Estimating Metric Poses of Dynamic Objects Using Monocular Visual-Inertial Fusion

Qiu, Kejie; Qin, Tong; Xie, Hongwen; Shen, Shaojie

doi:10.1109/iros.2018.8593748

Cited by 8 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The architecture for "model-based tracking" enables the estimation of 3D object detection, but to our knowledge, no work has been done in this field to link two autonomous systems such as a CNN and VINS altogether. Most of these methods use visual features such as ORB [28] or region-based visual bundle adjustment where the first detection is supposed to be correct as in [19]. This paper is very close from our work in terms for 2D-3D matching.…”

Section: B Tracking Systemssupporting

confidence: 64%

See 1 more Smart Citation

Exploiting the ACCuracy-ACCeleration tradeoff: VINS-assisted real-time object detection on moving systems

Dem¹,

Nakazawa

2019

2019 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)

View full text Add to dashboard Cite

In recent years, Convolutional Neural Networks (CNNs) have repeatedly shown state-of-the-art performance for their accuracy in the task of object detection, but their heavy computational costs impede their ability for real-time detection when the supporting system is moving especially accelerating. At the same time, recent progress on visual inertial systems takes great advantage of movement information to robustly estimate the robot state and surrounding. This paper proposes to exploit the advantages of inertial odometry research for the purpose of real-time object detection system on mobile robots. We combine a CNN detector with VINS-Mono, a moving visual odometry system, and show reliable improvement in the detection process, especially as the robot accelerates or decelerates. Our system is ready-to-use in that it has very low deployment cost and requires no calibration. The resulting system allows for simultaneous robot state estimation and object detection, as well as object tracking. Lastly, the architecture is flexible in that it is not restrained to a specific object type or detector.

show abstract

Section: B Tracking Systemssupporting

confidence: 64%

“…Between tracking and mapping field of research, object pose estimation has also been researched with [14] [19] or without neural networks [7]. However, this latter method were not developed in the perspective of a robotic object detection but rather for environment mapping like Semantic SLAM does.…”

Section: Related Work a Object Detection In 3dmentioning

confidence: 99%

Exploiting the ACCuracy-ACCeleration tradeoff: VINS-assisted real-time object detection on moving systems

Dem¹,

Nakazawa

2019

2019 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)

View full text Add to dashboard Cite

show abstract

“…However, the improvement of the performance of the VINS through the M-estimator is limited in dynamic scenarios. Similar research was extended in [39,40] and the same framework was used. The M-estimator was applied to increase the robustness of the standard error function and improved performance was obtained.…”

Section: Introductionmentioning

confidence: 99%

Robust Visual-Inertial Integrated Navigation System Aided by Online Sensor Model Adaption for Autonomous Ground Vehicles in Urban Areas

2020

View full text Add to dashboard Cite

The visual-inertial integrated navigation system (VINS) has been extensively studied over the past decades to provide accurate and low-cost positioning solutions for autonomous systems. Satisfactory performance can be obtained in an ideal scenario with sufficient and static environment features. However, there are usually numerous dynamic objects in deep urban areas, and these moving objects can severely distort the feature-tracking process which is critical to the feature-based VINS. One well-known method that mitigates the effects of dynamic objects is to detect vehicles using deep neural networks and remove the features belonging to surrounding vehicles. However, excessive feature exclusion can severely distort the geometry of feature distribution, leading to limited visual measurements. Instead of directly eliminating the features from dynamic objects, this study proposes to adopt the visual measurement model based on the quality of feature tracking to improve the performance of the VINS. First, a self-tuning covariance estimation approach is proposed to model the uncertainty of each feature measurement by integrating two parts: (1) the geometry of feature distribution (GFD); (2) the quality of feature tracking. Second, an adaptive M-estimator is proposed to correct the measurement residual model to further mitigate the effects of outlier measurements, like the dynamic features. Different from the conventional M-estimator, the proposed method effectively alleviates the reliance on the excessive parameterization of the M-estimator. Experiments were conducted in typical urban areas of Hong Kong with numerous dynamic objects. The results show that the proposed method could effectively mitigate the effects of dynamic objects and improved accuracy of the VINS is obtained when compared with the conventional VINS method.

show abstract

“…However, the improvement of the performance of the VINS based on the M-estimator is limited in dynamic scenarios. In fact, similar researches are extended in [37,38], and the same framework is used. M-estimator is applied to increase the robustness of the standard error function, and the improved performance is obtained.…”

Section: Introductionmentioning

confidence: 99%

Robust Visual-Inertial Integrated Navigation System Aided by Online Sensor Model Adaption for Autonomous Ground Vehicles in Urban Areas

Bai

Wen

Hsu

2020

Preprint

View full text Add to dashboard Cite

Visual-inertial integrated navigation system (VINS) has been extensively studied over the past decades to provide accurate and low-cost positioning solutions for autonomous systems. Satisfactory performance can be obtained in an ideal scenario with sufficient and static environment features. However, there are usually numerous dynamic objects in deep urban areas, and these moving objects can severely distort the feature tracking process which is fatal to the feature-based VINS. The well-known method mitigates the effects of dynamic objects is to detect the vehicles using deep neural networks and remove the features belongs to the surrounding vehicle. However, excessive exclusion of features can severely distort the geometry of feature distribution, leading to limited visual measurements. Instead of directly eliminating the features from dynamic objects, this paper proposes to adopt the visual measurement model based on the quality of feature tracking to improve the performance of VINS. Firstly, a self-tuning covariance estimation approach is proposed to model the uncertainty of each feature measurements by integrating two parts: 1) the geometry of feature distribution (GFD), 2) the quality of feature tracking. Secondly, an adaptive M-estimator is proposed to correct the measurement residual model to further mitigate the impacts of outlier measurements, such as the dynamic features. Different from the conventional M-estimator, the proposed method effectively alleviates the reliance of excessive parameterization of M-estimator. Experiments are conducted in a typical urban area of Hong Kong with numerous dynamic objects, and the results show that the proposed method could effectively mitigate the effects of dynamic objects and improved accuracy of VINS is obtained when compared with the conventional method.

show abstract

Estimating Metric Poses of Dynamic Objects Using Monocular Visual-Inertial Fusion

Cited by 8 publications

References 21 publications

Exploiting the ACCuracy-ACCeleration tradeoff: VINS-assisted real-time object detection on moving systems

Exploiting the ACCuracy-ACCeleration tradeoff: VINS-assisted real-time object detection on moving systems

Robust Visual-Inertial Integrated Navigation System Aided by Online Sensor Model Adaption for Autonomous Ground Vehicles in Urban Areas

Robust Visual-Inertial Integrated Navigation System Aided by Online Sensor Model Adaption for Autonomous Ground Vehicles in Urban Areas

Contact Info

Product

Resources

About