Optimal colour‐based mean shift algorithm for tracking objects

The mean shift algorithm has achieved considerable success in object tracking due to its simplicity and robustness. It finds local minima of a similarity measure between the color histograms or kernel density estimates of the model and target image. The most typically used similarity measures are the Bhattacharyya coefficient or the Kullback-Leibler divergence. In practice, these approaches face three difficulties. First, the spatial information of the target is lost when the color histogram is employed, which precludes the application of more elaborate motion models. Second, the classical similarity measures are not very discriminative. Third, the sample-based classical similarity measures require a calculation that is quadratic in the number of samples, making real-time performance difficult. To deal with these difficulties we propose a new, simple-to-compute and more discriminative similarity measure in spatial-feature spaces. The new similarity measure allows the mean shift algorithm to track more general motion models in an integrated way. To reduce the complexity of the computation to linear order we employ the recently proposed improved fast Gauss transform. This leads to a very efficient and robust nonparametric spatial-feature tracking algorithm. The algorithm is tested on several image sequences and shown to achieve robust and reliable frame-rate tracking.

Color histogram is one of the most widely used visual feature representations the JPEG/MPEG compressed domains, the DC coefficients are used commonly to form the color histograms without fully decompressing the image or the video bit stream. In this paper, we address the issues arising from the adaptation of DC based color histograms to the arbitrarily shaped MPEG-4 video objects. More specifically, we discuss the color space selection, quantization, and histogram computation with the consideration of the specific characteristics of the MPEG-4 video objects. We also propose a method for reducing the chroma keying artifacts that may occur at the boundaries of the objects. The experimental results show that great retrieval performance improvements are achieved by employing the proposed method in the presence of such artifacts.KeywordsColor SpaceColor HistogramRetrieval PerformanceRetrieval ResultBoundary BlockThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

An algebraic compiler allows incremental development of the source program and builds its target image by composing the target images of the program components. In this paper we describe the general structure of an algebraic compiler focusing on compositional code generation. We show that the mathematical model for register management by an algebraic compiler is a graph coloring problem in which an optimally colored graph is obtained by composing optimally colored subgraphs. More precisely, we define the clique-composition of graphs \(G_1\) and \(G_2\) as the graph obtained by joining all the vertices in a clique in \(G_1\) with all the vertices in a clique in \(G_2\) and show that optimal register management by an algebraic compiler is achieved by performing clique-composition operations. Thus, an algebraic compiler provides automatically adequate clique separation of the global register management graph. We present a linear-time algorithm that takes as input optimally colored graphs \(G_1\) and \(G_2\) and constructs an optimal coloring of any clique-composition of \(G_1\) and \(G_2\). Motivated by the operation of clique-composition, we define the class of clique-composable graphs as those graphs that can be iteratively built from single vertices using the clique-composition operation. We show that the class of clique-composable graphs coincides with the well-known class of chordal graphs.

Using color histograms in automatic emotion recognition systems faces different issues. One of the important challenges is to determine the appropriate number of bins in the color histogram to achieve the highest recognition performance possible with minimal computations. This research focuses on emotion recognition induced by visual contents of images, or REVC for short, using ARTphoto dataset. Twenty-two different classifiers are used with color histograms in both RGB (red, green, blue) and HSV (hue, saturation, value) color spaces across different numbers of bins, and overall performance of each bin size is compared with that of other bin sizes. The research findings show that the performance of REVC system does not improve in terms of overall sensitivity rate, when the number of bins in color histogram is increased. Moreover, this paper identifies the advantage of using HSV color space over RGB in using color histogram for REVC systems. Furthermore, findings recognize the optimum number of bins in both RGB and HSV color spaces, and ANOVA (analysis of variance) is used to analyze experimental data, which identifies the optimum color histogram bin size used for HSV color space is significantly better than that used for RGB color space in REVC systems.

Image retrieval using color histograms generated by Gauss mixture vector quantization

Three-dimensional (3-D) imaging and the 3-D micromotion feature extraction technique of space targets provide significant information for target classification and recognition. The idea of multiantenna interferometric processing from the interferometric inverse synthetic aperture radar (InISAR) is introduced into the 3-D imaging of micromotional space targets. After the modeling analysis of the micromotion characteristic induced by the target on the range–slow-time plane, a 3-D interferometric imaging method for space precession targets in wideband radar is proposed. The real 3-D images of the target in both the normal mode and the squint mode are obtained by the proposed method. Meanwhile, some 3-D precession features and structure parameters of the target are extracted accurately. Finally, simulation results validate the effectiveness and robustness of the proposed method. Compared with the existed approaches, this study can achieve real 3-D imaging and extract precession features and structure parameters for space precession target only by a monostatic radar with multi-antenna.

Motor oil classification is important for quality control and the identification of oil adulteration. In this work, we propose a simple, rapid, inexpensive and nondestructive approach based on image analysis and pattern recognition techniques for the classification of nine different types of motor oils according to their corresponding color histograms. For this, we applied color histogram in different color spaces such as red green blue (RGB), grayscale, and hue saturation intensity (HSI) in order to extract features that can help with the classification procedure. These color histograms and their combinations were used as input for model development and then were statistically evaluated by using linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and support vector machine (SVM) techniques. Here, two common solutions for solving a multiclass classification problem were applied: (1) transformation to binary classification problem using a one-against-all (OAA) approach and (2) extension from binary classifiers to a single globally optimized multilabel classification model. In the OAA strategy, LDA, QDA, and SVM reached up to 97% in terms of accuracy, sensitivity, and specificity for both the training and test sets. In extension from binary case, despite good performances by the SVM classification model, QDA and LDA provided better results up to 92% for RGB-grayscale-HSI color histograms and up to 93% for the HSI color map, respectively. In order to reduce the numbers of independent variables for modeling, a principle component analysis algorithm was used. Our results suggest that the proposed method is promising for the identification and classification of different types of motor oils.

Objectives: Nowadays, the capacity of digital image information is rapidly surging. The computational complexity of retrieving images from database also increases. Methods/Statistical Analysis: Texture and colour are the most important components of visual information which can be used effectively to reduce the complexity. This paper presents Content- Based Image Retrieval System (CBIR) based on texture and colour similarity. The RGB colour space and the colour histogram are used as the colour feature of each image. The texture of each image is obtained by applying gray level co-occurrence matrix. Findings: Based on the similarity between image features CBIR methods retrieve images accurately from the image database. But the traditional system will work well only for the data set which has more dissimilarity. In this study, based on combining the Gaussian Mixture Model (GMM) with k-means clustering algorithm, a new hybrid algorithm for clustering is proposed. A one to one matching scheme is used to compare the query and target image on the basis of all the features extracted. This hybrid Gaussian mixture model will provide more accurate retrieval in the case of the dissimilarity between the image data set is very low. The proposed system is capable of working fewer dissimilarity data set as well more dissimilarity data. Applications/Improvements: The proposed hybrid retrieval method provide more accurate retrieval with the precision measures of 98% and also more robustness with retrieval of 95%.

In this paper, we propose a new region-based image matching method to find the user defined regions in other images. We use color histogram and SAR (simultaneous autoregressive) model parameters as matching features. We characterize the spatial structure of image region with its block features, and we match the image region in target images with spatial constraints. SAR model was usually used to characterize the spatial interactions among neighboring pixels. But the spectrum of the transition matrix G in the SAR model is not well distributed. Therefore in this paper, we use a regularized SAR model to characterize the spatial interactions among neighboring image blocks, which is based on the solution of a penalized LSE (Least Squares Estimation) for computing SAR model parameters. The experimental results show that our method is effective.

A natural color mapping method has been previously proposed that matches the statistical properties (mean and standard deviation) of night-vision (NV) imagery to those of a daylight color image (manually selected as the "target" color distribution). Thus the rendered NV image appears to resemble the target image in terms of colors. However, in this prior method the colored NV image may appear unnatural if the target image's "global" color statistics are too different from that of the night vision scene (e.g., it would appear to have too much green if much more foliage was contained in the target image). Consequently, a new "local coloring" method is presented in the current paper, and functions to render the NV image segment-by-segment by using a histogram matching technique. Specifically, a false-color image (source image) is formed by assigning multi-band NV images to three RGB (red, green and blue) channels. A nonlinear diffusion filter is then applied to the false-colored image to reduce the number of colors. The final grayscale image segments are obtained by using clustering and merging techniques. The statistical matching procedure is merged with the histogram matching procedure to assure that the source image more closely resembles the target image with respect to color. Instead of using a single target color image, the mean, standard deviation and histogram distribution of a set of natural scene images are used as the target color properties for each color scheme. Corresponding to the source region segments, the target color schemes are grouped by their scene contents (or colors) such as green plants, roads, ground/earth. In our experiments, five pairs of night-vision images were initially analyzed, and the images that were colored (segment-by-segment) by the proposed "local coloring" method are shown to be much more natural, realistic, and colorful when compared with those produced by the "global-coloring" method.

Background subtraction is a very popular approach for vehicle detection in traffic surveillance systems. A conventional color histogram (CCH) considers neither the color similarity across different bins nor the color dissimilarity in the same bin. Therefore, it is sensitive to noisy interference such as illumination changes and quantization errors. Furthermore, CCHs large dimension or histogram bins requires large computation on histogram comparison. However, structured motion patterns of the background (e.g., Vehicular traffic videos, waving leaves, spouting fountain, rippling water, etc.), which are distinctive from variations due to noise, are hardly tolerated in this assumption. To address these concerns, we introduce a background subtraction algorithm for temporally dynamic texture scenes. Specifically, we propose to adopt a clustering-based feature, called fuzzy color histogram (FCH), which has an ability of greatly attenuating color variations generated by background motions while still highlighting moving objects. Experimental results demonstrate that the proposed method is effective for background subtraction in dynamic texture scenes using LFCH features with adaptive updating procedure compared to several competitive methods proposed in the literature.

The video retrieval system refers to the task of retrieving the most relevant video collection, given a user query. By applying some feature extraction models the contents of the video can be extracted. With the exponential increase in video data in online and offline databases as well as a huge implementation of multiple applications in health, military, social media, and art, the Content-Based Video Retrieval (CBVR) system has emerged. The CBVR system takes the inner contents of the video frame and analyses features of each frame, through which similar videos are retrieved from the database. However, searching and retrieving the same clips from huge video collection is a hard job because of the presence of complex properties of visual data. Video clips have many frames and every frame has multiple properties that have many visual properties like color, shape, and texture. In this research, an efficient content-based video retrieval system using the AlexNet model of Convolutional Neural Network (CNN) on the keyframes system has been proposed. Firstly, select the keyframes from the video. Secondly, the color histogram is then calculated. Then the features of the color histogram are compared and analyzed for CBVR. The proposed system is based on the AlexNet model of CNN and color histogram, and extracted features from the frames are together to store in the feature vector. From MATLAB simulation results, the proposed method has been evaluated on benchmark dataset UCF101 which has 13320 videos from 101 action categories. The experiments of our system give a better performance as compared to the other state-of-the-art techniques. In contrast to the existing work, the proposed video retrieval system has shown a dramatic and outstanding performance by using accuracy and loss as performance evaluation parameters.

Optimal reconstruction from quantized data

Extensive research on deep neural networks for LiDAR point clouds has contributed inexhaustible momentum to the development of computer 3D vision applications. However, storage and energy consumption have always been a challenge for deploying these deep models on mobile devices. Quantization provides a feasible route, of which current primary research is focused on uniform bit-width quantization without considering different layers or filters’ sensitivity to different bit-widths. This article proposes a novel hybrid compression method based on relaxed mixed-precision quantization, relaxed weights pruning, and knowledge distillation to overcome the limitations of uniform quantization illustrated above, while further improving model accuracy and reducing model memory consumption. It employs a differentiable searching method to search for the optimal bit allocation and weight sparsity, while conducting feature distillation, accordingly considering the feature degradation by pooling operation in point cloud deep models. The proposed method combines three compression techniques to balance the trade-off between compression accuracy and model size. Pruning alleviates the increasing memory consumption problem caused by mixed-precision quantization, while distillation improves compression accuracy without increasing model size. The experiments validate that the proposed method outperforms state-of-the-art typical uniform quantization methods in terms of accuracy with an acceptable and relatively competitive compression performance.

In automatic image tracking systems, Ihe motion information on the target image is a very important cue for locking onto the aim point. A four points matching approach for measuring the motion information of a target image in a dynamic image sequence is proposed. Comparing with two simple spatio-temporal gradient approaches, it provides good measurements in a gaussian noisy image sequence. An algorithm for extracting four points of a target image by entropic segmentation is developed. The effect of different pre-processing techniques is also discussed. Finally, the simulations are effected by a natural FLIR target image template with two artificial manoeuvring paths. The simulation results appear satisfactory even in a noise corrupted medium.