Ultraviolet target tracking using mask-based four-pixel parallel detection

Target detection and tracking is a key technology in intelligent monitoring system. However, it is still difficult to design a robust, accurate and real-time target detection and tracking algorithm. Taking target Tracking as the research focus, this paper focuses on one of the current mainstream algorithms, namely, TLD (tracking-learning-detection) target Tracking algorithm. Based on the theory of TLD target tracking and corner detection, a new target tracking method was proposed to solve the existing problems. A classifier is built online to track and learn the target in real time, and a target contour detector is added in the system to complement the random forest detector to solve the problem of tracking failure. Experimental results show that the proposed algorithm can effectively overcome the influence of fast change or depth occlusion, and improve the tracking efficiency of moving targets.

Target positioning and tracking in wireless sensor networks (WSNs) are necessary for real ap-plications. This paper uses an artificial fish swarm algorithm (AFSA) with receive signal strength indicator (RSSI) for indoor target positioning and tracking. The performance of random and fixed artificial fish deployment topologies in AFSA for target positioning and tracking is investigated when the number of artificial fish is 12, 24, 52, 72, and 100, respectively. The simulation results show that the difference in average error between the random and fixed deployments is 5%, and the average positioning time is 2% for target position. The target tracking performance of fixed deployment is better than that of random one when the number of artificial fish is small.

Purpose/Objective(s): Herein, we report the results of an IRB-approved phase II trial of Varian Trilogy/TrueBeam-based stereotactic ablative body radiotherapy (SABR) monotherapy for low-risk prostate cancer using the Calypso® System to provide real-time electromagnetic tracking of the prostate’s position during treatment delivery.Materials/Methods: A total of 102 low-risk patients completed protocol treatment between January 2007 and May 2009. A total dose of 40.0 Gy in 5 every-other-day fractions of 8.0 Gy was prescribed to the planning target volume. Target setup and tracking procedures were as follows: (1) the Calypso® System was used to achieve target setup prior to each fraction; (2) conebeam CT imaging was then used for correction of setup error and for assessment of target and organs-at-risk deformations; (3) after treatment delivery was initiated, the Calypso® System then provided real-time intrafractional target tracking. The NCI CTCAE v3.0 was used to assess urinary and rectal toxicity during treatment and at defined follow-up time points. Biochemical response and quality of life measurements were made at concurrent follow-up points.Results: Urinary toxicities were most common. At 6 months, 19.6, 2.9, and 4.9% of patients reported grades 1–2 urinary frequency, dysuria, and retention, respectively. Rectal toxicities were uncommon. By 12 months, 2.9% of patients reported painless rectal bleeding with subsequent symptom resolution without requiring invasive interventions. Quality of life measurements demonstrated a significant decline over baseline in urinary irritative/obstructive scores at 1 month following SABR but otherwise did not demonstrate any difference for bowel, bladder, and sexual function scores at any other follow-up time point. One patient suffered biochemical recurrence at 6 years following SABR.Conclusion: At 5 years, minimum follow-up for this favorable patient cohort, prostate SABR resulted in favorable toxicity, quality of life, and biochemical outcomes.

The on‐board target tracking of unmanned aerial vehicle (UAV) relies on on‐board computer to process the collected ground image information, and then use the target tracking algorithm to achieve the target tracking function, which provides the user with target position, trajectory and other information. UAVs are limited by load and power consumption. Due to the high resolution and frame rate of UAV's image collection system, traditional target tracking platforms cannot meet the requirements. As a result, the real‐time nature of the tracking platform urgently needs to be resolved. This study designs and implements the airborne ground target tracking accelerator for UAV. The kernelised correlation filters (KCFs) algorithm with low computational complexity and precision is selected to achieve the airborne ground target tracking function and its performance bottleneck is analysed. In order to improve the real‐time performance of the tracking task processing, the ZYNQ platform based on ARM and field programmable gate arrays is chosen to achieve the hardware acceleration of the KCF algorithm. The KCF algorithm is implemented in hardware using the high‐level synthesis technology, and a high‐speed data transmission link is established. Experiments show that the design can achieve a tracking rate of more than 30 FPS under 960 × 540 resolution, which meets the real‐time requirements of UAV target tracking task.

The poor real-time performance and target occlusion occurred easily when the UAV was tracking the target. In this paper, a target tracking method based on the Back Propagation neural network fusion Kalman filter algorithm was developed to solve the position prediction problem of the UAV target tracking in real time. Firstly, the target tracking algorithm was used to acquire the center position coordinates of the target on the onboard computer, and then the coordinate difference matrix was constructed to train the BP neural network in real time. Secondly, when the target was occluded by the obstacles judged by the Bhattacharyya coefficient, the BP neural network fusion Kalman filter algorithm was used to accurately predict the center position coordinates of the occluded target. Then the flight speed of UAV was calculated by the deviation between the coordinates of the target and the image center. Finally, the velocity command was sent to the UAV by the onboard computer. The experimental results shown that the target position predicted by BP neural network fusion Kalman filter algorithm was more accurate and robust in predicting the center position coordinates of the target, and the UAV can track the moving target on the ground stably.

This paper aims to increase the Unmanned Aerial Vehicle's (UAV) capacity for target tracking. First, a control model based on fuzzy logic is created, which modifies the UAV's flight attitude in response to the target's motion status and changes in the surrounding environment. Then, an edge computing-based target tracking framework is created. By deploying edge devices around the UAV, the calculation of target recognition and position prediction is transferred from the central processing unit to the edge nodes. Finally, the latest Vision Transformer model is adopted for target recognition, the image is divided into uniform blocks, and then the attention mechanism is used to capture the relationship between different blocks to realize real-time image analysis. To anticipate the position, the particle filter algorithm is used with historical data and sensor inputs to produce a high-precision estimate of the target position. The experimental results in different scenes show that the average target capture time of the algorithm based on fuzzy logic control is shortened by 20% compared with the traditional proportional-integral-derivative (PID) method, from 5.2 s of the traditional PID to 4.2 s. The average tracking error is reduced by 15%, from 0.8 m of traditional PID to 0.68 m. Meanwhile, in the case of environmental change and target motion change, this algorithm shows better robustness, and the fluctuation range of tracking error is only half of that of traditional PID. This shows that the fuzzy logic control theory is successfully applied to the UAV target tracking field, which proves the effectiveness of this method in improving the target tracking performance.

An improved maximum between-cluster variance (Otsu) method based on iteration was proposed for the purpose of realizing target recognition and target tracking effectively. Improved Otsu method was used to segment image collected by CCD, so as to extract the target from image and finish the target localization. By calculating centroid of the target in a single frame and extracting feature point of outline constituted by centroids of the single-frame target within unit interval, a polygon can be formed, the gravity center of which was taken as the target position. Filter model was established of which the control input is nonzero based on Kalman filter Principle, which was combined with target position at this moment can be used to predict the gravity center of the target at the next moment. The experiment and simulation results indicated that improved Otsu method can solve the problem that target and background are segmented mistakenly when image thresholding. Kalman filtering was able to predict target trajectory effectively after target being recognized. The requirement of target tracking was satisfied and target tracking was realized through this improved Otsu target tracking algorithm based on iteration.

针对图像序列中运动目标检测、跟踪的难点问题，提出了一种实时运动目标检测与跟踪算法。该算法基于自适应背景建模，获取运动目标背景模型和前景图像，从而实现运动目标检测；通过建立运动目标的位置、大小、形状以及颜色分布模型，构造运动目标全局匹配函数，结合目标活力特征，实现多运动目标连续匹配和跟踪。实验结果表明，相对于传统的运动目标跟踪方法，本文方法明显减少了运算时间，增强了环境适应性，实现了复杂场景下运动目标的准确检测和稳定跟踪，对非刚性目标的形变、旋转具有较强的鲁棒性。In this paper, we propose a real-time mobile target detection and tracking algorithm for challenges of mobile target detection and tracking in sequential images. This algorithm based on the adaptive background modeling obtains background model and front-view images of mobile targets, which is the way to achieve target detection. Continuous matching and tracking of multiple mobile targets are realized through constructing position, size, shape and color distribution of the mobile targets, defining a global matching function for those targets, and associating their vitality characteristics. It is demonstrated by experiments that the algorithm presented in this paper, compared to the traditional methods of mobile target tracking, significantly reduces the computation time, improves adaptive feature to environments, achieves accurate detection and robust tracking of mobile targets in complex environments, and shows strong robustness to deformation and rotation of non-rigid targets.

In this paper an uncooled infrared camera with embedded target detection and tracking capability is presented. The camera is built upon four main electronic cards. Sensor card is designed to read and digitize the analog output signal generated by the infrared (IR) imaging sensor. FPGA card carries out the control process of the data transfer between sensor card and other peripherals. Target detection/tracking task is on the row image data provided by the FPGA card is carried out on the DSP card. Frame thresholding and differencing methods are used for target detection. Kalman filter is utilized for target tracking. According to the experimental results, camera is capable of performing target detection and tracking tasks in real time.

Video tracking uses the semantic information between video image sequences to process, analyze and study the target to achieve target tracking. In response to the problems of sharp changes in target position, large deformation, and occlusion due to similar background interference, changes in lighting conditions, and different shapes of targets in the target tracking process, the tracking algorithm is less accurate and less robust in target appearance. An improved target tracking algorithm based on multi-domain network (MDNet) is proposed to solve this problem. By adding the Image-Align layer to the video target tracking task, a more accurate target value is obtained; applying the Directed Acyclic Graph-Recurrent Neural Network (DAG-RNN) by combining it with a convolutional neural network and modeling image neighborhood context dependencies for the target region to be tracked, we improve the problem that conventional networks only perform multi-layer extraction for the appearance features of the target, thus resulting in poor robustness to changes in target appearance; ROI Align layer is added after the convolution layer to speed up target feature extraction.

Target detection and tracking in real-time video streaming is one of the core tasks in the field of computer vision, and its performance directly affects the effectiveness of intelligent surveillance, automatic driving and other applications. In this paper, a three-frame frame difference method incorporating Sobel operator is proposed to optimize the boundary extraction by combining morphological filtering. Meanwhile, the Mean Shift-based target tracking algorithm is improved by introducing a recognizable interferer model with a dual attention mechanism to enhance the tracking robustness. Experiments show that the improved inter-frame difference method achieves F-measure of 93.38%, 96.20% and 91.83% on Highway, Road and Highway2 datasets, respectively, and the detection frame rate is improved to 32 f/s. The improved Mean Shift algorithm improves the tracking accuracy by 2.67%-3.09% and the success rate by 0.98%-1.75% over the mainstream algorithm on the UAV123 and VOT2024 datasets. In addition, the multi-target tracking experiments achieve MOTA of 75.76% and 80.61% on the MOT16 and MOT17 datasets, respectively, validating the comprehensive performance advantages of the algorithms. This study provides an efficient and robust solution for target detection and tracking in real-time video streaming.

Background. The increasing complexity of radiotherapy (RT) has motivated research into three-dimensional (3D) dosimetry. In this study we investigate the use of 3D dosimetry with polymerizing gels and optical computed tomography (optical CT) as a verification tool for complex RT: dose painting and target tracking. Materials and Methods. For the dose painting studies, two dosimeters were irradiated with a seven-field intensity modulated radiotherapy (IMRT) plan with and without dose prescription based on a hypoxia image dataset of a head and neck patient. In the tracking experiments, two dosimeters were irradiated with a volumetric modulated arc therapy (VMAT) plan with and without clinically measured prostate motion and a third with both motion and target tracking. To assess the performance, 3D gamma analyses were performed between measured and calculated stationary dose distributions. Results. Gamma pass-rates of 95.3% and 97.3% were achieved for the standard and dose-painted IMRT plans. Gamma pass-rates of 91.4% and 54.4% were obtained for the stationary and moving dosimeter, respectively, while tracking increased the pass-rate for the moving dosimeter to 90.4%. Conclusions. This study has shown that the 3D dosimetry system can reproduce and thus verify complex dose distributions, also when influenced by motion.

Current image-guided prostate radiotherapy often relies on the use of implanted fiducial markers (FMs) or transducers for target localization. Fiducial or transducer insertion requires an invasive procedure that adds cost and risks for bleeding, infection and discomfort to some patients. We are developing a novel markerless prostate localization strategy using a pre-trained deep learning model to interpret routine projection kV X-ray images without the need for daily cone-beam computed tomography (CBCT). A deep learning model was first trained by using several thousand annotated projection X-ray images. The trained model is capable of identifying the location of the prostate target for a given input X-ray projection image. To assess the accuracy of the approach, three patients with prostate cancer received volumetric modulated arc therapy (VMAT) were retrospectively studied. The results obtained by using the deep learning model and the actual position of the prostate were compared quantitatively. The deviations between the target positions obtained by the deep learning model and the corresponding annotations ranged from 1.66 mm to 2.77 mm for anterior-posterior (AP) direction, and from 1.15 mm to 2.88 mm for lateral direction. Target position provided by deep learning model for the kV images acquired using OBI is found to be consistent that derived from the implanted FMs. This study demonstrates, for the first time, that highly accurate markerless prostate localization based on deep learning is achievable. The strategy provides a clinically valuable solution to daily patient positioning and real-time target tracking for image-guided radiotherapy (IGRT) and interventions.

Suppose that we have the distances to p + 1 targets obtained from a moving platform at discrete times with the ( p + 1)st target being a reference beacon. Assume that the distances are measured with an additive error which has a zero mean and that the errors are uncorrelated in time and space. Given the knowledge of the error structure, the position of the reference target, and the set of the successive simultaneous ranges, we present a statistical method for accurately determining the positions of the remaining targets in a computationally reasonable manner, assuming that the platform positions satisfy a certain constraint. Alternatively, reversing the roles of targets and observer, the method can be used to track a moving target platform using ranges simultaneously measured from p observers whose fixed positions are known, provided that there is a ( p + 1)st observer at a known position. As long as the target track is sufficiently variable, the discrete-time range data can be used to estimate the position of the p observers and the target track. In practice the method could be used to refine the location estimates of the observers based on successive simultaneous range measurements of the target while tracking the target. If {\sl two} observer positions {sl are known}, {sl no constraint} has to be put on the target track. The technique is analyzed using several artificial data sets for one reference target (or observer). We show that when the error is small we obtain an accurate map of ten fixed targets from 500 platform locations, and the map is also reasonably accurate even when the mean error is 70 percent of the average true distance. We also analyze another model that has 14 targets observed from 1000 locations but where the location of two of these targets are known. In any of the scenerios, as the number of successive range measurements whose errors are uncorrelated grows to infinity, the coordinate estimates of the p target (observer) locations converges in probability to the true coordinates.

Radiotherapy of moving targets, such as lung, liver or prostate tumors, is prone to treatment errors due to the uncertainties in the target position. Minimizing such error is critical for radiotherapy treatments, especially hypofractionated SBRT treatments. On‐board real time imaging verification and tracking of moving targets has become one of the most exciting areas in radiotherapy. The tremendous developments in this area enable us to improve targeting accuracy and reduce the healthy tissue toxicity, which paves the road to further margin reduction and dose escalation in conventionally fractionated or SBRT treatments.Over the past few years, several real‐time imaging techniques have been clinically implemented, including techniques using ionizing radiation, such as x‐ray based imaging, and radiation‐free techniques such as MRI, imaging based on implanted electromagnetic transponders and optical imaging. The x‐ray imaging techniques are widely accessible in clinics, although they have limited soft tissue contrast and contribute to patient exposure. Recently, MRI has gained wide interests in radiotherapy due to its better soft tissue contrast and no radiation dose. Imaging based on electromagnetic transponders and optical imaging have also gained popularity in many clinical scenarios due to their unique capabilities.Based on these imaging techniques, various tracking approaches have been developed. The room mounted orthogonal 2D x‐ray system (CyberKnife system) was the first medical device capable to perform real‐time target tracking by combining image guidance with robotically targeted radiation delivery. In the Vero system, tumor tracking is achieved by combining image‐guidance with a two‐dimensional pivot assembly of the linear accelerator. In gantry‐based linear accelerators, target motion can be tracked in real time by repositioning the MLC based on the signal from x‐ray images or electromagnetic transponders implanted.The rapid development of new imaging and tracking technologies raises new challenges in revolutionizing our treatment procedures. It becomes important to understand the functionality, limitations and clinical impact of each technique so that they can be chosen wisely for different clinical settings. The goal of this educational session is to compare and contrast different imaging and tracking techniques implemented in CyberKnife, Vero, MRI based, and gantry‐based radiotherapy machines. The general concepts of real‐time imaging and tracking, from imaging the target to adapting the treatment, will be reviewed for each modality. While discussing the technical aspects of the systems including the overall uncertainties and residual imaging and tracking errors, emphasis will be placed on the clinical implementation and workflow. The increased patient dose due to x‐ray imaging and quality assurance procedures will be described. Additionally, the impact of tracking on treatment volume and margin reduction will be discussed. The session will close with an outlook at future developments.Learning Objectives: Understand the opportunities and challenges of real time imaging and tumor tracking. Understand the advantages and limitations of different imaging and tracking techniques, as well as the clinical implementation of each technique. Understand the clinical impact of real time tumor tracking and future directions in this area. Supported by National Institutes of Health, Varian Medical System, Accuray Inc.