Results 91 to 100 of about 8,796 (251)

Inferring Brown Bear Hair Snare Interactions by Automatically Detecting Bipedalism on Camera Trap Images Using Pose Estimation and a Multilayer Perceptron

Remote Sensing in Ecology and Conservation, EarlyView.
This study proposes an automated method to infer brown bear hair snare interactions by detecting bipedal behavior in camera‐trap images using a pose estimation model and a multilayer perceptron (MLP). A YOLO‐based model, fine‐tuned from humans and dogs to a custom dataset, achieved high performance (≈93% keypoint precision and ≈96% classification ...
Arnau Campanera‐Moliné, Víctor Sazatornil, Lluís Brotons, Felipe Lumbreras Ruiz, Robert Benavente, Maguiña Ramilo‐Henry, Cristina Ramos, Santiago Palazón, Daniel Ponsa   +8 more
wiley   +1 more source

Fusion or Confusion? Assessing the Impact of Visible‐Thermal Image Fusion for Automated Wildlife Detection

Remote Sensing in Ecology and Conservation, EarlyView.
This study evaluates the performances of synchronous aerial visible (VIS) and thermal infrared (TIR) imagery for detecting great blue heron (Ardea herodias) nests and individuals using a YOLO11n model. VIS and TIR images were automatically aligned using deep learning, and both early and late fusion approaches were tested.
Camille Dionne‐Pierre, Samuel Foucher, Jérôme Théau, Jérôme Lemaître, Patrick Charbonneau, Maxime Brousseau, Mathieu Varin   +6 more
wiley   +1 more source

Instance Detection by Keypoint Matching Beyond the Nearest Neighbor [PDF]

, 2016
The binary descriptors are the representation of choice for real-time keypoint matching. However, they suffer from reduced matching rates due to their discrete nature.
Uzyıldırım, Furkan Eren, Özuysal, Mustafa   +1 more
core   +4 more sources

SFK: Shape‐ and Function‐Grounded Keypoint Representation for Sequential Manipulation

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Sequential manipulation is the process by which robots perform multiple interdependent steps to accomplish composite tasks, demanding tight integration of perception, planning and execution. Existing methods incorporate explicit features such as category, semantics, 6D pose or affordance to enhance consistency, yet single‐feature ...
Yaxin Liu, Yan Liu, Xinyu Song, Ruiqing Han, Haiyong Liu, Bo Huang, Yufeng Yao, Ming Zhong   +7 more
wiley   +1 more source

Reducing Keypoint Database Size [PDF]

, 2009
Keypoints are high dimensional descriptors for local features of an image or an object. Keypoint extraction is the first task in various computer vision algorithms, where the keypoints are then stored in a database used as the basis for comparing images or image features. Keypoints may be based on image features extracted by feature detection operators
Shahar Jamshy, Eyal Krupka, Yehezkel Yeshurun   +2 more
openaire   +1 more source

Boosting Embodied Visual Localisation Through Multi‐Granular Semantics and Multi‐Robot Consensus

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Achieving high accuracy and synergy remains extremely difficult for multi‐robot embodied visual localisation, which suffers from persistent real‐world challenges such as viewpoint ambiguity, appearance variation and dynamic occlusion. Conventional optimisation‐based methods often lead to incorrect feature matching without domain adaptation ...
Wenshuai Wang, Shiyu Liu, Peifeng Jiang, Hong Liu, Runwei Ding   +4 more
wiley   +1 more source

Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection

2025 IEEE/CVF International Conference on Computer Vision (ICCV)
Keypoint detection, integral to modern machine perception, faces challenges in few-shot learning, particularly when source data from the same distribution as the query is unavailable. This gap is addressed by leveraging sketches, a popular form of human expression, providing a source-free alternative.
Subhajit Maity, Ayan Kumar Bhunia, Subhadeep Koley, Pinaki Nath Chowdhury, Aneeshan Sain, Yi-Zhe Song   +5 more
openaire   +2 more sources

Regional Infrared and Visible Image Registration for Distribution Substation Areas With Wide Depth of Field

High Voltage, EarlyView.
ABSTRACT Infrared and visible image registration is a key task in automated distribution network inspection. Previous approaches typically apply a single homography to align infrared and visible images leading to local misalignment. To address this, this study proposes a novel region‐based registration algorithm specifically designed for wide‐depth ...
Yingchen Zhang, Bo Wang, Fei Tang
wiley   +1 more source

Temperature Extraction Scheme for Composite Insulator Core Rod Sheath of Overhead Transmission Lines Based on Oriented Bounding Boxes

High Voltage, EarlyView.
ABSTRACT Unmanned Aerial Vehicle (UAV) inspection of overhead transmission line composite insulators allows for the rapid acquisition of large amounts of infrared images of insulators in service, which can be used to analyse their operational status. However, efficiently and accurately analysing these images remains a challenge.
Zhenan Zhou, Xinzhe Yu, Yu Deng, Chen Gu, Kun Zhang, Zheyuan Liu, Songsong Zhou, Yueneng Xu   +7 more
wiley   +1 more source

3D face recognition via discriminative keypoint selection [PDF]

, 2017
In this paper, we propose a discriminative keypoint selection-based 3D face recognition method that is superior to prevalent techniques in terms of both computational complexity and performance.
Hwang, Wonjun, Dongyoon Han, Kim, Jiwhan, Wonjun Hwang, Jiwhan Kim, Han, Dongyoon, Kim, Junmo, Junmo Kim   +7 more
core   +1 more source