中文
相关论文

相关论文: MVA 2025 Small Multi-Object Tracking for Spotting …

200 篇论文

Object tracking is divided into single-object tracking (SOT) and multi-object tracking (MOT). MOT aims to maintain the identities of multiple objects across a series of continuous video sequences. In recent years, MOT has made rapid…

计算机视觉与模式识别 · 计算机科学 2023-03-20 Yukuan Zhang , Yunhua Jia , Housheng Xie , Mengzhen Li , Limin Zhao , Yang Yang , Shan Zhao

We propose a method for multi-object tracking and segmentation based on a novel memory-based mechanism to associate tracklets. The proposed tracker, MeNToS, addresses particularly the long-term data association problem, when objects are not…

计算机视觉与模式识别 · 计算机科学 2023-05-18 Mehdi Miah , Guillaume-Alexandre Bilodeau , Nicolas Saunier

Recent progresses in model-free single object tracking (SOT) algorithms have largely inspired applying SOT to \emph{multi-object tracking} (MOT) to improve the robustness as well as relieving dependency on external detector. However, SOT…

计算机视觉与模式识别 · 计算机科学 2019-02-25 Peng Chu , Heng Fan , Chiu C Tan , Haibin Ling

Detection of small-sized targets is of paramount importance in many aerial vision-based applications. The commonly deployed low cost unmanned aerial vehicles (UAVs) for aerial scene analysis are highly resource constrained in nature. In…

计算机视觉与模式识别 · 计算机科学 2019-09-04 Murari Mandal , Manal Shah , Prashant Meena , Santosh Kumar Vipparthi

Autonomous-driving perception systems require robust Multi-Object Tracking (MOT) to operate reliably in dynamic environments. MOT maintains consistent object identities across frames while preserving spatial accuracy. Recent foundation…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Diogo Mendonça , Tiago Barros , Cristiano Premebida , Urbano J. Nunes

Unmanned aerial vehicle (UAV) tracking is critical for applications like surveillance, search-and-rescue, and autonomous navigation. However, the high-speed movement of UAVs and targets introduces unique challenges, including real-time…

计算机视觉与模式识别 · 计算机科学 2025-08-22 You Wu , Xucheng Wang , Dan Zeng , Hengzhou Ye , Xiaolan Xie , Qijun Zhao , Shuiwang Li

We propose a metadata-aware self-supervised learning~(SSL)~framework useful for fine-grained classification and ecological mapping of bird species around the world. Our framework unifies two SSL strategies: Contrastive Learning~(CL) and…

计算机视觉与模式识别 · 计算机科学 2023-10-31 Srikumar Sastry , Subash Khanal , Aayush Dhakal , Di Huang , Nathan Jacobs

The increasing deployment of small drones as tools of conflict and disruption has amplified their threat, highlighting the urgent need for effective anti-drone measures. However, the compact size of most drones presents a significant…

计算机视觉与模式识别 · 计算机科学 2024-12-24 Hanfang Liang , Jinming Hu , Xiaohuan Ling , Bing Wang

The growing proliferation of unmanned aerial vehicles (UAVs) poses major challenges for reliable airspace surveillance, as drones are typically small, have low radar cross-sections, and often move slowly in cluttered environments. These…

信号处理 · 电气工程与系统科学 2026-04-16 Anders Malthe Westerkam , Jakob Möderl , Erik Leitinger , Troels Pedersen

Classically, visual object tracking involves following a target object throughout a given video, and it provides us the motion trajectory of the object. However, for many practical applications, this output is often insufficient since…

计算机视觉与模式识别 · 计算机科学 2020-11-25 Maximilian Filtenborg , Efstratios Gavves , Deepak Gupta

Without manually annotated identities, unsupervised multi-object trackers are inferior to learning reliable feature embeddings. It causes the similarity-based inter-frame association stage also be error-prone, where an uncertainty problem…

计算机视觉与模式识别 · 计算机科学 2023-12-21 Kai Liu , Sheng Jin , Zhihang Fu , Ze Chen , Rongxin Jiang , Jieping Ye

The high temporal variation of the point clouds is the key challenge of 3D single-object tracking (3D SOT). Existing approaches rely on the assumption that the shape variation of the point clouds and the motion of the objects across…

计算机视觉与模式识别 · 计算机科学 2024-09-09 Qiao Wu , Kun Sun , Pei An , Mathieu Salzmann , Yanning Zhang , Jiaqi Yang

Despite recent progress in Multiple Object Tracking (MOT), several obstacles such as occlusions, similar objects, and complex scenes remain an open challenge. Meanwhile, a systematic study of the cost-performance tradeoff for the popular…

计算机视觉与模式识别 · 计算机科学 2024-01-23 Yu-Hsiang Wang , Jun-Wei Hsieh , Ping-Yang Chen , Ming-Ching Chang , Hung Hin So , Xin Li

In the context of multi-object tracking using video synthetic aperture radar (Video SAR), Doppler shifts induced by target motion result in artifacts that are easily mistaken for shadows caused by static occlusions. Moreover, appearance…

计算机视觉与模式识别 · 计算机科学 2025-08-12 Haoxiang Chen , Wei Zhao , Rufei Zhang , Nannan Li , Dongjin Li

This paper presents a new algorithm for autonomous multitarget tracking of resident space objects using optical angles-only measurements from a spaceborne observer. To enable autonomous angles-only navigation of spacecraft swarms, an…

信号处理 · 电气工程与系统科学 2021-10-04 Justin Kruger , Simone D'Amico

Recently, Siamese network based trackers have received tremendous interest for their fast tracking speed and high performance. Despite the great success, this tracking framework still suffers from several limitations. First, it cannot…

计算机视觉与模式识别 · 计算机科学 2018-09-06 Anfeng He , Chong Luo , Xinmei Tian , Wenjun Zeng

Multiple object tracking (MOT) from unmanned aerial vehicle (UAV) platforms requires efficient motion modeling. This is because UAV-MOT faces both local object motion and global camera motion. Motion blur also increases the difficulty of…

计算机视觉与模式识别 · 计算机科学 2024-12-13 Mufeng Yao , Jinlong Peng , Qingdong He , Bo Peng , Hao Chen , Mingmin Chi , Chao Liu , Jon Atli Benediktsson

Multi-object tracking is a classic field in computer vision. Among them, pedestrian tracking has extremely high application value and has become the most popular research category. Existing methods mainly use motion or appearance…

计算机视觉与模式识别 · 计算机科学 2025-07-04 Teng Fu , Yuwen Chen , Zhuofan Chen , Mengyang Zhao , Bin Li , Xiangyang Xue

In the recent past, the computer vision community has developed centralized benchmarks for the performance evaluation of a variety of tasks, including generic object and pedestrian detection, 3D reconstruction, optical flow, single-object…

计算机视觉与模式识别 · 计算机科学 2015-04-09 Laura Leal-Taixé , Anton Milan , Ian Reid , Stefan Roth , Konrad Schindler

Camera traps have become a common tool for wildlife monitoring efforts in ecological research and biodiversity conservation. Wildlife classification models have benefited from the increase in wildlife visual data. These models reach high…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Mufhumudzi Muthivhi , Jiahao Huo , Fredrik Gustafsson , Terence L. van Zyl