Mean Shift Tracking Research Articles

Adaptive Real-Time Tracking of Molten Metal Using Multi-Scale Features and Weighted Histograms

In this study, we study the tracking of the molten metal region in the dross removal process during metal ingot casting, and propose a real-time tracking method based on adaptive feature selection and weighted histogram. This research is highly significant in metal smelting, as efficient molten metal tracking is crucial for effective dross removal and ensuring the quality of metal ingots. Due to the influence of illumination and temperature in the tracking environment, it is difficult to extract suitable features for tracking molten metal during the metal pouring process using industrial cameras. We transform the images captured by the camera into a multi-scale feature space and select the features with the maximum distinction between the molten metal region and its surrounding background for tracking. Furthermore, we introduce a weighted histogram based on the pixel values of the target region into the mean-shift tracking algorithm to improve tracking accuracy. During the tracking process, the target model updates based on changes in the molten metal region across frames. Experimental tests confirm that this tracking method meets practical requirements, effectively addressing key challenges in molten metal tracking and providing reliable support for the dross removal process.

Siamese Cross-Domain Tracker Design for Seamless Tracking of Targets in RGB and Thermal Videos

Multimodal (RGB and thermal) applications are swiftly gaining importance in the computer vision community with advancements in self-driving cars, robotics, Internet of Things, and surveillance applications. Both the modalities have complementary performance depending on illumination constraints. Hence, a judicious combination of both modalities will result in robust RGBT systems capable of all-day all-weather applications. Several studies have been proposed in the literature for integrating the multimodal sensor data for object tracking applications. Most of the proposed networks try to delineate the information into modality-specific and modality shared features and attempt to exploit the modality shared features in enhancing the modality specific information. In this work, we propose a novel perspective to this problem using a Siamese inspired network architecture. We design a custom Siamese cross-domain tracker architecture and fuse it with a mean shift tracker to drastically reduce the computational complexity. We also propose a constant false alarm rate inspired coasting architecture to cater for real-time track loss scenarios. The proposed method presents a complete and robust solution for object tracking across domains with seamless track handover for all-day all-weather operation. The algorithm is successfully implemented on a Jetson-Nano, the smallest graphics processing unit (GPU) board offered by NVIDIA Corporation.

Novel object detection technique for videos with homogeneous background

Object detection and tracking in video frames play a major role in all the computer vision systems. Several computer vision systems use background subtraction method for detecting the objects. However, Background subtraction method often results in lack of accuracy during frame comparison. Also, it leads to increase in memory requirements and computational complexity while setting threshold. The new Local Mean Diamond Pattern (LMDP) is introduced here to overcome the existing issues by extracting the objects directly from the frames. The extracted objects are tracked using mean shift tracking algorithm. The experimental result shows that the LMDP outperforms the existing methods viz., Local Binary Pattern (LBP), Local Extrema Pattern (LEP) and Local Rhombus Pattern (LRP) in terms of accuracy.

Intelligent Wearable Devices Enabled Automatic Vehicle Detection and Tracking System with Video-Enabled UAV Networks Using Deep Convolutional Neural Network and IoT Surveillance.

The discipline of computer vision is becoming more popular as a research subject. In a surveillance-based computer vision application, item identification and tracking are the core procedures. They consist of segmenting and tracking an object of interest from a sequence of video frames, and they are both performed using computer vision algorithms. In situations when the camera is fixed and the backdrop remains constant, it is possible to detect items in the background using more straightforward methods. Aerial surveillance, on the other hand, is characterized by the fact that the target, as well as the background and video camera, are all constantly moving. It is feasible to recognize targets in the video data captured by an unmanned aerial vehicle (UAV) using the mean shift tracking technique in combination with a deep convolutional neural network (DCNN). It is critical that the target detection algorithm maintains its accuracy even in the presence of changing lighting conditions, dynamic clutter, and changes in the scene environment. Even though there are several approaches for identifying moving objects in the video, background reduction is the one that is most often used. An adaptive background model is used to create a mean shift tracking technique, which is shown and implemented in this work. In this situation, the background model is provided and updated frame-by-frame, and therefore, the problem of occlusion is fully eliminated from the equation. The target tracking algorithm is fed the same video stream that was used for the target identification algorithm to work with. In MATLAB, the works are simulated, and their performance is evaluated using image-based and video-based metrics to establish how well they operate in the real world.

Intelligent Target Detection and Tracking Algorithm for Martial Arts Applications

Moving object detection and tracking is the basis and key technology for intelligent video surveillance, human-computer interaction, mobile robot and vehicle visual navigation, industrial robot system, and other applications. It has important applications in intelligent monitoring, human-computer interaction, visual navigation, and so on. Intelligent technology can greatly facilitate the monitoring of countless targets. This paper adopts the random motion model to describe the motion state of the target. Based on wireless communication and information security, this paper studies the communication and information security of the intelligent system of martial arts target detection and tracking algorithm, and the basic idea of mean-shift tracking algorithm is to use gradient climbing of probability density to find local optimal. This paper uses the background subtraction method based on the vibe algorithm to obtain the binary image of the foreground object; the shadow detection algorithm is used to remove the shadow of the foreground image; the haar-like (Haar) feature is selected as the feature of motion detection, and the feature value of the rectangular area is quickly calculated to describe the adjacent image area. The difference between the features, the final result image, and then the intelligent system for analysis. Experimental data shows that the time consumed by the tracking algorithm is less than 20 ms, which can meet the real-time requirements of ordinary target tracking systems. The average processing time of the hybrid modeling method is 62.8 ms, and the detection rate is 15.92 frames/SEC. The results show that the algorithm improves the utilization of particles, greatly reduces the complexity, and reduces the degradation of the particle filter.

A fast region-based active contour for non-rigid object tracking and its shape retrieval.

Conventional tracking approaches track objects using a rectangle bounding box. Gait, gesture and many medical analyses require non-rigid shape extraction. A non-rigid object tracking is more difficult because it needs more accurate object shape and background separation in contrast to rigid bounding boxes. Active contour plays a vital role in the retrieval of image shape. However, the large computation time involved in contour tracing makes its use challenging in video processing. This paper proposes a new formation of the region-based active contour model (ACM) using a mean-shift tracker for video object tracking and its shape retrieval. The removal of re-initialization and fast deformation of the contour is proposed to retrieve the shape of the desired object. A contour model is further modified using a mean-shift tracker to track and retrieve shape simultaneously. The experimental results and their comparative analysis concludes that the proposed contour-based tracking succeed to track and retrieve the shape of the object with 71.86% accuracy. The contour-based mean-shift tracker resolves the scale-orientation selection problem in non-rigid object tracking, and resolves the weakness of the erroneous localization of the object in the frame by the tracker.

Curling stone tracking based on an enhanced mean-shift algorithm using optimal feature vector

Computer vision technology can automatically detect and recognize objects on the ground or on a court, such as balls, players, and lines, using camera sensors. These are non-contact sensors, which do not interfere with an athlete’s movement. The game elements detected by such measuring equipment can be used for game analysis, judgment, context recognition, and visualization. This paper proposes a method to automatically track the position of stones in curling sport images using computer vision technology. The authors extract the optimal feature vector of the mean-shift tracking algorithm by obtaining the optimal histogram from the color and edge information of the curling stone, thereby adaptively controlling the number of bins in the histogram. After evaluating the performance of the curling stone tracking method among 1424 image frames from curling sport videos, the authors found that the proposed method improved detection rate (overlap threshold = 0.9) by 14.85% compared to the general mean-shift method.

Memory access minimization for mean-shift tracking in mobile devices

Due to the development of artificial intelligence and computer vision technology, many autonomous drones have been studied. However, computer vision technology requires high performance CPU due to its high complexity, and battery consumption is so high that drones are constrained to fly for a long time. Therefore, low-power mobile devices require tracking algorithms that minimize battery consumption. In this paper, we propose a mean-shift based tracking algorithm that minimizes memory access to reduce battery consumption. To accomplish this, we minimize the number of memory accesses by using an algorithm that divides the direction of the mean-shift vector into eight, and calculates the sum of the density maps only for the new area without calculating the sum of the density maps for the already calculated area. It is possible to increase the calculation efficiency by lowering the memory access cost. Experimental results show that the proposed method is more efficient than the existing method.

High-order Taylor expansion based image space transform method for real-time augmented reality

This paper proposes a real-time augmented reality method based on Taylor expansion formula. This method has the advantage that the pixel relationship in the discrete image space is converted to a continuous high-order Taylor space and maintains pixel invariance. After conversion to Taylor space, the ability to resist dramatic changes in illumination between frames is enhanced and robust to intra-frame local illumination mutations. In the spatial transformation process, differential low-order features are used to represent higher-order features, multiplied by appropriate feature coefficients. These coefficients are first determined theoretically and then experimentally verified, allowing us to obtain high-order feature information and approximate the original pixel values based on the features. We then applied this technique to color-based mean shift tracking problems to achieve promising results.

Research and Implementation of Object Tracking

Aiming at the problems that the traditional MeanShift has a singleness feature, this paper introduces depth feature based on binocular vision, thus proposes a depth feature based real-time MeanShift tracking algorithm. Firstly, a similarity measurement method based on advanced quadratic-form distance is put forward. Secondly, the self-adaptive adjustment mechanism of feature weight coefficient and updating strategy of object model are improved based on the color and depth features. Finally, the algorithm is simulated by Matlab. Results show that the proposed algorithm performs well in tracking accuracy, robustness.

Re-projected SURF Features Based Mean-Shift Algorithm For Visual Tracking

Visual tracking is an art of tracking a moving object over video frames using non-stationary cameras, for which feature descriptors of the target are computed and applied to a motion model. In this paper, SURF is used to compute the feature descriptors and Mean-Shift algorithm as a motion model. Mean-shift algorithm is fundamentally a logical approach to track the object on an image frame where the appearance is described by histograms. Mean-Shift tracking can directly be applied to SURF features but there is a big constraint of availability of an adequate number of feature keypoints for a given object. To get over this limitation, the re-projection technique is implemented in this paper for tracking an object in any video recorded from a mobile or stationary camera. Re-projection, online updates the histogram of object template for every frame by superimposing the feature keypoints from upcoming frames to the first frame. The object can be tracked using SURF descriptors without using any secondary information (color, texture, optical flow, gradient, etc.) regarding the object, which makes it computationally inexpensive to be used in real-time systems. Also, the SURF feature is calculated only for the target object that is to be tracked, this further reduces computational complexity. The simulation results prove the effectiveness of the work.

Continuously Adaptive Mean-shift Tracking Algorithm Based on Improved Gaussian Model

In complex scenes with light changes, deformations, and occlusions, target tracking easily contains a large amount of background color information when building a target color model. Thus, the tracking effect is reduced. To improve the accuracy of the traditional continuously adaptive mean-shift algorithm (CAMShift) in complex scenarios, a target tracking algorithm based on an improved Gaussian mixture model was proposed. Using the Gaussian mixture model, the tracking image was divided into the foreground and background superposition. The histograms of the hue component were respectively established in the foreground and background of the target area. By suppressing the same hue as the background color in the tracking image, the target color model was established. The target position was iteratively obtained by implementing the CAMShift algorithm using the enhanced target color model. The Bhattacharyya distance between the candidate target and the target template was used as basis for updating the target model. Simulation analysis under benchmark data sets and actual monitoring scenarios verified the accuracy of the proposed algorithm. Results show that the distance precision and overlap success rate of the proposed algorithm are 0.88 and 0.625, respectively. The proposed algorithm effectively solves long-term target tracking problems with complex scenes, such as occlusion, background clutters, and illumination variation. This study eliminates the problem of target recognition caused by environmental changes and provides references for real-time monitoring of abnormal traffic conditions.

Scale-Adaptive Human Target Tracking for Through-Wall Imaging Radar

In this letter, we consider the problem of human target detecting and tracking, exploiting small-aperture through-wall imaging radar. We build a novel target model considering both the statistical and the geometrical information of the target image. A scale-adaptive target tracking method is proposed to track the scale and orientation variant human targets based on the mean-shift tracking framework, where the image moments are exploited to estimate the scale and orientation of the target image dynamically. Finally, the proposed algorithm is evaluated by simulations and experimental results.

TIR-MS: Thermal Infrared Mean-Shift for Robust Pedestrian Head Tracking in Dynamic Target and Background Variations

Thermal infrared (TIR) pedestrian tracking is one of the major issues in computer vision. Mean-shift is a powerful and versatile non-parametric iterative algorithm for finding local maxima in probability distributions. In existing infrared data, and mean-shift-based tracking is generally based on the brightness feature values. Unfortunately, the brightness is distorted by the target and background variations. This paper proposes a novel pedestrian tracking algorithm, thermal infrared mean-shift (TIR-MS), by introducing radiometric temperature data in mean-shift tracking. The thermal brightness image (eight-bits) was distorted by the automatic contrast enhancement of the scene such as hot objects in the background. On the other hand, the temperature data was unaffected directly by the background change, except for variations by the seasonal effect, which is more stable than the brightness. The experimental results showed that the TIR-MS outperformed the original mean-shift-based brightness when tracking a pedestrian head with successive background variations.

Mean Shift Tracking Based on Fuzzy Background Weighting

Aiming at the problem that Mean Shift tracking algorithm cannot track well in complicated background, a Mean Shift algorithm based on fuzzy background weighting is proposed. It introduces a fuzzy membership function based on difference, which makes use of the difference between target model and background model in order to represents each pixel contribution to target exact description, and improves target description accuracy. At the same time, the original scale increment and decrement method is improved by using background information for adapting to target scale changing. Experimental results show that the proposed algorithm solves the problem of small-scale wandering and tracking hysteresis of the scale increment and decrement method to a certain extent, and improves the robustness of Mean Shift algorithm under complex background disturbances.

Context-Aware Three-Dimensional Mean-Shift With Occlusion Handling for Robust Object Tracking in RGB-D Videos

Depth cameras have recently become popular and many vision problems can be better solved with depth information. But, how to integrate depth information into a visual tracker to overcome the challenges such as occlusion and background distraction is still underinvestigated in current literature on visual tracking. In this paper, we investigate a 3-D extension of a classical mean-shift tracker whose greedy gradient ascend strategy is generally considered as unreliable in conventional 2-D tracking. However, through careful study of the physical property of 3-D point clouds, we reveal that objects which may appear to be adjacent on a 2-D image will form distinctive modes in the 3-D probability distribution approximated by kernel density estimation, and finding the nearest mode using 3-D mean-shift can always work in tracking. Based on the understanding of 3-D mean-shift, we propose two important mechanisms to further boost the tracker's robustness: one is to enable the tracker to be aware of potential distractions and make corresponding adjustments to the appearance model; and the other is to enable the tracker to detect and recover from tracking failures caused by total occlusion. The proposed method is both effective and computationally efficient. On a conventional personal computer, it runs at more than 60 FPS without graphical processing unit acceleration.

Optimized Memory Allocation and Power Minimization for FPGA-Based Image Processing.

Memory is the biggest limiting factor to the widespread use of FPGAs for high-level image processing, which require complete frame(s) to be stored in situ. Since FPGAs have limited on-chip memory capabilities, efficient use of such resources is essential to meet performance, size and power constraints. In this paper, we investigate allocation of on-chip memory resources in order to minimize resource usage and power consumption, contributing to the realization of power-efficient high-level image processing fully contained on FPGAs. We propose methods for generating memory architectures, from both Hardware Description Languages and High Level Synthesis designs, which minimize memory usage and power consumption. Based on a formalization of on-chip memory configuration options and a power model, we demonstrate how our partitioning algorithms can outperform traditional strategies. Compared to commercial FPGA synthesis and High Level Synthesis tools, our results show that the proposed algorithms can result in up to 60% higher utilization efficiency, increasing the sizes and/or number of frames that can be accommodated, and reduce frame buffers’ dynamic power consumption by up to approximately 70%. In our experiments using Optical Flow and MeanShift Tracking, representative high-level algorithms, data show that partitioning algorithms can reduce total power by up to 25% and 30%, respectively, without impacting performance.

Visual Detection and Tracking Based on Fusion Saliency

In order to improve the ability of target tracking effectively, an improved MeanShift algorithm is proposed in this paper. The algorithm combines the saliency map from the computer and from the human vision through Kinect, so that it can obtain the fusion saliency. Then an image segmentation algorithm is adopted to get the target, which is modelled for an improved MeanShift tracking framework. Experimental results show that the algorithm can significantly improve the accuracy.

Using spatial overlap ratio of independent classifiers for likelihood map fusion in mean-shift tracking

We combine the outputs of independent classifiers for mean-shift tracking within the likelihood map fusion framework and introduce a novel likelihood fusion technique that directly employs the tracking confidences of likelihood maps which are generated by different binary classifiers. Our proposed measure tries to compensate drifting that may be caused by each likelihood map using their independent tracking results. We present results obtained with the proposed fusion approach using two different classifiers, where one models the tracked object and one models the background. The results show superior performance of the proposed fusion technique as compared to the others. We further discuss how the proposed likelihood map fusion approach can be generalized to any number and any kind of likelihood maps.

Summary of the Special Issue “Neutrosophic Information Theory and Applications” at “Information” Journal

Over a period of seven months (August 2017–February 2018), the Special Issue dedicated to “Neutrosophic Information Theory and Applications” by the “Information” journal (ISSN 2078-2489), located in Basel, Switzerland, was a success. The Guest Editors, Prof. Dr. Florentin Smarandache from the University of New Mexico (USA) and Prof. Dr. Jun Ye from the Shaoxing University (China), were happy to select—helped by a team of neutrosophic reviewers from around the world, and by the “Information” journal editors themselves—and publish twelve important neutrosophic papers, authored by 27 authors and coauthors. There were a variety of neutrosophic topics studied and used by the authors and coauthors in Multi-Criteria (or Multi-Attribute and/or Group) Decision-Making, including Cross Entropy-Based MAGDM, Neutrosophic Hesitant Fuzzy Prioritized Aggregation Operators, Biparametric Distance Measures, Pattern Recognition and Medical Diagnosis, Intuitionistic Neutrosophic Graph, NC-TODIM-Based MAGDM, Neutrosophic Cubic Set, VIKOR Method, Neutrosophic Multiple Attribute Group Decision-Making, Competition Graphs, Intuitionistic Neutrosophic Environment, Neutrosophic Commutative N-Ideals, Neutrosophic N-Structures Applied to BCK/BCI-Algebras, Neutrosophic Similarity Score, Weighted Histogram, Robust Mean-Shift Tracking, and Linguistic Neutrosophic Cubic Numbers.