Optical flow calculation from feature space analysis through an automatic segmentation process

A sequential dual-energy subtraction technique for image-guided radiation therapy (IGRT) was developed. Here, we report on a computerized method for creating sequential soft-tissue images and the accuracy of tracking targets on the images obtained, in comparison to conventional fluoroscopic images. Two sets of sequential chest images during respiration of a normal subject were obtained with X-rays of different energy separately with a flat-panel detector (FPD). Sequential soft-tissue images were created from the two sets of sequential images consisting of real-time images and reference template images, respectively. The creation of sequential soft-tissue images consisted of three steps: one-to-one image correspondence of the two sequential images, image registration, and image subtraction in each frame. Motion tracking of lung vessels was then performed by the template-matching technique. For evaluation of the accuracy of motion tracking on the sequential soft-tissue images, the results were compared with those on the original sequential images. Sequential soft-tissue images provided more accurate tracking than the original images (P < 0.01). There was no significant error throughout all frames in the soft-tissue images, whereas the rib shadow introduced a tracking error in the original images. The maximum errors were 4.1 +/- 0.3 mm in the sequential soft-tissue images and 28.1 +/- 20.0 mm in the original images. In conclusion, sequential soft-tissue images were helpful for tracking of a target affected by respiratory motion. Dual-energy subtraction has the potential to improve the accuracy of IGRT without implanted markers.

The computation of optical flow has been proposed as a pre-processing step for many high-level vision algorithms. One of the main approaches to the optical flow problem is the gradient-based approach which differentiates the image intensity to compute the optical flow. Often motion vectors computed using various approaches are not reliable. Spatial smoothing of the image sequence is advisable in order to improve velocity estimates in the presence of noise. That is, the application of some kind of linear operation to the images in the sequence before solving for the flow. The pre-processing typically takes the form of some type of spatial Gaussian smoothing or scale specific band-pass filtering of the input images. The main objectives of such filtering have been to lessen the effects of noise, to isolate image structure of interest and to attenuate temporal aliasing and quantization effects in the input images.This paper investigates the effect of presmoothing on this computation of optical flow. The well known method of Horn and Schunck as well as our own finite element method are implemented and tested for improvements due to presmoothing. Discussions are provided on the effects of presmoothing for a variety of image sequences. In our experiments, smoothing is carried out on a selection of well known sequences in both time and space. Improvements are shown using presmoothing.KeywordsFinite Volume MethodsInverse Finite Element MethodsMotion TrackingOptical FlowSpatial SmoothingTemporal Smoothing

To estimate the motion and deformation of nonrigid objects accurately from image sequences, this paper proposes a method for nonrigid motion tracking based on smoothness constraints, which have an effect on noise reduction in optical flow computation by a gradient‐based method. The motion of nonrigid objects generally is assumed to be smooth according to such physical properties as inertia and elasticity. Therefore, such smoothness constraints are defined in space (in frame) and time (between frames) as an active net model in formulating an energy functional and Lagrange equation, and the optical flow field derived from image sequences by shape preservation and natural deformation is modified. In addition, applying continuous Kalman filtering theory for long sequences of image frames, it is possible to estimate the temporal continuous deformation of elastic objects. The nonrigid motion tracking is demonstrated by experiments involving the modification of the shape distortion yielded by noise and the reconstruction of the real motion and deformation.

Robust Regression for the Detection of Independent 3D Motion by a Binocular Observer

The problem of volume averaging in quantitating CSF, gray-matter, and white-matter fractions in the brain is solved using a three-compartment model and a simple graphical analysis of a multispectral MR feature space. Compartmentalization is achieved without the ambiguities of thresholding techniques or the need to assume that the underlying pixel probability distributions have a particular form. A 2D feature space is formed by double SE (proton density- and T2-weighted) MR data with image nonuniformity removed by a novel technique in which the brain itself serves as a uniformity reference. Compartments other than the basic three were rejected by the tailoring of limits in feature space. Phantom scans substantiate this approach, and the importance of the careful selection and standardization of pure tissue reference signals is demonstrated. Compartmental profiles from standardized subvolumes of three normal brains, based on a 3D (Talairach) coordinate system, demonstrate slice-by-slice detail; longitudinal studies confirm reproducibility. Compartmentalization may be described graphically and algebraically, complementing data displays in feature space and images of compartmentalized brain scans. These studies anticipate the application of our compartmentalization technique to patients with neurological disorders.

While some image textures can be changed with scale, others cannot. We focus on a multi-scale features of determing the sensitivity of the texture intensity to change. This paper presents a new method of texture structure classification and depth estimation using multi-scale features extracted from a higher order of the local autocorrelation functions. Multi-scale features consist of the meansand variances of distributions, which are extracted from theautocorrelation feature vectors according to multi-level scale. In order to reduce dimensional feature vectors, we employ the Principal Component Analysis (PCA) in the autocorrelation feature space. Each training image texture makes its own multi-scale model in a reduced PCA feature space, and the test of the texture image is projected in the homogeneous PCA space of the training data. The experimental results show that the proposed multi-scale feature can be utilized notonly for texture classification, but also depth estimation in two dimensional images with texture gradients.

A novel approach for the computation of flow based on an L' type minimization is presented. It is shown that the approach has inherent advantages since it does not smooth the flow-velocity across the edges andhence preserves edge information. A numerical approach based on computation of evolving curves is proposedfor computing the flow field. Computations carried out on a number of real image sequences in order toillustrate the theory as well as the numerical approach.Keywords: curve evolution; flow; motion; scale spaces; gradient descent 1 INTRODUCTION Optical flow field is defined as the velocity vector field of apparent motion of brightness patterns in a sequenceof images. Relative motion between a camera and objects being imaged (or relative motion among the objectsbeing imaged) are very common cases which give rise to flow.One common simplifying assumption is the constancy of intensity at any point in the image and gives rise tothe optical flow constraint (OFC). It can be expressed as the following linear equation in the unknown variablestt

Many problems of image processing and image sequence analysis involve both great computational complexity and the accommodation of noise and uncertainty through the indirect observation of quantities of interest. In this chapter we describe several aspects of an estimation theoretic approach to such problems. The vehicle for our development is the estimation of the apparent velocity field of a sequence of images. This apparent velocity field, known as the optical flow, appears as an important quantity in both the qualitative and quantitative analysis of image sequences. For example, knowledge of the optical flow is used in the detection of object boundaries and the segmentation of visual scenes [1, 2], the derivation of 3-D motion and structure [3, 4] and the compression of image sequences for efficient transmission [5, 6].

We present in this paper a motion computation and interpretation framework for oceanographic satellite images. This framework is based on the use of a non quadratic regularization technique in optical flow computation that preserves flow discontinuities. We also show that using an appropriate tessellation of the image according to an estimate of the motion field can improve optical flow accuracy and yields more reliable flows. This method defines a non uniform multiresolution scheme that refines mesh resolution only in the neighborhood of moving structures. The second part of the paper deals with the interpretation of the obtained displacement field. We use a phase portrait model with a new formulation of the approximation of an oriented flow field. This allows us to consider arbitrary polynomial phase portrait models for characterizing salient flow features. This new framework is used for processing oceanographic and atmospheric image sequences and presents an alternative to the very complex physical modelling techniques.

This paper describes the tracking of an object in a sequence of video-recorded images by a template matching approach based on a genetic algorithm learning technique to generate adaptive templates. The system is intended for real images. Contrary to a controlled environment, where the template may be generated from a noise free image and all successive frames do not show great changes, we hypothesise a set of images acquired at possible different environmental conditions. The varying environmental conditions greatly influence the matching, but they cannot be coded/used because they are not known a priori. In addition, 2D projections of 3D objects may vary during the sequence. Despite these difficulties, the need for robust systems that can locate objects in frame sequences is rapidly increasing due to the explosion in the amount of visual data in the communications systems.

Objectives: Cardiac Image Segmentation field have a lot of difficulties when we take the big changes in sequences of images that are of different types. In image sequences, Segmentation of objects which are not fixed is more challenging. To handle such situations, use of Improved Genetic Algorithm for Image Segmentation of Cardiac images is presented.Methods: We propose an algorithm based on Improved Genetic Algorithm, for segmentation of medical image sequences, which uses K-mean clustering. For clustering in the feature space, we used feature vector of two- dimension. Findings: In our paper, for Cardiac Image Segmentation, we are presenting a state of art review of various methods and techniques. Various sequences of Cardiac image have been Registered, and then for segmentation process, single image is used. Novelty/Improvement: Satisfactory results have been given by the experiments done on Cardiac images.

Prompt learning automates the manual crafting of prompts for adapting vision-and-language models, to downstream tasks, particularly in few-shot scenarios. This paper addresses two key challenges in prompt learning: limited performance in one-shot settings and inefficient dataset construction from unlabeled data. To tackle these challenges, we visualize and compare CLIP's feature spaces after prompt learning under one-shot and 16-shot conditions, identifying necessary characteristics of feature spaces that yield better prompts. We propose two novel loss functions—Inclusive Loss and Exclusive Loss—that enhance accuracy in one-shot scenarios by encouraging the feature space to resemble those trained with sufficient data. Additionally, we investigate the distribution of image features within CLIP's feature space and introduce a sampling method called Cluster-Centroid Sampling (CCS). CCS constructs a more category-balanced dataset by selecting samples closest to cluster centroids. To validate our approaches, we conducted extensive experiments. First, we demonstrate the effectiveness of our proposed loss functions across multiple datasets, showing accuracy improvements in one-shot conditions. Second, we evaluate CCS using an unlabeled data pool, confirming its superiority over existing sampling methods in downstream task accuracy due to the construction of more balanced dataset.

In this paper, a generalized statistical tool is introduced to estimate key frames in a video sequence. The tool works based on the inter-relationship between different features of image frames in a video. The image feature vectors are plotted in feature space as points and a randomness measure is determined from the distribution of these points. The randomness measure of the feature vectors is defined with respect to simulated random point patterns and expressed as a probability value of a frame being a key frame. Since, depending on the video content more than one inter-relationship of features can be used to determine a single key frame, different probability values are derived to support a frame as a key frame. To integrate these probability values a combiner model is designed to uniquely decide the status of a key frame. The combiner model is based on the Dempster-Shafer theory of evidence. To demonstrate the idea, randomness measures, and consequently the probabilities of a frame to be a key frame, are obtained separately from spatial domain and frequency domain features. The combined probability value enhances the confidence in selecting a frame as a key frame. The result is tested on a number of standard video sequences and it outperforms the related approach

Road visual navigation relies on accurate road models. This study was aimed at proposing an improved scale-invariant feature transform (SIFT) algorithm for recovering depth information from farmland road images, which would provide a reliable path for visual navigation. The mean image of pixel value in five channels (R, G, B, S and V) were treated as the inspected image and the feature points of the inspected image were extracted by the Canny algorithm, for achieving precise location of the feature points and ensuring the uniformity and density of the feature points. The mean value of the pixels in 5×5 neighborhood around the feature point at an interval of 45o in eight directions was then treated as the feature vector, and the differences of the feature vectors were calculated for preliminary matching of the left and right image feature points. In order to achieve the depth information of farmland road images, the energy method of feature points was used for eliminating the mismatched points. Experiments with a binocular stereo vision system were conducted and the results showed that the matching accuracy and time consuming for depth recovery when using the improved SIFT algorithm were 96.48% and 5.6 s, respectively, with the accuracy for depth recovery of –7.17%-2.97% in a certain sight distance. The mean uniformity, time consuming and matching accuracy for all the 60 images under various climates and road conditions were 50%-70%, 5.0-6.5 s, and higher than 88%, respectively, indicating that performance for achieving the feature points (e.g., uniformity, matching accuracy, and algorithm real-time) of the improved SIFT algorithm were superior to that of conventional SIFT algorithm. This study provides an important reference for navigation technology of agricultural equipment based on machine vision. Keywords: scale-invariant feature transform (sift), feature matching, canny operator, energy method of feature point, farmland road, depth recovery, visual navigation DOI: 10.25165/j.ijabe.20191204.4821 Citation: Yao L J, Hu D, Yang Z D, Li H B, Qian M B. Depth recovery for unstructured farmland road image using an improved SIFT algorithm. Int J Agric & Biol Eng, 2019; 12(4): 141–147.

In this paper, we propose a robust feature extraction method for texture image retrieval, and verify the effectiveness. In this method, the original image is transformed to log-polar autocorrelation image. The log-polar image is decomposed by discreet wavelet transform to obtain the approximation images. We extract the edge component from the approximation image by sobel filter processing, and we use higher order local autocorrelation as feature vector. Using this method to texture image, we obtain the robust feature for geometrical (shift, rotation, scale) and illumination distortions.In order to show the effectiveness of this method, we estimated the similarity between images by using the feature vector. According to the result of computer simulation, we verified the higher retrieval rate to geometrical and illumination distorted images than the conventional approaches.