Autonomous Wheels And Camera Calibration In Duckietown Project

Krinkin, Kirill; CHayka, Konstantin; Filatov, Antón; Filatov, Artyom

doi:10.1016/j.procs.2021.04.135

Cited by 3 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The proposed method was evaluated using three datasets, including CitySpaces’ dataset (5000 images) [ 31 ], KITTI’s dataset (400 images) [ 32 ], and Duckie’s dataset collected from Ducktown (1200 images) [ 33 ]. In addition, we collected a set of 1200 additional authentic images from the Ta Quang Buu library to enhance the dataset.…”

Section: Resultsmentioning

confidence: 99%

“… Raw images from four datasets of CitySpaces [ 31 ], KITTI [ 32 ], Ducktown [ 33 ], and TaQuangBuu’s dataset. …”

Section: Figurementioning

confidence: 99%

“…The proposed model was trained on four datasets (Figure 4), which include Cit-ySpaces (5000 images) [31], KITTI (400 images) [32], Duckie-dataset collected from Ducktown (1200 images) [33], and TaQuangBuu's dataset consisting of 1200 images collected from Ta Quang Buu library supplied in the Data Availability Statement. [31], KITTI [32], Ducktown [33], and TaQuangBuu's dataset.…”

Section: Model Trainingmentioning

confidence: 99%

“…When using the Binary Cross Entropy as loss function, the learning model tends to favor the object that appears more frequently in the data. Adding more instances of the less dominant class to training data might potentially solve [31], KITTI [32], Ducktown [33], and TaQuangBuu's dataset.…”

Section: Model Trainingmentioning

confidence: 99%

See 3 more Smart Citations

IRDC-Net: Lightweight Semantic Segmentation Network Based on Monocular Camera for Mobile Robot Navigation

Dang

Tran

Tan

2023

Sensors

View full text Add to dashboard Cite

Computer vision plays a significant role in mobile robot navigation due to the wealth of information extracted from digital images. Mobile robots localize and move to the intended destination based on the captured images. Due to the complexity of the environment, obstacle avoidance still requires a complex sensor system with a high computational efficiency requirement. This study offers a real-time solution to the problem of extracting corridor scenes from a single image using a lightweight semantic segmentation model integrating with the quantization technique to reduce the numerous training parameters and computational costs. The proposed model consists of an FCN as the decoder and MobilenetV2 as the decoder (with multi-scale fusion). This combination allows us to significantly minimize computation time while achieving high precision. Moreover, in this study, we also propose to use the Balance Cross-Entropy loss function to handle diverse datasets, especially those with class imbalances and to integrate a number of techniques, for example, the Adam optimizer and Gaussian filters, to enhance segmentation performance. The results demonstrate that our model can outperform baselines across different datasets. Moreover, when being applied to practical experiments with a real mobile robot, the proposed model’s performance is still consistent, supporting the optimal path planning, allowing the mobile robot to efficiently and effectively avoid the obstacles.

show abstract

Section: Resultsmentioning

confidence: 99%

“… Raw images from four datasets of CitySpaces [ 31 ], KITTI [ 32 ], Ducktown [ 33 ], and TaQuangBuu’s dataset. …”

Section: Figurementioning

confidence: 99%

Section: Model Trainingmentioning

confidence: 99%

Section: Model Trainingmentioning

confidence: 99%

See 2 more Smart Citations

IRDC-Net: Lightweight Semantic Segmentation Network Based on Monocular Camera for Mobile Robot Navigation

Dang

Tran

Tan

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…fiducial markers) представляют собой набор визуальных искусственных объектов, предназначенных для робастного обнаружения их среди других объектов окружения на изображениях. Они используются для широкого круга задач: компьютерное зрение, дополненная реальность (AR) [1], робототехника [2], калибровка камер [3] и во многих других областях.…”

Section: Introductionunclassified

Computer Modeling of Fiducial Markers Images to Estimate the Accuracy of Object Positioning in Space

Sivov

Poroykov

2022

Proceedings of the 32nd International Conference on Computer Graphics and Vision

View full text Add to dashboard Cite

Fiducial markers are widely used in machine vision systems. One of the main ways of their application is to estimate the relative position of the camera and marker in space. The latter are visual artificial objects, which are designed for their robust detection among other objects in the environment of the images. Examples of fiducial marker accuracy estimation are found in many studies. Usually such studies are conducted for one or two or three code marker systems. And accuracy estimates are given only for specific parameters of the machine vision system, which is designed by the authors of the work. This approach is not universal, and for other parameters it is necessary to carry out the error estimation again. This paper presents an approach to determining the error for comparing more fiducial marker systems with each other using more universal metrics. For this purpose, computer simulations of marker images were performed for five different systems with different spatial orientations. The images were processed using detection algorithms proposed by the authors of the marker systems. The processing results were compared with the specified parameters in the simulations. Relative error estimates were obtained for the five different code marker systems.

show abstract

Research on Stability of Gray Value of Excited-State Fluorescent Oil Film Based on Variable Light Vector Angle

Qian

Dong

Zhang

2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

In global skin-friction measurement of aircraft, the fluorescent oil film method can characterize the distribution of skin friction well. However, in an actual wind tunnel test, the wing of the aircraft will inevitably produce corresponding vibrations due to the influence of wind, which will change the relative position between fluorescent oil film and UV (ultraviolet) excitation light source (position fixed). This also directly affects gray value imaging of fluorescent oil films. Based on this, a mathematical model is established to judge the stability of the gray value of fluorescent oil film in this vibrational environment; then, the model can be solved to obtain the vibrational range constraint that enables the gray value of fluorescent oil film to be stabilized. In order to simplify the calculation process, the light vector angle is used to describe the constraint, which also makes the results more intuitive. Through experimental analysis and demonstration, the prediction accuracy of this model can reach 95.61%, which has certain practical engineering application significance.

show abstract

Autonomous Wheels And Camera Calibration In Duckietown Project

Cited by 3 publications

References 6 publications

IRDC-Net: Lightweight Semantic Segmentation Network Based on Monocular Camera for Mobile Robot Navigation

IRDC-Net: Lightweight Semantic Segmentation Network Based on Monocular Camera for Mobile Robot Navigation

Computer Modeling of Fiducial Markers Images to Estimate the Accuracy of Object Positioning in Space

Research on Stability of Gray Value of Excited-State Fluorescent Oil Film Based on Variable Light Vector Angle

Contact Info

Product

Resources

About