检索结果-内蒙古大学图书馆

multi-object tracking review: retrospective and emerging trend

ARTIFICIAL INTELLIGENCE REVIEW 2025年第8期58卷 1-46页

作者： Guan, Zhiyu Wang, Zhaofa Zhang, Gan Li, Luwei Zhang, Miaomiao Shi, Zhiping Jiang, Na Capital Normal Univ Beijing 100048 Peoples R China Beijing Acad Sci & Technol Beijing 100083 Peoples R China

multi-object tracking (MOT) is a critical task involving detecting and continuously tracking multiple objects within a video sequence. It is widely used in various fields, such as autonomous driving and intelligent security. In recent years, deep learning architectures have effectively promoted the development of MOT. However, this task poses significant challenges regarding accuracy due to occlusion/truncation, light variation, camera movement. Researchers have proposed many methods to address these issues to reduce trajectory fragmentation, identity switches, and missing targets. To better understand these advancements, it is essential to categorize the approaches based on their methodologies. This article reviewed the recent development of MOT, divided into tracking by Detection (TBD) and End-to-End (E2E). By introducing and comparing the two types of tracking algorithms, readers can quickly understand the current development status of MOT. Meanwhile, this review summarizes the links to open-source code of excellent algorithms and common benchmark datasets in the appendix. And provide a unified MOT toolkit that includes evaluation and visualization at https://***/guanzhiyu817/MOT-tools. In addition, this review discusses the future directions of MOT, specifically cross-modal reasoning.

关键词： multi-object tracking tracking by detection End-to-end object detection Cross-modal

来源：评论

学校读者我要写书评

暂无评论

multi-object tracking based on graph neural networks

引用

multiMEDIA SYSTEMS 2025年第1期31卷 1-16页

作者： Zhang, Yubo Zheng, Liying Huang, Qingming Harbin Engn Univ Sch Comp Sci & Technol Harbin 150001 Peoples R China Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 100019 Peoples R China

multi-object tracking (MOT), an essential task in computer vision, underperforms when existing occlusions or motion blurs, which will cause changes in the object's appearances. We develop three modules based on Graph Neural Networks (GNNs) to handle such appearance changes. The appearance enhancement module boosts appearance features by applying self-attention and Graph Convolutional Neural Network (GCNN) to the local features. The temporal feature updating module automatically updates a tracklet appearance template using GCNNs with different Laplacian operations. The spatial feature updating module encodes interactive spatial features by combining a graph attention network and a GCNN. After processing input video frames with these three modules, our tracker stores all extracted features in a memory bank and then forwards them to a matching algorithm to complete tracking. Using popular benchmark datasets MOT16, MOT17, and MOT20, we show that introducing GNNs to MOT benefits tracking, and the proposed tracker surpasses the state-of-the-art trackers, including StrongSORT, ByteTrack, and BoT-SORT. Specifically, we can achieve 81.1% (77.9%) in MOTA, 80.3% (77.3%) in IDF1, and 65.1% (63.2%) in HOTA on the challenging MOT17 (or the newest MOT20) datasets.

关键词： multi-object tracking Appearance changes Graph convolutional neural network Graph attention network

来源：评论

学校读者我要写书评

暂无评论

multi-object tracking with Spatial-Temporal Tracklet Association

引用

ACM TRANSACTIONS ON multiMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 2024年第5期20卷 1-21页

作者： You, Sisi Yao, Hantao Bao, Bing-Kun Xu, Changsheng Nanjing Univ Posts & Telecommun 66 New Model Rd Nanjing 210003 Jiangsu Peoples R China Tianjin Univ Technol Nanjing Peoples R China Chinese Acad Sci CASIA Inst Automat State Key Lab Multimodal Artificial Intelligence 95 Zhongguancun East Rd Beijing 100190 Peoples R China

Recently, the tracking-by-detection methods have achieved excellent performance in multi-object tracking (MOT), which focuses on obtaining a robust feature for each object and generating tracklets based on feature similarity. However, they are confronted with two issues: (1) unstable features in short-term occlusion and (2) insufficient matching in long-term occlusion. Specifically, the unstable feature is caused by the appearance variation under occlusion, and the association with the current unstable feature will lead to insufficient matching in long-term occlusion. To address the above issues, we propose a two-stage tracklet-level association method, Spatial-Temporal Tracklet Association (STTA), to effectively combine spatial-temporal context between feature extraction and data association. In the first stage, we propose the Tracklet-guided Spatial-Temporal Attention network (TSTA) to generate robust and stable features. Specifically, TSTA captures spatial-temporal context to obtain the most salient regions between the current and previous clips. In the second stage, we design the Bi-Tracklet Spatial-Temporal association (BTST) module to fully exploit the spatial-temporal context in data association. Specifically, we leverage BTST to merge different tracklets into long-term trajectories by jointly learning visual feature and spatial-temporal context and designing a bidirectional interpolation to recover the missed objects between matched tracklets. Extensive experiments of public and private detections on four benchmarks demonstrate the robustness of STTA. Furthermore, the proposed method is a model-agnostic method, which can be plugged and played with existing methods to boost their performance, e.g., obtain 11.0%, 10.1%, 2.9%, 3.2%, and 7.8% improvement on IDF1 in the MOT16 validation dataset for Tracktor, CenterTrack, Deepsort, JDE, and CTracker, respectively.

关键词： multi-object tracking spatial-temporal tracklet association tracklet-guided spatial-temporal attention network bi-tracklet spatial-temporal association

来源：评论

学校读者我要写书评

暂无评论

multi-object tracking Algorithm for Unmanned Vehicle Autonomous Driving Scene Based on Online Spatiotemporal Feature Correlation

引用

IEEE ACCESS 2024年 12卷 116489-116497页

作者： Li, Haijun Xu, Zhuye Ma, Changxi Tang, Xiao Lanzhou Jiaotong Univ Sch Transportat Lanzhou 730070 Peoples R China Lanzhou Jiaotong Univ Sch New Energy & Power Engn Lanzhou 730070 Peoples R China Changsha Univ Sci & Technol Natl Engn Res Ctr Highway Maintenance Technol Changsha 410114 Hunan Peoples R China

Aiming at the problem that the multi-object tracking algorithm is difficult to accurately design the object feature model and data association algorithm in the process of unmanned vehicle autonomous driving, a multi-object tracking algorithm based on online spatiotemporal feature correlation for unmanned vehicle autonomous driving scene (MOTA-BOSFCFUVADS) is proposed. Firstly, the algorithm performs object detection on the training samples, calibrates the coordinates of the detection results in the time dimension and the coordinates of the space dimension, eliminates the detection results whose confidence is less than the set value, and eliminates the overlapping boundaries in the detection through non-maximum suppression. Secondly, we use Kalman filter to predict the position of the tracking object in the current frame, then build the feature model of the object in the time dimension and the space dimension respectively, and fuse the temporal feature model of the tracking object with the spatial feature model, thereby, the spatiotemporal feature model of the tracking object is obtained. Finally, the spatiotemporal feature response of the object in the current frame is detected online, and the spatiotemporal feature response is correlated with the spatiotemporal object feature model of the tracking object, and then the similarity metric matching matrix obtained by fusion is calculated, and the tracking is solved by using the Hungarian algorithm. The optimal correlation pair between the object historical trajectory and the detection response, and update the parameters of the object spatiotemporal feature model. In addition, we use the MOT2015 database to test the effectiveness of the algorithm. The results show that the proposed algorithm has better tracking performance than the other two algorithms, and can effectively track multiple object continuously in time and space.

关键词： Target tracking Feature extraction Spatiotemporal phenomena Trajectory Data models Kalman filters tracking Autonomous driving Autonomous vehicles Autonomous driving of unmanned vehicles multi-object tracking spatiotemporal feature model data association

来源：评论

学校读者我要写书评

暂无评论

multi-object tracking in UAVs with feature fusion distribution and occlusion awareness

引用

SIGNAL IMAGE AND VIDEO PROCESSING 2025年第1期19卷 1-11页

作者： Wang, Yuchen Zhao, Wei Zhang, Rufei Li, Nannan Li, Dongjin Lv, Jianwei Xu, Jingyu Beihang Univ Beijing 100191 Peoples R China Beijing Inst Control & Elect Technol Beijing 100038 Peoples R China

multi-object tracking (MOT) in unmanned aerial vehicles (UAVs) is a crucial computer vision task with diverse applications in both military and civilian domains. However, the unique characteristics of UAVs, such as motion uncertainty and sudden changes in viewpoints, lead to objects with scale variance, occlusion, dense distribution, and frequent appearance and disappearance in the image, posing significant challenges in MOT in UAVs. In this paper, we address these issues by proposing two novel techniques: Feature Fusion Distribution Network (FFDN) and Occlusion-Aware Prediction and Association (OAPA), which are integrated into a new MOT algorithm named OATrack. The FFDN aims to improve object detection by optimizing the fusion of multi-scale features within the detection network, especially for densely distributed and different sized objects. The OAPA aims to enhance the accuracy and robustness of prediction and association for objects lost due to occlusion, thus addressing the issue of occlusion in UAV scenes. Experiments are conducted on Visdrone2019 and UAVDT, and the results clearly demonstrate the effectiveness and superiority of the proposed method.

关键词： multi-object tracking Unmanned aerial vehicle Feature fusion distribution Occlusion awareness

来源：评论

学校读者我要写书评

暂无评论

multi-object tracking with scale-aware transformer and enhanced association strategy

引用

multiMEDIA SYSTEMS 2025年第2期31卷 1-13页

作者： Xiang, Xuezhi Zhou, Xiankun Wang, Xinyao Zhai, Mingliang El Saddik, Abdulmotaleb Harbin Engn Univ Sch Informat & Commun Engn Harbin 150001 Peoples R China Minist Ind & Informat Technol Key Lab Adv Marine Commun & Informat Technol Harbin 150001 Peoples R China Nanjing Univ Posts & Telecommun Sch Automat Nanjing 210023 Peoples R China Univ Ottawa Sch Elect Engn & Comp Sci Ottawa ON K1N 6N5 Canada

multiple object tracking (MOT) is an important task in computer vision. The effectiveness of existing MOT methods can be easily hurt by multi-scale objects and extreme occlusions in the tracking process. To effectively improve the tracking performance of multi-scale objects, we propose a Scale-aware Transformer module integrating multi-scale global information into feature maps of various scales to augment the representation, which can improve detection and ID embedding tasks to help data association without heavy computation cost. For false associations caused by occluded objects, an enhanced association strategy is proposed which combines detection recovery mechanism and detection confidence hierarchical matching into JDE-based association, and a new CIoU-Embedding similarity matrix is re-designed for matching. The results on MOT16, MOT17, and MOT20 benchmarks indicate that our method achieves competitive performance among JDE-based models and Transformer-based methods, e.g., 77.5 MOTA and 74.9 IDF1 on MOT17 while maintaining 19.5 FPS tracking speed.

关键词： multi-object tracking Scale-aware transformer JDE tracking CIoU-embedding similarity matrix

来源：评论

学校读者我要写书评

暂无评论

multi-object tracking using context-sensitive enhancement via feature fusion

引用

multiMEDIA TOOLS AND APPLICATIONS 2024年第7期83卷 19465-19484页

作者： Zhou, Yan Chen, Junyu Wang, Dongli Zhu, Xiaolin Xiangtan Univ Sch Automat & Elect Informat Xiangtan 411105 Peoples R China Xiangtan Univ Sch Math & Computat Sci Xiangtan 411105 Peoples R China

multi-object tracking (MOT) is one of the most challenging tasks in the field of computer vision. Most MOT methods generally face the problem of not being able to handle pedestrian features such as size and appearance well, which can easily lead to the problem of missed detection and occlusion. Considering this, an end-to-end multi-target tracking network with feature fusion and feature enhancement is proposed. The network framework integrates feature extraction, object detection, and data association. Using two adjacent frames as input chain nodes, based on Inception convolution as the backbone network, which has special pre-training weights that increase the perceptual domain of the network for multiple targets. In addition, the three-times repetitive overlay weighted bidirectional pyramid structure in the feature fusion module, which can focus more on key features and enhance the adaptability to target deformation. In order to solve the phenomenon of crowding in complex scenes, a context-sensitive prediction modules are added, which contain deeper and wider convolution to enhance the key information between targets. After the above processing, three loss function branches are formed, where the classification branch and the identity branch together form the attention multiplied by the regression branch to ensure the accuracy of regression. In MOT16 and MOT17 dataset experiments, our model MOTA metrics reach 67.9 and 67.7, with frame rates up to 30 FPS on a single GPU, with improved visualization results beyond Chain-Tracker.

关键词： multi-object tracking Inception convolution Weighted bidirectional pyramid Feature fusion Context-sensitive prediction modules

来源：评论

学校读者我要写书评

暂无评论

multi-object tracking in surveillance scenarios based on joint detection and multi-feature fusion

引用

JOURNAL OF SUPERCOMPUTING 2025年第8期81卷 1-30页

作者： Zhao, Runxing Gong, Jianxin Wang, Zhiwen Guangxi Univ Sci & Technol Sch Automat Liuzhou 545616 Peoples R China Liuzhou City Vocat Coll Liuzhou 545036 Peoples R China Guangxi Univ Sci & Technol Sch Elect Engn Liuzhou 545006 Peoples R China

multi-object tracking (MOT) in surveillance scenarios demands both high accuracy and computational efficiency, especially under challenging conditions such as occlusion, scale variation, and dense targets. While one-stage joint detection and embedding models offer promising real-time performance, they often suffer from task inconsistency and feature scale mismatch between detection and re-identification (ReID) branches, leading to degraded appearance embeddings and frequent identity switches. To address this issue, this paper proposes a novel joint detection and appearance embedding based on YOLOv9: YOLO-JDE. We use a kind of dynamic-aware downsampling (DAD) in the original model to enhance the network's capability to extract global feature information, which effectively improves detection accuracy. Due to the intrinsic dissimilarity between the detection task and the re-identification (ReID) task, we introduce a multi-task decomposition network (MTDNet) that mitigates the conflict between these two tasks by learning the dissimilarity to output different feature maps. In addition, we propose a multi-scale aggregation network (MSANet) in the ReID branch to address the issue of identity switches caused by occlusion, scale variation, and dense targets during the tracking and matching process. In the final stage of data association, we propose a multilevel association matching approach that leverages confidence, appearance, and IoU distance, which can achieve about 0.7% performance improvement on multiple tracking models. Through validation on the public MOT16, MOT17, and MOT20 test sets for surveillance scenarios, YOLO-JDE achieved MOTA metrics of 78.2%, 77.4%, and 73.0%, respectively.

关键词： multi-object tracking YOLO Appearance embedding Joint detection multi-feature fusion

来源：评论

学校读者我要写书评

暂无评论

multi-object tracking via deep feature fusion and association analysis

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2023年第1期124卷

作者： Li, Hui Liu, Yapeng Liang, Xiaoguo Yuan, Yongfeng Cheng, Yuanzhi Zhang, Guanglei Tamura, Shinichi Qingdao Univ Sci & Technol Sch Informat Sci & Technol Qingdao 266061 Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Harbin 150001 Peoples R China Beihang Univ Sch Biol Sci & Med Engn Beijing 100191 Peoples R China NBL Technovator Co Ltd Shindachimakino 631 Sennan 5900522 Japan Osaka Univ ISIR Rm I-2718-1 Mihogaoka Ibaraki Osaka 5670047 Japan Osaka Univ Grad Sch Med Dept Radiol 2-2 Yamadaoka Suita Osaka 5650871 Japan

We describe a tracking-by-detection framework for multi-object tracking (MOT). It first detects the objects of interest in each frame of the video, followed by identifying association with the object detected in the previous frame. A deep association network is described to perform object feature matching in the arbitrary two frames to infer association degree of objects, and then similarity matrix loss is used to calculate association between each object in different frames to achieve an accurate tracking. The novelty of the work lies in the design of a multi-scale fusion strategy by gradually concatenating sub-networks of low-resolution feature maps in parallel to the main network of high-resolution feature maps, in the construction of a deeper backbone network which can enhance the semantic information of object features, and in the use of a siamese network for training a pair of discontinuous frames. The main advantage of our framework is that it avoids missing detection and partial detection. It is particularly suitable for solving the problem of object ID switch caused by occlusion, entering and leaving of objects. Our method is evaluated and demonstrated on the publicly available MOT15, MOT16, MOT17 and MOT20 benchmark datasets. Compared with the state-of-the-art methods, our method achieves better tracking performance, and is therefore, more suited for MOT tasks.

关键词： multi-object tracking Association analysis Similarity matrix object occlusion Siamese network

来源：评论

学校读者我要写书评

暂无评论

multi-object tracking: a systematic literature review

引用

multiMEDIA TOOLS AND APPLICATIONS 2023年第14期83卷 43439页

作者： Hassan, Saif Mujtaba, Ghulam Rajput, Asif Fatima, Noureen Sukkur IBA Univ Ctr Excellence Robot Artificial Intelligence & Blo Dept Comp Sci Sukkur Pakistan

The field of computer vision is revolutionized with the advancement of deep learning and the availability of high computational power. In addition, in the field of computer vision, object detection, and tracking have gained much interest. Several authors are proposing new approaches to detect and track multiple objects from a given video frame and publishing their novel approaches in well-reputed academic journals and proceedings. However, a comprehensive systematic literature review is needed to summarize and critically appraise the existing primary works on multi-object tracking approaches. Therefore, to address this, we aim to produce a systematic literature review on multi-object tracking approaches published from 2019 to 2021. In addition, in this paper, we have systematically reviewed different datasets, multi object-tracking approaches, and performances of existing approaches. Further, we have also presented the critical appraisal of existing primary studies on the subject matter. Finally, we have also provided seven future research directions for future researchers who are interested in further contributing to the field of multi-object tracking. We believe that this work will be beneficial for novice as well as expert researchers who are further willing to contribute to the field of multi-object tracking.

关键词： multi-object tracking Computer vision Deep learning multi-tracking Re-identification augmentation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：