• Corpus ID: 90888

Multiple-Kernel Based Vehicle Tracking Using 3D Deformable Model and Camera Self-Calibration

@article{Tang2017MultipleKernelBV,
  title={Multiple-Kernel Based Vehicle Tracking Using 3D Deformable Model and Camera Self-Calibration},
  author={Zheng Tang and Gaoang Wang and Tao Liu and Young-Gun Lee and Adwin Jahn and X. Liu and Xiaodong He and Jenq-Neng Hwang},
  journal={ArXiv},
  year={2017},
  volume={abs/1708.06831}
}
Tracking of multiple objects is an important application in AI City geared towards solving salient problems related to safety and congestion in an urban environment. [] Key Method The proposed method utilizes shape fitness evaluation besides color information to track vehicle objects robustly and efficiently. To build 3D car models in a fully unsupervised manner, we also implement evolutionary camera self-calibration from tracking of walking humans to automatically compute camera parameters.

Figures and Tables from this paper

Single-Camera and Inter-Camera Vehicle Tracking and 3D Speed Estimation Based on Fusion of Visual and Semantic Features

TLDR
A histogram-based adaptive appearance model is introduced to learn long-term history of visual features for each vehicle target and evolutionary optimization is applied to camera calibration for reliable 3D speed estimation.

Multi-camera vehicle tracking and re-identification based on visual and spatial-temporal features

TLDR
A novel framework for multi-camera tracking, which integrates visual features, orientation prediction and temporal-spatial information of the trajectories for optimization is proposed, which achieves the first place in vehicle re-identification at the NVIDIA AI City Challenge 2019.

Joint Multi-View People Tracking and Pose Estimation for 3D Scene Reconstruction

TLDR
This work proposes an effective integration of visual and semantic object attributes, i.e., appearance models, geometry information and poses/actions, to associate tracklets across different views in a surveillance system with camera arrays of overlapping views.

ACCURATE VEHICLE SPEED ESTIMATION FROM MONOCULAR CAMERA FOOTAGE

TLDR
A workflow is devised in this paper by which vehicle speeds are estimated semi-automatically via fixed DSLR camera via British National Grid Coordinate System, and the robustness of the method was tested in a real-world context and environmental conditions.

Robust Automatic Monocular Vehicle Speed Estimation for Traffic Surveillance

TLDR
Experimental results conducted on three diverse benchmarks demonstrate excellent speed estimation accuracy that could enable the wide use of CCTV cameras for traffic analysis, even in challenging conditions where state-of-the-art methods completely fail.

Constrained Multi Camera Calibration for Lane Merge Observation

TLDR
Evaluations on data recorded on a test track show that the proposed calibration technique provides adequate calibration accuracy while the accuracies of reference implementations are insufficient.

Vehicle Speed Measurement Based on Binocular Stereovision System

TLDR
A novel stereovision-based system for vehicle speed measurement that performs non-intrusive and stealth measurement in intelligent traffic surveillance and overcomes the challenges of speed measurement for multiple vehicles on multiple lanes in different motions simultaneously.

PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data

TLDR
A Pose-Aware Multi-Task Re-Identification (PAMTRI) framework that overcomes viewpoint-dependency by explicitly reasoning about vehicle pose and shape via keypoints, heatmaps and segments from pose estimation and achieves significant improvement over state-of-the-art on two mainstream vehicle ReID benchmarks.

Vehicle Tracking and Speed Estimation from Traffic Videos

TLDR
This paper combines modern deep learning models with classic computer vision approaches to propose an efficient way to predict vehicle speed and introduces some state-of-the-art approaches in vehicle speed estimation, vehicle detection, and object tracking.

Accuracy Evaluation of Camera-based Vehicle Localization

TLDR
The scope of this paper is the implementation and evaluation of a system which provides the detection, tracking, and localization of vehicles for a cooperative maneuvers scenario where the vehicle localizations are used for the planning of trajectories.

References

SHOWING 1-10 OF 23 REFERENCES

Multiple-kernel based vehicle tracking using 3-D deformable model and license plate self-similarity

TLDR
Experimental results have shown the favorable performance of the proposed system, which can successfully track vehicles under serious occlusion while maintaining the knowledge of 3-D geometry of the tracked vehicles.

Three-Dimensional Deformable-Model-Based Localization and Recognition of Road Vehicles

TLDR
It is shown that the local gradient-based method can evaluate accurately and efficiently the fitness between the projection of the vehicle model and the image data.

Camera self-calibration from tracking of moving persons

TLDR
A robust segmentation and tracking system is applied to provide accurate estimation of head and foot locations of moving persons and it is proposed to use the estimation of distribution algorithm (EDA) to search for the local optimal solution for camera calibration that minimizes average reprojection error on the ground plane.

Vehicle tracking iterative by Kalman-based constrained multiple-kernel and 3-D model-based localization

TLDR
Experimental results have shown the favorable performance of the proposed system, which can successfully track vehicles while maintaining the knowledge of 3-D vehicle geometry.

Online-Learning-Based Human Tracking Across Non-Overlapping Cameras

TLDR
This paper presents a novel approach to tracking each human within a single camera and across multiple disjoint cameras and introduces an effective integration of appearance and context features in inter-camera tracking.

Tracking Human Under Occlusion Based on Adaptive Multiple Kernels With Projected Gradients

TLDR
An innovative method, which uses projected gradient to facilitate multiple kernels, in finding the best match during tracking under predefined constraints, and embeds the multiple-kernel tracking into a Kalman filtering-based tracking system to enable fully automatic tracking.

Multiple-kernel adaptive segmentation and tracking (MAST) for robust object tracking

TLDR
Evaluations of the proposed Multiple-kernel Adaptive Segmentation and Tracking (MAST) method demonstrate that the proposed method can successfully track objects in similar-color background and/or shadow areas with favorable segmentation performance.

An equalised global graphical model-based approach for multi-camera object tracking

TLDR
This paper tries to improve the overall multi-camera object tracking performance by a global graph model with an improved similarity metric and shows that the method can work better even in the condition of poor single camera object tracking.

Inter-camera tracking based on fully unsupervised online learning

TLDR
A novel fully automatic approach to track the same human across multiple disjoint cameras and introduces an effective and robust integration of appearance and context features.

Human tracking by adaptive Kalman filtering and multiple kernels tracking with projected gradients

TLDR
This paper embeds the multiple kernels tracking into a Kalman filtering-based tracking system, which uses Kalman prediction as the initial position for the multiple kernel tracking, and applies the result of the latter as the measurement to the Kalman update.