Visual ordnance recognition for clearing test ranges

Olson, Clark F.; Matthies, Larry

doi:10.1117/12.324184

Cited by 3 publications

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Adaptive-scale filtering and feature detection using range data

Olson

2000

IEEE Trans. Pattern Anal. Machine Intell.

View full text Add to dashboard Cite

ÐIn edge and corner detection applications, it is typical to examine a single scale without knowing which scale is appropriate for each location in the image. However, many images contain a wide variation in the distance to the scene pixels and, thus, features of the same size can appear at greatly differing scales in the image. We present a method where the scale of the filtering and feature detection is varied locally according to the distance to the scene pixel, which we estimate through stereoscopy. The features that are detected are, thus, at the same scale in the world, rather than at the same scale in the image. This method has been implemented efficiently by filtering the image at a discrete set of scales and performing interpolation to estimate the response at the correct scale for each pixel. The application of this technique to an ordnance recognition problem has resulted in a considerable improvement in performance.

show abstract

Adaptive-scale filtering and feature detection using range data

Olson

2000

IEEE Trans. Pattern Anal. Machine Intell.

View full text Add to dashboard Cite

show abstract

Variable-scale smoothing and edge detection guided by stereoscopy

Olson

Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231)

View full text Add to dashboard Cite

It is typical in edge detection applications to examine a single scale or to consider some space o f s c ales in the image without knowing which scale is appropriate for each location in the image. However, many images contain a wide variation in the distance to the scene points, and thus objects of the same size can appear at greatly di ering scales in the image. We present a method where the scale of the smoothing and edge detection is varied l o cally according to the distance t o t h e scene point, which we estimate through stereoscopy. The edges that are detected a r e thus at the same scale in the world, rather than at the same scale in the image. This method has been implemented e ciently by smoothing the image at a discrete set of scales and performing interpolation to estimate the response at the correct scale for each pixel. The application of this technique to an ordnance recognition problem has resulted i n a c onsiderable improvement in performance.

show abstract

Analysis of Computer Vision Methods and Means for Explosive Ordnance Detection Mobile Systems

Mishchuk,

Fesenko

2024

Èlektron. model.

View full text Add to dashboard Cite

The detection and removal of unexploded ordnance and landmines are vital for ensuring civil-ian safety, enabling the repurposing of affected land, and supporting post-conflict recovery ef-forts. Robotization plays a pivotal role in addressing the hazardous and labor-intensive nature of demining operations. The purpose of this paper is to review prominent computer vision tech-niques, particularly object detection, and analyze their applications in the specialized domain of explosive ordnance detection. An extensive review of the literature was conducted to explore the utilization of computer vision in the field of explosive ordnance detection. The study in-volved a comparative analysis of diverse imaging sensors employed for data capture. Special at-tention was given to reviewing sources that elaborate on different methods for detecting objects within the field of computer vision. Various approaches to object detection were thoroughly examined and compared. The research extensively examined the metrics and datasets used to evaluate different approaches for object detection. Possibilities of applying computer vision methods to detect explosive ordnance under the limitations of mobile platforms were studied. Directions of future research are formulated.

show abstract

Visual ordnance recognition for clearing test ranges

Cited by 3 publications

References 13 publications

Adaptive-scale filtering and feature detection using range data

Adaptive-scale filtering and feature detection using range data

Variable-scale smoothing and edge detection guided by stereoscopy

Analysis of Computer Vision Methods and Means for Explosive Ordnance Detection Mobile Systems

Contact Info

Product

Resources

About