TrackNet: A Triplet metric-based method for Multi-Target Multi-Camera Vehicle Tracking

2022-05-27 · David Serrano, Francesc Net, Juan Antonio Rodríguez, Igor Ugarte

We present TrackNet, a method for Multi-Target Multi-Camera (MTMC) vehicle tracking from traffic video sequences. Cross-camera vehicle tracking has proved to be a challenging task due to perspective, scale and speed variance, as well occlusions and noise conditions. Our method is based on a modular approach that first detects vehicles frame-by-frame using Faster R-CNN, then tracks detections through single camera using Kalman filter, and finally matches tracks by a triplet metric learning strategy. We conduct experiments on TrackNet within the AI City Challenge framework, and present competitive IDF1 results of 0.4733.

📄 PDF Abstract BibTeX arXiv:2205.13857

Code (1)

davidserra9/tracknet 공식 구현 pytorch

Tasks

Metric LearningTriplet

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

RoIPool 설명 없음

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

RPN A Region Proposal Network, or RPN, is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained…

Faster R-CNN Faster R-CNN is an object detection model that improves on Fast R-CNN by utilising a region proposal network…

TrackNetV5: Residual-Driven Spatio-Temporal Refinement and Motion Direction Decoupling for Fast Object Tracking

2025-12-02 · Haonan Tang, Yanjun Chen, Lezhi Jiang, Qianfei Li 외 arxiv

The TrackNet series has established a strong baseline for fast-moving small object tracking in sports. However, existing iterations face significant limitations: V1-V3 struggle with occlusions due to a reliance on purely…

Object Tracking

TrackNetV2: Efficient Shuttlecock Tracking Network

2020-12-03 · Conference 2020 12 · Nien-En Sun, Yu-Ching Lin, Shao-Ping Chuang, Tzu-Han Hsu 외

TrackNet, a deep learning network, was proposed to track high-speed and tiny objects such as tennis balls and shuttlecocks from videos. To conquer low image quality issues such as blur, afterimage, and short-term occlusi…

GPU Sports Ball Detection and Tracking

TrackNetV4: Enhancing Fast Sports Object Tracking with Motion Attention Maps

2024-09-22 · Arjun Raj, Lei Wang, Tom Gedeon

Accurately detecting and tracking high-speed, small objects, such as balls in sports videos, is challenging due to factors like motion blur and occlusion. Although recent deep learning frameworks like TrackNetV1, V2, and…

Object Tracking Trajectory Prediction

Detection of Abnormal Vessel Behaviours from AIS data using GeoTrackNet: from the Laboratory to the Ocean

2020-08-12 · Duong Nguyen, Matthieu Simonin, Guillaume Hajduch, Rodolphe Vadaine 외

The constant growth of maritime traffic leads to the need of automatic anomaly detection, which has been attracting great research attention. Information provided by AIS (Automatic Identification System) data, together w…

Anomaly Detection

TrackNet: A Deep Learning Network for Tracking High-speed and Tiny Objects in Sports Applications

2019-07-08 · Yu-Chuan Huang, I-No Liao, Ching-Hsuan Chen, Tsì-Uí İk 외

Ball trajectory data are one of the most fundamental and useful information in the evaluation of players' performance and analysis of game strategies. Although vision-based object tracking techniques have been developed …

Object Tracking Position