This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a substantial range of affine distortion, change in 3D viewpoint, addition of noise, and change in illumination. The features are highly distinctive, in the sense that a single feature can be correctly matched with high probability against a large database of features from many images. This paper also describes an approach to using these features for object recognition. The recognition proceeds by matching individual features to a database of features from known objects using a fast nearest-neighbor algorithm, followed by a Hough transform to identify clusters belonging to a single object, and finally performing verification through least-squares solution for consistent pose parameters. This approach to recognition can robustly identify objects among clutter and occlusion while achieving near real-time performance.

/pdf/distinctive-image-features-from-scale-invariant-keypoints-3waurjqzke.pdf

Distinctive Image Features from Scale-Invariant Keypoints

Fiji is a distribution of the popular open-source software ImageJ focused on biological-image analysis. Fiji uses modern software engineering practices to combine powerful software libraries with a broad range of scripting languages to enable rapid prototyping of image-processing algorithms. Fiji facilitates the transformation of new algorithms into ImageJ plugins that can be shared with end users through an integrated update system. We propose Fiji as a platform for productive collaboration between computer science and biology research communities.

/pdf/fiji-an-open-source-platform-for-biological-image-analysis-1v529iu3cx.pdf

Fiji: an open-source platform for biological-image analysis

We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.

/pdf/going-deeper-with-convolutions-1yobw2o2ds.pdf

Going deeper with convolutions

Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

Deep Learning

The Scale-Invariant Feature Transform (or SIFT) algorithm is a highly robust method to extract and consequently match distinctive invariant features from images. These features can then be used to reliably match objects in diering images. The algorithm was rst proposed by Lowe [12] and further developed to increase performance resulting in the classic paper [13] that served as foundation for SIFT which has played an important role in robotic and machine vision in the past decade.

We present a fully integrated active vision system for interpreting dynamic scenes We argue that even if the ego-motion of the mobile vision system is known, a single view camera calibration cannot adequately support scene model acquisition and maintenance It is shown that stable camera/grabber chain calibration can be achieved using a multi-view calibration process With such calibration, a predicted view of the scene from any arbitrary view point can successfully be used for object verification and scene model maintenance Experimental results in scene interpretation confirm the benefits of the multi-view calibration approach

On Camera Calibration for Scene Model Acquisition and Maintenance Using an Active Vision System

This paper investigates the plausibility of using approximate models for hypothesis generation in a RANSAC framework to accurately and reliably estimate the fundamental matrix. Two novel fundamental matrix estimators are introduced that sample two correspondences to generate affine-fundamental matrices for RANSAC hypotheses. A new RANSAC framework is presented that uses local optimization to estimate the fundamental matrix from the consensus correspondence sets of verified hypotheses, which are approximate models. The proposed estimators are shown to perform better than other approximate models that have previously been used in the literature for fundamental matrix estimation in a rigorous evaluation. In addition the proposed estimators are over 30 times faster, in terms of models verified, than the 7-point method, and offer comparable accuracy and repeatability on a large subset of the test set.

Approximate models for fast and accurate epipolar geometry estimation

We present a method for exploiting weakly annotated images to improve text extraction pipelines. The approach uses an arbitrary end-to-end text recognition system to obtain text region proposals and their, possibly erroneous, transcriptions. The method includes matching of imprecise transcriptions to weak annotations and an edit distance guided neighbourhood search. It produces nearly error-free, localised instances of scene text, which we treat as “pseudo ground truth” (PGT). The method is applied to two weakly-annotated datasets. Training with the extracted PGT consistently improves the accuracy of a state of the art recognition model, by 3.7% on average, across different benchmark datasets (image domains) and 24.5% on one of the weakly annotated datasets11Acknowledgements. The authors were supported by Czech Technical University student grant SGS20/171/0HK3/3TJ13, the MEYS VVV project CZ.02.1.01/0.010.0J16 019/0000765 Research Center for Informatics, the Spanish Research project TIN2017-89779-P and the CERCA Programme / Generalitat de Catalunya.

Text Recognition - Real World Data and Where to Find Them

We present the evaluation methodology, datasets and results of the BOP Challenge 2022, the fourth in a series of public competitions organized with the goal to capture the status quo in the field of 6D object pose estimation from an RGB/RGB-D image. In 2022, we witnessed another significant improvement in the pose estimation accuracy -- the state of the art, which was 56.9 AR$_C$ in 2019 (Vidal et al.) and 69.8 AR$_C$ in 2020 (CosyPose), moved to new heights of 83.7 AR$_C$ (GDRNPP). Out of 49 pose estimation methods evaluated since 2019, the top 18 are from 2022. Methods based on point pair features, which were introduced in 2010 and achieved competitive results even in 2020, are now clearly outperformed by deep learning methods. The synthetic-to-real domain gap was again significantly reduced, with 82.7 AR$_C$ achieved by GDRNPP trained only on synthetic images from BlenderProc. The fastest variant of GDRNPP reached 80.5 AR$_C$ with an average time per image of 0.23s. Since most of the recent methods for 6D object pose estimation begin by detecting/segmenting objects, we also started evaluating 2D object detection and segmentation performance based on the COCO metrics. Compared to the Mask R-CNN results from CosyPose in 2020, detection improved from 60.3 to 77.3 AP$_C$ and segmentation from 40.5 to 58.7 AP$_C$. The online evaluation system stays open and is available at: \href{http://bop.felk.cvut.cz/}{bop.felk.cvut.cz}.

BOP Challenge 2022 on Detection, Segmentation and Pose Estimation of Specific Rigid Objects

In this paper we propose an optimisation technique to choose a user independent feature subset from the input feature set for a dynamic time-warping (DTW) based text-dependent speaker verification system. The results indicate that with the optimised feature set the verification error rate of the system can be improved.

/pdf/selection-of-speaker-independent-feature-for-a-speaker-2otbah2tf2.pdf

Jiri Matas

Papers

On Camera Calibration for Scene Model Acquisition and Maintenance Using an Active Vision System

Approximate models for fast and accurate epipolar geometry estimation

Text Recognition - Real World Data and Where to Find Them

BOP Challenge 2022 on Detection, Segmentation and Pose Estimation of Specific Rigid Objects

Selection of speaker independent feature for a speaker verification system