Artificial Intelligence based Camera Calibration

Raza, Syed Navid; Rehman, Hafiz Raza ur; Lee, Suk Gyu; Choi, Gyu Sang

doi:10.1109/iwcmc.2019.8766666

Cited by 18 publications

(13 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the known grid size of the checkerboard and the unknown exact ground truth for real data, we only compute the MERE index, as is done in [5,10], and the CDR index. Figure 6 shows two examples of detected results by the proposed detector.…”

Section: Real Data Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A highly accurate and robust deep checkerboard corner detector

2021

Electronics Letters

View full text Add to dashboard Cite

Checkerboard corners are routinely used during tasks such as camera calibration, and accurate detection of them is essential. Traditional methods such as those based on the Harris corner detector are usually affected by image artefacts such as noise and blur. The more recently proposed deep network approach also suffers from the lack of accurate training data. In this article, we make the following contributions: First, we propose a synthetic training data generation method that simulates the real imaging process, with the most notable being that the exact sub‐pixel corner positions in the image become readily available. Second, we design a relatively simple deep network and train it using the synthetic data generated by the proposed method. Finally, because the exact sub‐pixel corner positions can be obtained in the proposed method, this article paves a way for objectively comparing different checkerboard corner detectors in terms of metrics such as the mean Euclidean location error. Experimental results using both synthetic and real data show that the proposed detector significantly outperforms typical methods, including the commonly used Matlab camera calibration toolbox, the OpenCV checkerboard corner detectors, and the more recently proposed deep learning‐based methods.

show abstract

Section: Real Data Resultsmentioning

confidence: 99%

“…Implementation details: Unlike other deep learning-based methods (e.g. [8][9][10] ) that are trained on real datasets with manually annotated corner positions, we train our network on synthetic dataset with exact ground truth corner positions.…”

Section: Non-maximum Suppression Post-processingmentioning

confidence: 99%

A highly accurate and robust deep checkerboard corner detector

2021

Electronics Letters

View full text Add to dashboard Cite

show abstract

“…This system is an object detection system that uses a camera to capture the environment and receive messages back to Raspberry Pi. The camera records video as the pet approaches a certain location [1]. All the information is sent to a server through Raspberry Pi.…”

Section: Solutionmentioning

confidence: 99%

“…Raza and Syed mention that camera calibration is important for collecting more precise data [11]. Three dimensional data is harder to collect because most of the cameras are designed to collect two dimensional images.…”

Section: Related Workmentioning

confidence: 99%

An Internet-of-Things (IoT) System to Automate the Pet Door Controlling using Artificial Intelligence and Computer Vision

Yu¹

2021

Software Engineering and Applications

View full text Add to dashboard Cite

Pets are cute and fun, but sometimes it gets annoying when you are trying to get some sleep in [14]. Also the population of people who would like to be accompanied by pets is rising rapidly. However, people these days lack time to meet all requirements of pets, which causes plenty of tragedies [3]. In this paper, we designed an application/tool called Automate the Pet Door Controlling which is using artificial intelligence and Computer vision to create a better living condition for pets, and a easier life for people who love their pets, especially for those who cannot spend a lot of time or physically hard to open doors for pets. My design builds an integratable system which is available for most smart home systems, also this design supports extra datasets imported to enlarge the types of pets.

show abstract

“…Javadnejad et al, 2019;Shortis, 2019) -is directly reflected in a steadily ongoing research which addresses issues such as computational efficiency, poor lighting/contrast, non-homogeneous illumination, overexposure, image blur, low image resolution, image noise, si-gnificant image distortion, missing corner points or partial occlusion of patterns, extreme imaging poses, board printing inaccuracy or deviations from planarity (recent works include Duda & Frese, 2018;Yamaguchi et al, 2018;Yan et al, 2018;Hannemose et al, 2019;Meng et al, 2019;Wholfeil et al, 2019;Zhu et al, 2019). Deep learning tools have also been recently used for robust detection of checkboard corners (Donné et al, 2016;Raza et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Camera Calibration Using Multiple Unordered Coplanar Chessboards

Γραμματικόπουλος

Adam

Petsa

et al. 2019

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. The now widely available and highly popular among non-expert users, particularly in the context of UAV photogrammetry, Structure-from-Motion (SfM) pipelines have also further renewed the interest in the issue of automatic camera calibration. The well-documented requirements for robust self-calibration cannot be always met, e.g. due to restrictions in time and cost, absence of ground control and image tilt, terrain morphology, unsuitable flight configuration etc.; hence, camera pre-calibration is frequently recommended. In this context, users often resort to flexible, user-friendly tools for camera calibration based on 2D coded patterns (primarily ordinary chessboards). Yet, the physical size of such patterns poses obvious limitations. This paper discusses the alternative of extending the size of the calibration object by using multiple unordered coplanar chessboards, which might accommodate much larger imaging distances. This is done initially by a detailed simulation to show that – in terms of geometry – this could be a viable alternative to single patterns. A first algorithmic implementation is then laid out, and results from real multi-pattern configurations, both ordered and unordered, are successfully compared. However, aspects of the proposed approach need to be further studied for its reliable practical employment.

show abstract

Artificial Intelligence based Camera Calibration

Cited by 18 publications

References 12 publications

A highly accurate and robust deep checkerboard corner detector

A highly accurate and robust deep checkerboard corner detector

An Internet-of-Things (IoT) System to Automate the Pet Door Controlling using Artificial Intelligence and Computer Vision

Camera Calibration Using Multiple Unordered Coplanar Chessboards

Contact Info

Product

Resources

About