A new algorithm for ball recognition using circle Hough transform and neural classifier

D’Orazio, Tiziana; Guaragnella, Cataldo; Leo, Marco; Distante, A.

doi:10.1016/s0031-3203(03)00228-0

Cited by 122 publications

(67 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Even for the reduced class of objects that we chose as targets, many different detection algorithms have been developed, based, e.g., on binary contours [22], background subtraction [23] or the Hough transform [24]. Following our objective of simplicity and high speed, we use a feedforward architecture based on a linear shift invariant filter (LSI) [11].…”

Section: Object Detectionmentioning

confidence: 99%

Real-time detection of colored objects in multiple camera streams with off-the-shelf hardware components

Lampert

Peters

2010

J Real-Time Image Proc

View full text Add to dashboard Cite

We describe RTblob, a high speed vision system that detects objects in cluttered scenes based on their color and shape at a speed of over 800 frames per second. Because the system is available as open-source software and relies only on off-the-shelf PC hardware components, it can provide the basis for multiple application scenarios. As an illustrative example, we show how RTblob can be used in a robotic table tennis scenario to estimate ball trajectories through 3D space simultaneously from four cameras images at a speed of 200 Hz.

show abstract

Section: Object Detectionmentioning

confidence: 99%

Real-time detection of colored objects in multiple camera streams with off-the-shelf hardware components

Lampert

Peters

2010

J Real-Time Image Proc

View full text Add to dashboard Cite

show abstract

“…The success of these approaches depends on the accuracy of the edges while line thickness is not considered. Although this family of methods has been largely applied in many real contexts [27][28][29][30], its main drawback is the strict requirement of the complete specification of the target object's exact shape to achieve precise localization, which is often difficult and not available for complex curvilinear structures in practice.…”

Section: Introductionmentioning

confidence: 99%

Automated Extraction of Archaeological Traces by a Modified Variance Analysis

et al. 2015

View full text Add to dashboard Cite

This paper considers the problem of detecting archaeological traces in digital aerial images by analyzing the pixel variance over regions around selected points. In order to decide if a point belongs to an archaeological trace or not, its surrounding regions are considered. The one-way ANalysis Of VAriance (ANOVA) is applied several times to detect the differences among these regions; in particular the expected shape of the mark to be detected is used in each region. Furthermore, an effect size parameter is defined by comparing the statistics of these regions with the statistics of the entire population in order to measure how strongly the trace is appreciable. Experiments on synthetic and real images demonstrate the effectiveness of the proposed approach with respect to some state-of-the-art methodologies.

show abstract

“…Other relevant applications are those analyses of golf [4], tennis [5], American football [6], hockey [7], baseball [8] and basketball [9] as well as ping pong and cricket [10], etc. Through image and motion analysis, additional information can be extracted for better comprehension of video and sports contents, such as video content annotation, summarization, team strategy analysis and verification of referee decisions, as well as further 2D/3D reconstruction and visualization [11][12][13][14][15][16].…”

Section: Introductionmentioning

confidence: 99%

“…Although motion-based tracking models are introduced in [11] and [16], there is no given process to automatically identify the ball before tracking. In Matsumoto et al [12] and D' Orazio et al [14], template matching and a modified Hough transform are presented to detect balls in soccer videos respectively. Since irregular ball shapes are usually extracted in different velocities, these two methods are still insufficient.…”

Section: Introductionmentioning

confidence: 99%