Introducing a novel marker-based geometry model in monocular vision

Bousaid, Alexandre; Theodoridis, Theodoros; Nefti‐Meziani, Samia

doi:10.1109/wpnc.2016.7822857

Cited by 3 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this particular case, where C is a midpoint and is coincident and perpendicular to the image plane, x C = (x A + x B )/2, x C becomes equivalent to the distance of the target from the COP. This leads to (3).…”

Section: Distortion On Centred Targetsmentioning

confidence: 99%

See 1 more Smart Citation

Perspective Distortion Modeling for Image Measurements

et al. 2020

Self Cite

View full text Add to dashboard Cite

A perspective distortion modelling for monocular view that is based on the fundamentals of perspective projection is presented in this work. Perspective projection is considered to be the most ideal and realistic model among others, which depicts image formation in monocular vision. There are many approaches trying to model and estimate the perspective effects in images. Some approaches try to learn and model the distortion parameters from a set of training data that work only for a predefined structure. None of the existing methods provide deep understanding of the nature of perspective problems. Perspective distortions, in fact, can be described by three different perspective effects. These effects are pose, distance and foreshortening. They are the cause of the aberrant appearance of object shapes in images. Understanding these phenomena have long been an interesting topic for artists, designers and scientists. In many cases, this problem has to be necessarily taken into consideration when dealing with image diagnostics, high and accurate image measurement, as well as accurate pose estimation from images. In this work, a perspective distortion model for every effect is developed while elaborating the nature of perspective effects. A distortion factor for every effect is derived, then followed by proposed methods, which allows extracting the true target pose and distance, and correcting image measurements.

show abstract

Section: Distortion On Centred Targetsmentioning

confidence: 99%

“…In perspective view everything changes like proportions, size, shapes, the angles that we see and even overlapped objects in the scene start to appear [1], [2]. The implication, out of perspective nature, results in the proposition of the perspective projection properties [3].…”

Section: Introductionmentioning

confidence: 99%

Perspective Distortion Modeling for Image Measurements

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this paper, we have developed a computer vision algorithm to detect potential obstacles along the path of the USR by using a single camera attached at the head module of the robot and reflective markers on the obstacles. The area of the markers is a priori knowledge and can be used to calculate the 3D distance based on the corresponding area in the image similar to Bousaid et al ( 2016 ). Different geometric shapes (i.e., triangle, square and circle).…”

Section: Introductionmentioning

confidence: 99%

Path Following, Obstacle Detection and Obstacle Avoidance for Thrusted Underwater Snake Robots

et al. 2019

View full text Add to dashboard Cite

The use of unmanned underwater vehicles is steadily increasing for a variety of applications such as mapping, monitoring, inspection and intervention within several research fields and industries, e.g., oceanography, marine biology, military, and oil and gas. Particularly interesting types of unmanned underwater vehicles are bio-inspired robots such as underwater snake robots (USRs). Due to their flexible and slender body, these versatile robots are highly maneuverable and have better access capabilities than more conventional remotely operated vehicles (ROVs). Moreover, the long and slender body allows for energy-efficient transit over long distances similar to torpedo-shaped autonomous underwater vehicles (AUVs). In addition, USRs are capable of performing light intervention tasks, thereby providing intervention capabilities which exceed those of AUVs and inspection class ROVs. USRs may also propel themselves using energy-efficient motion patterns inspired by their biological counterparts. They can thereby increase the propulsion efficiency during transit and maneuvering, which is among the great challenges for autonomous underwater vehicles. In this paper, a control system for path following, and algorithms for obstacle detection and avoidance, are presented for a USR with thrusters attached at the tail module. The position of the obstacles is detected using a single camera in the head module of the USR and a developed computer vision algorithm. For the proposed control concept the robot joints are used for directional control while the thrusters are used for forward propulsion. The USR circumvents obstacles by following a circular path around them before converging back to the main straight line path when this is safe. Experimental results that validate the proposed methods are also presented.

show abstract

Room‐Restricted Technologies: Challenges and Reliability

2019

Indoor Positioning

View full text Add to dashboard Cite

Introducing a novel marker-based geometry model in monocular vision

Cited by 3 publications

References 8 publications

Perspective Distortion Modeling for Image Measurements

Perspective Distortion Modeling for Image Measurements

Path Following, Obstacle Detection and Obstacle Avoidance for Thrusted Underwater Snake Robots

Room‐Restricted Technologies: Challenges and Reliability

Contact Info

Product

Resources

About