Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Topographic Surveying and Contours

Topographic Surveying and Contours

Topographic surveying is critical for documenting the Earth's surface, focusing on capturing elevations, slopes, and natural and man-made features. It is essential in construction planning, water resource management, and land-use analysis. The primary outcome of such surveys is a topographic map, which uses contour lines to visually represent the shape and slope of the terrain, providing valuable insights into the landscape's characteristics.Contour lines are fundamental to understanding the...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

A data-driven approach to determine the minimum number of spot samples for estimating methane and carbon dioxide emissions from Austrian dairy cows on commercial farms using GreenFeed.

Journal of dairy science·2026

Same author

dVP_FAM-development and evaluation of a transsectoral digital care platform for individuals with familial cancer risks: study protocol for a multi-centre, cluster-randomised, mixed-methods study.

Trials·2025

Same author

Incidence of neutrophil extracellular traps (NETs) in different membrane oxygenators: pilot in vitro experiments in commercially available coated membranes.

Journal of artificial organs : the official journal of the Japanese Society for Artificial Organs·2025

Same author

Predictive preoperative clinical score for patients with liver-only oligometastatic colorectal cancer.

ESMO open·2022

Same author

Mid-Term Outcomes of a Hybrid Approach Involving Open Surgery Plus TEVAR of the Descending Aorta in the Treatment of Complex Type A Dissection.

The Thoracic and cardiovascular surgeon·2022

Same author

Effects of temporal fine structure preservation on spatial hearing in bilateral cochlear implant users.

The Journal of the Acoustical Society of America·2021

Search research articles

Related Experiment Video

Updated: Jul 10, 2026

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Groups of adjacent contour segments for object detection.

V Ferrari¹, L Fevrier, F Jurie

¹Department of Engineering Science, University of Oxford, Oxford, UK. ferrari@robots.ox.ac.uk

IEEE Transactions on Pattern Analysis and Machine Intelligence

|November 15, 2007

Summary

We introduce k-chained, approximately straight contour segments (kAS), a novel scale-invariant local shape feature for robust object detection. kAS outperform traditional interest points in shape-based recognition tasks.

More Related Videos

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Related Experiment Videos

Last Updated: Jul 10, 2026

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Area of Science:

Computer Vision
Machine Learning
Pattern Recognition

Background:

Object detection often struggles with clutter and scale variations.
Local shape features are crucial for identifying objects based on their boundaries.
Existing methods like interest points have limitations in capturing complex shape information.

Purpose of the Study:

To introduce a new family of scale-invariant local shape features called k-chained, approximately straight contour segments (kAS).
To demonstrate the effectiveness of kAS for object class detection, particularly in cluttered environments.
To provide a reusable descriptor for kAS that is invariant to translation and scale.

Main Methods:

Developed kAS features by chaining k connected, roughly straight contour segments.
Defined a translation and scale invariant descriptor for kAS geometric configurations.
Implemented a sliding-window object detection scheme utilizing kAS features.
Conducted extensive evaluations on eight diverse object classes and over 1400 images.

Main Results:

kAS features effectively encode object boundary fragments, excluding clutter.
Performance was analyzed across varying feature complexity (k), identifying optimal degrees.
kAS features significantly outperformed interest points for shape-based object detection.
The proposed kAS detector demonstrated competitive performance against state-of-the-art systems.

Conclusions:

kAS features offer a powerful and repeatable representation of local shape structures.
The scale and translation invariant descriptor enhances the reusability of kAS features.
kAS present a significant advancement for object class detection, especially for shape-centric recognition.