Vision-based pirouettes using radial obstacle profile

Taylor, Trevor; Geva, Shlomo; Boles, Wageeh

doi:10.1109/ramech.2004.1438907

Cited by 4 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is remotely controlled by a PC via a wireless modem. A wireless colour camera on top of the robot is used to locate obstacles in the surrounding environment [13]. By performing a pirouette (spinning around on the spot) the robot builds a 360° view of its surroundings.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Directed Exploration Using a Modified Distance Transform

Taylor

Geva

Boles

2005

Digital Image Computing: Techniques and Applications (DICTA'05)

Self Cite

View full text Add to dashboard Cite

Mobile robots operating in unknown environments need to build maps. To do so they must have an exploration algorithm to plan a path. This algorithm should guarantee that the whole of the environment, or at least some designated area, will be mapped. The path should also be optimal in some sense and not simply a "random walk" which is clearly inefficient. When multiple robots are involved, the algorithm also needs to take advantage of the fact that the robots can share the task. In this paper we discuss a modification to the well-known distance transform that satisfies these requirements.

show abstract

Section: Methodsmentioning

confidence: 99%

“…The procedure for obtaining an ROP and creating a map has been described in our previous work [13]. Therefore step 1 above is not covered here.…”

mentioning

confidence: 99%

Directed Exploration Using a Modified Distance Transform

Taylor

Geva

Boles

2005

Digital Image Computing: Techniques and Applications (DICTA'05)

Self Cite

View full text Add to dashboard Cite

show abstract

“…A distance estimate is often done in one of two ways: based on positional information or size information. Referring to the findings of the research by Taylor et al [36], if an object is on the same plane as the camera, the position of the object in pixel coordinates can be converted to the real-world coordinates. The distance between the object and the camera can be estimated by a single image from a monocular camera, of which the FOV is known.…”

Section: Distance Estimation Using Position Informationmentioning

confidence: 99%

A Lightweight Robust Distance Estimation Method for Navigation Aiding in Unsupervised Environment Using Monocular Camera

Chou,

Wong,

Wong

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

This research addresses the challenges of visually impaired individuals’ independent travel by avoiding obstacles. The study proposes a distance estimation method for uncontrolled three-dimensional environments to aid navigation towards labeled target objects. Utilizing a monocular camera, the method captures cuboid objects (e.g., fences, pillars) for near-front distance estimation. A Field of View (FOV) model calculates the camera’s angle and arbitrary pitch relative to the target Point of Interest (POI) within the image. Experimental results demonstrate the method’s proficiency in detecting distances between objects and the source camera, employing the FOV and Point of View (POV) principles. The approach achieves a mean absolute percentage error (MAPE) of 6.18% and 6.24% on YOLOv4-tiny and YOLOv4, respectively, within 10 m. The distance model only contributes a maximum error of 4% due to POV simplification, affected by target object characteristics, height, and selected POV. The proposed distance estimation method shows promise in drone racing navigation, EV autopilot, and aiding visually impaired individuals. It offers valuable insights into dynamic 3D environment distance estimation, advancing computer vision and autonomous systems.

show abstract

“…In the case of the Palmbot, a point to note is how the 3-dimensional perspective can be taken into account in the state formation -in Figure 5 the near state ranges across the bottom 4 grid squares, compared to the far state which only ranges across the top 2 grid squares. This is because an 2-dimensional image of a 3-dimensional space has more horizontal distance in that space associated with the grid spaces higher in the image (which are closer to the horizon) [19]. This is easily accounted for in the distance abstraction membership functions of near, medium and far (shown in Figure 6 corresponding to the right side of Figure 5).…”

Section: Using Computer Visionmentioning

confidence: 99%