Automatic Object Recognition Research Articles

Smart scanning and near real-time 3D surface modeling of dynamic construction equipment from a point cloud

Abstract This paper introduces a framework of automatic object recognition and rapid surface modeling to aid the heavy equipment operation in rapidly perceiving 3D working environment at dynamic construction sites. A custom-designed data acquisition system was employed in this study to rapidly recognize the selected target objects in a 3D space by dynamically separating target object’s point cloud data from a background scene for a quick computing process. A smart scanning method was also applied to only update the target object’s point cloud data while keeping the previously scanned static work environments. Then the target’s point cloud data were rapidly converted into a 3D surface model using the concave hull surface modeling algorithm after a process of data filtering and downsizing to increase the model accuracy and data processing speed. The performance of the proposed framework was tested with two different heavy equipment types at a steel frame building construction site. The generated surface model and the point cloud of static surroundings were wirelessly presented to a remote operator. The field test results show that the proposed rapid target surface modeling method would significantly improve productivity and safety in heavy construction equipment operations by distinguishing a dynamic target object from a surrounding static environment in 3D views in near real time.

CONCERNING A FLOWERY TABLECLOTH AND THE COMPUTER-AIDED ANALYSIS OF A 19TH-CENTURY PHOTOGRAPHIC IMAGE / APIE GĖLĖTĄ STALTIESĘ IR XIX AMŽIAUS FOTOGRAFIJOS KOMPIUTERINĘ VAIZDO ANALIZĘ

The paper introduces some peculiarities of the analysis of the photographic image which emerged in the process of the investigation and preparation for publication of the album of prelate Povilas Januševičius’ the end of 19th – beginning of 20th century. Miscellaneous analysis of photograph image is presented. It also introduces how problems of photograph dating could be solved by combining in sights of investigator as well as application of information technology. Among other things a technological study is being presented in which similarity of flowered tablecloth was analysed in different photographs. Up-to-date programs for processing and analyzing images open up completely new possibilities leading to automatic recognition and identification of objects, symbols and faces. Santrauka Straipsnyje supažindinama su kai kuriomis senosios fotografijos datavimo problemomis, kurios iškilo rengiant publikavimui ir analizuojant bei komentuojant prelato Povilo Januševičiaus XIX amžiaus pabaigos – XX amžiaus pradžios fotografijų albumą. Pateikiama fotografijų vaizdo, fotografijų fotokortelių analizė. Supažindinama, kaip būtų galima spręsti fotografijų datavimo problemas, derinant tyrėjo įžvalgas ir pasitelkiant informacines technologijas. Taip pat pateikiamas technologinio pobūdžio tyrimas, kurio metu buvo tikrinamas gėlėtos staltiesės panašumas skirtingose nuotraukose. Šiuolaikinės vaizdo apdorojimo ir analizės programos suteikia kokybiškai naujas galimybes, kada tampa įmanomas automatizuotas objektų, simbolių ar veidų atpažinimas ir identifikavimas.

Projection-Recognition-Projection Method for Automatic Object Recognition and Registration for Dynamic Heavy Equipment Operations

AbstractIt is challenging to recognize dynamic three-dimensional (3D) objects in a scattered construction work environment because it is difficult to process large amounts of incomplete and complex site data from optical sensors in real time or near-real time. This paper proposes a model-based automatic dynamic object recognition and registration method, projection-recognition-projection (PRP), to help heavy equipment operators rapidly perceive the 3D working environment at construction sites. In this study, machine vision and laser scanning technologies were used to rapidly recognize and register dynamic target objects in 3D space. The proposed PRP method extracts a target object’s point cloud data from the background scene to significantly reduce scan data size and modeling time. The target objects’ point clouds are then processed to rapidly recognize and register 3D target models from a model database to the corresponding point clouds. Several field tests at construction equipment operation sites show ...

基于压缩感知的多角度合成孔径雷达成像

Multi-aspect synthetic aperture radar (SAR) imaging is an important technique for synthesizing multi-aspect SAR data or information. Achieving multi-aspect SAR imagery is invaluable for resolution improvement, radar object visualization, classification and automatic object recognition (ATR). However, achieving multi-aspect SAR imaging is challenging because of the diversity of space sampling positions and the transmission of signal waveforms. In this study, a new method, based on the model of a multi-aspect SAR data collection, is proposed to achieve multi-aspect SAR imaging using compressive sensing and sparse reconstruction theory. First, the factors which dominate the performance of the measurement matrix were studied. It was found that the distribution of space sampling and the carrier frequency of the transmission signal were the key factors dominating the mutual coherence (MC) of the measurement matrix. The object sampling space was also a key factor in determining the robustness and resolution of multi-aspect SAR imaging. Second, the measurement matrix for the multi-aspect SAR was constructed, depending on previous analysis, by careful selection of the parameters and sampling of the object. Third, the stage-wise orthogonal matching pursuit (StOMP) algorithm was applied to achieve multi-aspect SAR imaging. This algorithm was effective in solving high-dimensional ill-posed equations. Extensive experiments validated the feasibility and stability of the proposed algorithm.

IMPLICIT SHAPE MODELS FOR OBJECT DETECTION IN 3D POINT CLOUDS

Abstract. We present a method for automatic object localization and recognition in 3D point clouds representing outdoor urban scenes. The method is based on the implicit shape models (ISM) framework, which recognizes objects by voting for their center locations. It requires only few training examples per class, which is an important property for practical use. We also introduce and evaluate an improved version of the spin image descriptor, more robust to point density variation and uncertainty in normal direction estimation. Our experiments reveal a significant impact of these modifications on the recognition performance. We compare our results against the state-of-the-art method and get significant improvement in both precision and recall on the Ohio dataset, consisting of combined aerial and terrestrial LiDAR scans of 150,000 m2 of urban area in total.

Real-time concealed-object detection and recognition with passive millimeter wave imaging

Millimeter wave (MMW) imaging is finding rapid adoption in security applications such as concealed object detection under clothing. A passive MMW imaging system can operate as a stand-off type sensor that scans people in both indoors and outdoors. However, the imaging system often suffers from the diffraction limit and the low signal level. Therefore, suitable intelligent image processing algorithms would be required for automatic detection and recognition of the concealed objects. This paper proposes real-time outdoor concealed-object detection and recognition with a radiometric imaging system. The concealed object region is extracted by the multi-level segmentation. A novel approach is proposed to measure similarity between two binary images. Principal component analysis (PCA) regularizes the shape in terms of translation and rotation. A geometric-based feature vector is composed of shape descriptors, which can achieve scale and orientation-invariant and distortion-tolerant property. Class is decided by minimum Euclidean distance between normalized feature vectors. Experiments confirm that the proposed methods provide fast and reliable recognition of the concealed object carried by a moving human subject.

Robot Vision Application for Bearings Identification and Sorting

An automated object recognition application type, implemented on a robotic platform, is described. It is based on an image processing algorithm that enables: the detection of objects like bearings from a pallet conveyor, the identification of bearings type and the calculus of position and orientation, in order to be manipulated by a SCARA robot. The identification algorithm developed in Matlab software consists in HSV image segmentation and a matching technique based on comparison with previous given set of bearing prototypes. The methods used for camera and robot calibration are also described.

Automatic radar target recognition of objects falling on railway tracks

This paper presents an automatic radar target recognition procedure based on complex resonances using the signals provided by ultra-wideband radar. This procedure is dedicated to detection and identification of objects lying on railway tracks. For an efficient complex resonance extraction, a comparison between several pole extraction methods is illustrated. Therefore, preprocessing methods are presented aiming to remove most of the erroneous poles interfering with the discrimination scheme. Once physical poles are determined, a specific discrimination technique is introduced based on the Euclidean distances. Both simulation and experimental results are depicted showing an efficient discrimination of different targets including guided transport passengers.

Fuzzy Associative Databases for Visual Recognition of 2D and 3D Objects

It is desirable for automated object recognition using computer vision systems to emulate the human capacity for recognition of shapes invariant to various transformations. We present an algorithm, based on a Fuzzy Associative Database approach, which uses appropriately invariant metrics and a neuro-fuzzy inference method to accurately classify both two- and three-dimensional objects (using different metrics for each). The system is trained using a small number of images of each object class under varying degrees of the transformations, and as we show experimentally, is then able to identify objects under other non-explicitly-trained degrees of the transformations.

Automatic extraction of parallel edges based on eigenvalue analysis and collateral expansion

In the research field of remote sensing (RS), automatic extraction of parallel edges (AEPE) usually serves as the kernel when implementing automatic recognition of strip-like objects, such as rivers, highways, canyons and canals. The traditional algorithms proposed for edge detection commonly assume the mathematical singularity of boundaries as their theoretical basis and are also required to be all-prevalent, but the associated results cannot deal with the desired collection of parallel-only edges in most specific applications of RS data. To solve this problem, this article advances a novel algorithm for AEPE, which proceeds with the output edges from the existing edge-extraction methods as targets. The new algorithm comprises the procedure of eigenvalue analysis with improvements for extracting line segments, the procedure of collateral expansion for removing the non-parallel line segments recursively, and finally the procedure of segment connection. Finally, experiments based on both RS panchromatic images and light detection and ranging (LiDAR)-rastered images validate the new AEPE algorithm, with an efficacy greater than 70% and an accuracy better than 90%.

Super-resolution Imageing via Uncertainty Models

Super-resolution is the process of converting many similar low-resolution images or video sequences. Super-resolution can be used for superior automatic target or object detection. There is always an uncertainty related to this method. An uncertainty is rarely considered during analysis. In many cases, uncertainties are the noisy signals and their processing leads to invalid results. This paper reviews certain super-resolution methodologies and presents two uncertainty model based super-resolution techniques. The presented models consider the uncertainty factor and establish an absolute probability distribution. The first model is based on analytical computation while the second is based on a statistical algorithm. These algorithms are presented as separate methods for image analysis and enhance performance compared with that of the existing automatic object recognition super-resolution methods.

A 3D shape segmentation approach for robot grasping by parts

Neuro-psychological findings have shown that human perception of objects is based on part decomposition. Most objects are made of multiple parts which are likely to be the entities actually involved in grasp affordances. Therefore, automatic object recognition and robot grasping should take advantage from 3D shape segmentation. This paper presents an approach toward planning robot grasps across similar objects by part correspondence. The novelty of the method lies in the topological decomposition of objects that enables high-level semantic grasp planning. In particular, given a 3D model of an object, the representation is initially segmented by computing its Reeb graph. Then, automatic object recognition and part annotation are performed by applying a shape retrieval algorithm. After the recognition phase, queries are accepted for planning grasps on individual parts of the object. Finally, a robot grasp planner is invoked for finding stable grasps on the selected part of the object. Grasps are evaluated according to a widely used quality measure. Experiments performed in a simulated environment on a reasonably large dataset show the potential of topological segmentation to highlight candidate parts suitable for grasping.

Learning with few examples for binary and multiclass classification using regularization of randomized trees

The human visual system is often able to learn to recognize difficult object categories from only a single view, whereas automatic object recognition with few training examples is still a challenging task. This is mainly due to the human ability to transfer knowledge from related classes. Therefore, an extension to Randomized Decision Trees is introduced for learning with very few examples by exploiting interclass relationships. The approach consists of a maximum a posteriori estimation of classifier parameters using a prior distribution learned from similar object categories. Experiments on binary and multiclass classification tasks show significant performance gains

Non-parametric Bayesian super-resolution

Super-resolution of signals and images can improve the automatic detection and recognition of objects of interest. However, the uncertainty associated with this process is not often taken into consideration. This is important because the processing of noisy signals can result in spurious estimates of the scene content. This study reviews a variety of super-resolution techniques and presents two non-parametric Bayesian super-resolution algorithms that not only take uncertainty into account, but also retain knowledge about the output uncertainty in the form of a full probability distribution. One of the two Bayesian techniques is based on an analytical calculation re-interpreted as super-resolution, and the other is a novel numerical algorithm. Although the algorithms are presented as stand-alone techniques for image analysis, such Bayesian super-resolution algorithms can increase automatic target recognition performance over standard super-resolution.

NLOOK: a computational attention model for robot vision

Abstract The computational models of visual attention, originally proposed as cognitive models of human attention, nowadays are being used as front-ends to some robotic vision systems, like automatic object recognition and landmark detection. However, these kinds of applications have different requirements from those originally proposed. More specifically, a robotic vision system must be relatively insensitive to 2D similarity transforms of the image, as in-plane translations, rotations, reflections and scales, and it should also select fixation points in scale as well as position. In this paper a new visual attention model, called NLOOK, is proposed. This model is validated through several experiments, which show that it is less sensitive to 2D similarity transforms than other two well known and publicly available visual attention models: NVT and SAFE. Besides, NLOOK can select more accurate fixations than other attention models, and it can select the scales of fixations, too. Thus, the proposed model is a good tool to be used in robot vision systems.

NLOOK: a computational attention model for robot vision

The computational models of visual attention, originally proposed as cognitive models of human attention, nowadays are being used as front-ends to some robotic vision systems, like automatic object recognition and landmark detection. However, these kinds of applications have different requirements from those originally proposed. More specifically, a robotic vision system must be relatively insensitive to 2D similarity transforms of the image, as in-plane translations, rotations, reflections and scales, and it should also select fixation points in scale as well as position. In this paper a new visual attention model, called NLOOK, is proposed. This model is validated through several experiments, which show that it is less sensitive to 2D similarity transforms than other two well known and publicly available visual attention models: NVT and SAFE. Besides, NLOOK can select more accurate fixations than other attention models, and it can select the scales of fixations, too. Thus, the proposed model is a good tool to be used in robot vision systems.

DetecTiff©: A Novel Image Analysis Routine for High-Content Screening Microscopy

In this article, the authors describe the image analysis software DetecTiff, which allows fully automated object recognition and quantification from digital images. The core module of the LabView-based routine is an algorithm for structure recognition that employs intensity thresholding and size-dependent particle filtering from microscopic images in an iterative manner. Detected structures are converted into templates, which are used for quantitative image analysis. DetecTiff enables processing of multiple detection channels and provides functions for template organization and fast interpretation of acquired data. The authors demonstrate the applicability of DetecTiff for automated analysis of cellular uptake of fluorescence-labeled low-density lipoproteins as well as diverse other image data sets from a variety of biomedical applications. Moreover, the performance of DetecTiff is compared with preexisting image analysis tools. The results show that DetecTiff can be applied with high consistency for automated quantitative analysis of image data (e.g., from large-scale functional RNAi screening projects).

Adaptive supervision of moving objects for mobile robotics applications

One of the main tasks of mobile robotics is vision. Lighting independence, adaptivity and automated learning are still the main issues when it comes to applications. In this article, we present an image understanding system and its methods targeting automatic, lighting-independent and reliable color-based object recognition under real time conditions. Its application test bed is global vision robot soccer (i.e. FIRA MiroSot und RoboCup Small Size leagues) but it has many other applications in color-based supervision of moving objects. Under typical conditions, it learns the objects of recognition automatically, has zero setup time and tolerates environmental changes during run-time.

3차원 측정점으로부터의 객체 자동인식

측정점으로부터의 3차원 객체 자동인식은 컴퓨터비전, 지능형로봇 등의 분야에서 주요 연구주제이다. 본 논문에서 저자는 측정오차가 포함되어 있으며 정렬되지 않은 대용량 3차원 측정점으로부터 객체를 자동적으로 추출하며 그 형상계수를 추정하는 소프트웨어 기술에 대한 소개를 하고자 한다. 해당 소프트웨어는 기능적으로 상호 연결된 형상모델 제시, 측정점 분할, 형상모델 맞춤의 세 부분으로 이루어졌으며 최단거리 최소제곱법(ODF)이 핵심요소이다. ODF는 형상모델과 측정점 사이의 최단거리의 제곱합을 최소화하는 형상모델 계수를 추정한다. 무작위로 선정된 부분 측정점에 대한 임시 형상모델로서 이차 곡면이 ODF에 의하여 구하여지면 우리는 이로부터 3차원 객체를 자동적으로 추출하는 과정인 최종 형상모델 제시, 측정점 분할, 형상모델 맞춤에 필요한 초기값을 제공할 수 있다. 소개된 소프트웨어 기술을 실제 3차원 측정점에 적용함으로써 그의 성능을 확인하고자 한다. Automatic object recognition in 3D measuring data is of great interest in many application fields e.g. computer vision, reverse engineering and digital factory. In this paper we present a software tool for a fully automatic object detection and parameter estimation in unordered and noisy point clouds with a large number of data points. The software consists of three interactive modules each for model selection, point segmentation and model fitting, in which the orthogonal distance fitting (ODF) plays an important role. The ODF algorithms estimate model parameters by minimizing the square sum of the shortest distances between model feature and measurement points. The local quadric surface fitted through ODF to a randomly touched small initial patch of the point cloud provides the necessary initial information for the overall procedures of model selection, point segmentation and model fitting. The performance of the presented software tool will be demonstrated by applying to point clouds.

Approaches for Automated Object Recognition and Extraction from Images � a Study

Digital Image Interpretation is one of the most challenging and important tasks in many scientific and engineering applications. The two vital subtasks in image interpretation are recognition and extraction of object(s) of interest (OOI) from an image. When such tasks are manually performed, it calls for human experts, making them more time consuming, less cost effective and highly constrained. These negative factors led to the development of a computer system which performed an automatic analysis of visual information in order to bring in consistency, efficiency and accuracy in image analysis. This paper focuses on the survey of various existing automated approaches for recognition and extraction of OOI from an image in various scientific and engineering applications. In this work a categorization of these approaches is made based on the four principle factors (Input, Object, Feature, Attention) with which each approach is driven. Most of the approaches discussed in this paper are proved to work efficiently in real environments.