Learning OpenCV---Computer Vision with the OpenCV Library (Bradski, G.R. et al.; 2008)[On the Shelf]

By A. Zelinsky. 2009

3,427 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

CNN-Generated Images Are Surprisingly Easy to Spot… for Now (2019, methodology): “We evaluate several additional augmentation variants: (1) No aug : no augmentation applied, (2) Gaussian blur : before cropping, with 50% probability, images are blurred with σ ∼ Uniform [0 , 3] , (3) JPEG : with 50% probability images are JPEG-ed by two popular libraries, OpenCV [8] and the Python ”
Weight Agnostic Neural Networks (2019, methodology): “The MNIST version used in this paper is a downsampled version, reducing the digits from [28x28] to [16x16], and deskewed using the OpenCV library[7].”
CloudCV: Large-Scale Distributed Computer Vision as a Cloud Service (2015, methodology): “CloudCV VIP uses OpenCV [25] to avoid network latency.”
Autonomous door opening and plugging in with a personal robot (2010, methodology): “Similarly, to expedite computer vision tasks, we make extensive use of the Open Source Computer Vision library OpenCV 4 [19].”
A New Deep Learning-Based Food Recognition System for Dietary Assessment on An Edge Computing Service Infrastructure (2018, methodology): “shed algorithm runs on the local mobile devices and it is implemented using OpenCV [52] on Android devices.”
Shadow detection: A survey and comparative evaluation of recent methods (2012, background): “0 [3] to extract a foreground mask on each frame.”
A survey on face detection in the wild: Past, present and future (2015, background): “Notable examples include the OpenCV series of releases [36], the series of deformable parts-based models releases [37], as well as the recent efforts to make a high quality repository of convolutional neural network architectures [38].”
Extracting code from programming tutorial videos (2016, methodology): “We use Canny edge detection [3] and we apply a standard tool for finding contours.”
PERCEPTUAL GOAL SPECIFICATIONS FOR REINFORCEMENT LEARNING (2017, methodology): “In order to compute TA, we use template matching [8] to find the maximally matching window within the agent’s mirror state.”
T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-Less Objects (2017, methodology): “Intrinsic and distortion parameters of the sensors were estimated with the standard checkerboard-based procedure using OpenCV [6].”
HERB: a home exploring robotic butler (2010, methodology): “OpenCV checkerboard detector (Bradski and Kaehler 2008), which can run at 5 frames per second on a quad-core machine while simultaneously recognizing up to four different types of checkerboards.”
Assessing Threat of Adversarial Examples on Deep Neural Networks (2016, methodology): “Without details of the rescaling steps, we approximate what we consider the most important step, binarization, using an OpenCV [17] version of OTSU thresholding [18].”
Use of SIMD Vector Operations to Accelerate Application Code Performance on Low-Powered ARM and Intel Platforms (2013, methodology): “E XPERIMENTAL E VALUATION To investigate the ability of NEON operations in providing performance speed-ups with comparison to SSE2 operations, we use a set of image processing benchmarks from the popular OpenCV library [24].”
RTAB‐Map as an open‐source lidar and visual simultaneous localization and mapping library for large‐scale and long‐term online operation (2018, methodology): “(cid:129) Motion Estimation: When correspondences are computed, the Perspective ‐ n ‐ Point RANSAC implementation of OpenCV (Bradski & Kaehler, 2008) is used to compute the transformation of the current frame accordingly to features in Key Frame (F2F) or Feature Map (F2M).”
Fast 3D recognition and pose using the Viewpoint Feature Histogram (2010, methodology): “The stereo algorithm that we use was developed in [19] and uses the implementation in the OpenCV library [20] as described in detail in [21], running at 30Hz.”
A review of multimodal image matching: Methods and applications (2021, methodology): “ORB is implemented with OpenCV library [475], and the others are implemented by MATLAB Toolbox.”
Activity representation with motion hierarchies (2013, positive): “First, we compute the dense optical ﬂow ﬁeld of the video using the algorithm of [Farneb¨ack, 2003] as implemented in the OpenCV library [Bradski and Kaehler, 2008].”