object detectors often build dense feature maps, where the cost is…

Computer Vision and Pattern Recognition · Computer Science 2023-01-09 Lue Fan , Yuxue Yang , Feng Wang , Naiyan Wang , Zhaoxiang Zhang

In online multi-target tracking, modeling of appearance and geometric similarities between pedestrians visual scenes is of great importance. The higher dimension of inherent information in the appearance model compared to the geometric…

Computer Vision and Pattern Recognition · Computer Science 2020-10-12 Young-Chul Yoon , Du Yong Kim , Young-min Song , Kwangjin Yoon , Moongu Jeon

3D multi-object tracking in LiDAR point clouds is a key ingredient for self-driving vehicles. Existing methods are predominantly based on the tracking-by-detection pipeline and inevitably require a heuristic matching step for the detection…

Computer Vision and Pattern Recognition · Computer Science 2021-08-24 Chenxu Luo , Xiaodong Yang , Alan Yuille

Region-based methods have become increasingly popular for model-based, monocular 3D tracking of texture-less objects in cluttered scenes. However, while they achieve state-of-the-art results, most methods are computationally expensive,…

Computer Vision and Pattern Recognition · Computer Science 2022-03-01 Manuel Stoiber , Martin Pfanne , Klaus H. Strobl , Rudolph Triebel , Alin Albu-Schäffer

Template-based discriminative trackers are currently the dominant tracking paradigm due to their robustness, but are restricted to bounding box tracking and a limited range of transformation models, which reduces their localization…

Computer Vision and Pattern Recognition · Computer Science 2021-12-28 Alan Lukežič , Jiří Matas , Matej Kristan

In this paper, we provide an intuitive viewing to simplify the Siamese-based trackers by converting the tracking task to a classification. Under this viewing, we perform an in-depth analysis for them through visual simulations and real…

Computer Vision and Pattern Recognition · Computer Science 2023-06-16 Xingping Dong , Jianbing Shen , Fatih Porikli , Jiebo Luo , Ling Shao