https://github.com/kemo-huang/jmodt
공식 코드Joint Multi-Object Detection and Tracking with Camera-LiDAR Fusion for Autonomous Driving
Papers with Code 아카이브
Object Tracking
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 10
- 평가표
- 10
- 보존된 평가 기록
- 43
Object tracking is the task of taking an initial set of object detections, creating a unique ID for each of the initial detections, and then tracking each of the objects as they move around frames in a video, maintaining the ID assignment. State-of-the-art methods involve fusing data from RGB and event-based cameras to produce more reliable object tracking. CNN-based models using only RGB images as input are also effective. The most popular benchmark is OTB. There are several evaluation metrics specific to object tracking, including HOTA, MOTA, IDF1, and Track-mAP.
<span style="color:grey; opacity: 0.6">( Image credit: Towards-Realtime-MOT )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/kitware/mevid
공식 코드MEVID: Multi-view Extended Videos with Identities for Video Person Re-Identification
https://github.com/kruzaeva/activity-cell-tracking
공식 코드Cell tracking for live-cell microscopy using an activity-prioritized assignment strategy
https://github.com/kuanchihhuang/moma-m3t
공식 코드Delving into Motion-Aware Matching for Monocular 3D Object Tracking
https://github.com/lRomul/ball-action-spotting
공식 코드https://github.com/lab206/echotrack
공식 코드EchoTrack: Auditory Referring Multi-Object Tracking for Autonomous Driving
https://github.com/larsbredereke/object_tracking
공식 코드https://github.com/lauziere/mhht
공식 코드https://github.com/leandro-svg/hybridtrack
공식 코드HybridTrack: A Hybrid Approach for Robust Multi-Object Tracking
https://github.com/leeyeehoo/SiamVGG
공식 코드https://github.com/lemmersj/ground-truth-or-daer
공식 코드Ground-truth or DAER: Selective Re-query of Secondary Information
https://github.com/leozhiheng/mmf-tracker
공식 코드MMF-Track: Multi-modal Multi-level Fusion for 3D Single Object Tracking
https://github.com/leozhiheng/mtm-tracker
공식 코드Motion-to-Matching: A Mixed Paradigm for 3D Single Object Tracking
https://github.com/liangp/mcstn-3dsot
공식 코드Multi-Correlation Siamese Transformer Network with Dense Connection for 3D Single Object Tracking
https://github.com/lifeng9472/STRCF
공식 코드Learning Spatial-Temporal Regularized Correlation Filters for Visual Tracking
https://github.com/linh-gist/AdaptConfByteTrack
공식 코드Adaptive Confidence Threshold for ByteTrack in Multi-Object Tracking
https://github.com/linh-gist/VisualRFS
공식 코드https://github.com/linh-gist/ms-glmb-nuScenes
공식 코드3D Multi-Object Tracking Employing MS-GLMB Filter for Autonomous Driving
https://github.com/linh-gist/mv-glmb-ab
공식 코드Track Initialization and Re-Identification for~3D Multi-View Multi-Object Tracking
https://github.com/linjieyangsc/video_seg
공식 코드https://github.com/litinglin/lorat
공식 코드Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance
https://github.com/litinglin/swintrack
공식 코드SwinTrack: A Simple and Strong Baseline for Transformer Tracking
https://github.com/little-podi/grm
공식 코드https://github.com/liujia99/M3SOT
공식 코드M3SOT: Multi-frame, Multi-field, Multi-space 3D Single Object Tracking
https://github.com/liuqk3/OTCD
공식 코드https://github.com/liuyuml/depth-attention
공식 코드https://github.com/liuyuml/nv-vot211
공식 코드NT-VOT211: A Large-Scale Benchmark for Night-time Visual Object Tracking
https://github.com/liuzhonglincc/ratracker
공식 코드Representation Alignment Contrastive Regularization for Multi-Object Tracking
https://github.com/lixiaoyu2000/fastpoly
공식 코드Fast-Poly: A Fast Polyhedral Framework For 3D Multi-Object Tracking
https://github.com/liyunfenglyf/kf_in_underwater_trackers
공식 코드Underwater Object Tracker: UOSTrack for Marine Organism Grasping of Underwater Vehicles
https://github.com/liyunfenglyf/sonart165
공식 코드SonarT165: A Large-scale Benchmark and STFTrack Framework for Acoustic Object Tracking
https://github.com/liyunfenglyf/uostrack
공식 코드Underwater Object Tracker: UOSTrack for Marine Organism Grasping of Underwater Vehicles
https://github.com/ljacksonpan/ratrack
공식 코드RaTrack: Moving Object Detection and Tracking with 4D Radar Point Cloud
https://github.com/longcw/MOTDT
공식 코드https://github.com/longyin880815/STCNN
공식 코드https://github.com/lorenzovaquero/busca
공식 코드Lost and Found: Overcoming Detector Failures in Online Multi-Object Tracking
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.