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/LdDl/rust-road-traffic
YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
https://github.com/LeeJunHyun/Image_Segmentation
U-Net: Convolutional Networks for Biomedical Image Segmentation
https://github.com/LilyHu/image_segmentation_chromosomes
U-Net: Convolutional Networks for Biomedical Image Segmentation
https://github.com/LinhanDai/yolov4-deepsort
Simple Online and Realtime Tracking with a Deep Association Metric
https://github.com/Lkruitwagen/remote-sensing-solar-pv
U-Net: Convolutional Networks for Biomedical Image Segmentation
https://github.com/LokiVKlokeNaAndoke/hackathon_traffic_light
https://github.com/LuanAdemi/VisualGo
U-Net: Convolutional Networks for Biomedical Image Segmentation
https://github.com/LucaHermes/graph-unet-traffic-prediction
U-Net: Convolutional Networks for Biomedical Image Segmentation
https://github.com/LukasHedegaard/co3d
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
https://github.com/LuojieH/CycleTrack
https://github.com/MEME-Phoenix/Autonomous-Driving-Cart-MEME
Simple Online and Realtime Tracking with a Deep Association Metric
https://github.com/MEME-Phoenix/MEME
Simple Online and Realtime Tracking with a Deep Association Metric
https://github.com/MNaiel/rcmss
https://github.com/MS-Mind/MS-Code-06/tree/main/OSVOS
https://github.com/MTCloudVision/mxnet-dssd
https://github.com/MTMC-DeeCamp2018/deep_sort
Simple Online and Realtime Tracking with a Deep Association Metric
https://github.com/MacherLabs/deep_sort
Simple Online and Realtime Tracking with a Deep Association Metric
https://github.com/Manthata/william-
https://github.com/MargeryLab/Pytorch-UNet-copy
U-Net: Convolutional Networks for Biomedical Image Segmentation
https://github.com/MarkoLewis-Projects/Sign_language_detection
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
https://github.com/MatthewQi2002/Unet_mindspore
U-Net: Convolutional Networks for Biomedical Image Segmentation
https://github.com/Maveric4/pr19aaw01
U-Net: Convolutional Networks for Biomedical Image Segmentation
https://github.com/MaximeBataille/tennis_tracking
https://github.com/MdAli1993/Multiclass_Semantic_Segmentation
U-Net: Convolutional Networks for Biomedical Image Segmentation
https://github.com/Media-Smart/vedaseg
U-Net: Convolutional Networks for Biomedical Image Segmentation
https://github.com/MenGuangwen-CN-0411/Simple-Use-of-SSD
https://github.com/Microsoft/SA-Siam
https://github.com/MikelBros/Yolov3_DeepSort_Pytorch
Simple Online and Realtime Tracking with a Deep Association Metric
https://github.com/Miltos-90/UNet_Biomedical_Image_Segmentation
U-Net: Convolutional Networks for Biomedical Image Segmentation
https://github.com/Mind23-2/MindCode-101/tree/main/JDE
SimpleTrack: Rethinking and Improving the JDE Approach for Multi-Object Tracking
https://github.com/Mind23-2/MindCode-129
YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
https://github.com/Mind23-2/MindCode-130
https://github.com/Mind23-2/MindCode-3/tree/main/JDE
SimpleTrack: Rethinking and Improving the JDE Approach for Multi-Object Tracking
https://github.com/Mind23-2/MindCode-33
https://github.com/Mind23-2/MindCode-4/tree/main/nri-mpm
MPM: Joint Representation of Motion and Position Map for Cell Tracking
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.