A mean shift algorithm based on modified Parzen window for small target tracking

In order to enhance the robustness of IR fast small target tracking, a novel mean shift tracking algorithm using improved similarity measure of is proposed. Firstly, problems of local background interfering in original mean shift algorithm for tracking fast motion small target is analyzed, and the reasons is located in the Bhattacharyya coefficient similarity measure expression for all gray weights of components are same, which cannot reflect the advantage contribution of the small target’s gray component in the process of measuring similarity, causing serious interference of the background in the tracking process, leaving the algorithm converging easily. Therefore, to solve this problem, the improvements Bhattacharyya coefficient similarity measure with the local background information fused is proposed. Then, shift vector is deduced in the framework of mean shift by regarding Bhattacharyya coefficients as the similarity measure.In shifting process, the robustness of the small target tracking is improved effectively according to target gray level of large membership degree with high shift weight, and vice versa with low shift weight, which the background interference is suppressed to some extent. In sake of verifying the performance of the proposed algorithm, the classical mean shift algorithm and the algorithm of this paper is used in the target tracking simulation experiment, as well as the infrared image sequences containing the small fast targets of uncooled infrared camera is used. Finally the experimental result indicates that the performance of tracking the small fast target in IR images is robust.

Small target detection and dynamic target continuous tracking are difficulties in the field of target detection and tracking respectively. The experimental results show that the smaller the target size is, the lower the detection accuracy is, the more dynamic the target is, and the lower the tracking accuracy is. This paper presents a high dynamic small target detection and tracking system which is composed of a yolov4 network, KCF tracker, and Kalman filter prediction algorithm. In this system, the detection network is divided into global and local levels, in which the global network is used for initial detection and re-detection after tracking failure, while the local detection network and tracker are used for real-time tracking of small targets, a more robust system is constructed. Compared with the original target detection network, this method weakens the influence of external factors such as the change of target shape and the fast-moving speed on the detection accuracy. The recognition rate of the small target is more than 96%, and the detection accuracy achieves 78%.

Detecting and tracking the small moving target which is below 6×6 pixels with low signal to clutter ratio is the main difficulty in practical engineering. Based on morphology, this paper presents a new approach to promote the signal to clutter rate and highlight the small target. Then a new algorithm based on kernel function density estimation and mean-shift algorithm is proposed to track the small target. Experimental results demonstrate that this approach can track and detect the real target effectively.

To solve the problems of occlusion and fast motion of small targets in unmanned aerial vehicle target tracking, an adaptive algorithm that fuses the improved color histogram tracking response and the correlation filter tracking response based on multichannel histogram of oriented gradient features is proposed to realize small target tracking with high accuracy. The state judgment index is used to determine whether the target is in a fast motion or an occlusion state. In the fast motion state, the search area is enlarged, and the color optimal model that suppresses the suspected area is used for rough detection. Then, redetection in the location of multiple peaks in the rough detection response is carried out using the correlation filter to accurately locate the target. In an occlusion state, the model stops updating, the search area is expanded, and the current color model is used for rough detection. Then, redetection in the place of multiple peaks in the rough detection response is carried out using the correlation filter to accurately locate the target. Experimental results show that the proposed method can track small targets accurately. The frame rate of the proposed method is 40.23 frames/s, indicating usable real-time performance.

Active tracking of underwater small targets is a great challenge with kinematic information alone. This is because the active sonar often encounters multipath propagation and the induced clutter can even mask target echoes. Recently, high-order time lacunarity (HOT-Lac) has shown its ability in effectively highlighting "blob" targets from high clutter harbor environments. Hence, this paper proposes a HOT-Lac aided track scoring mechanism to solve the ambiguity of data association within the framework of Multiple Hypotheses Tracking (MHT). Specifically, the trajectory consistency of potential targets is captured by a momentum accumulation of the HOT Lac feature, which can inherit the historical information for the whole track. Meanwhile, due to the separability of the distribution of target and clutter in the HOT-Lac feature space, the probabilities of the target hypothesis and null hypothesis are modeled by the online computation of the HOT-Lac feature. Finally, the cumulative likelihood ratio based on HOT-Lac is integrated into MHT to score the potential tracks. Experiments in several real-world harbor scenarios demonstrate that the proposed HOT-Lac feature-aided tracker can suppress false tracks accurately and quickly.

In this paper, the research significance of infrared small target detection and tracking is briefly introduced. Secondly, the target detection and tracking algorithm is reviewed. The basic concepts and main methods of target detection and tracking technology are clarified. The deep learning algorithm is introduced, because it becomes more and more popular in target detection and tracking algorithm. Low and relatively complex background, the detection and tracking of infrared small targets is difficult and important.

Automatic Target Recognition is typically based on single frame image processing. In this paper we report about our work in improving ATR performance by the exploitation of image sequences using a combination of target detection and tracking. The proposed detection/tracking system consists of three subsystems: (1) the target detection module which is based on a combination of multiresolution neural network target filters which are combined by a probabilistic belief network; (2) the sensor motion compensation system which generates a dense velocity field over the actual image frame, thus estimating the effect of the unknown sensor platform motion in image coordinates and (3) a multi-target-tracker which associates existing target tracks with new observations. By the hand of real world examples we show that the combined detection/tracking method overcomes the problem of spurious false alarms generated by the single frame target detector.

Dim and small infrared target fast detection guided by visual saliency

4DCT-based treatment plan, 4DCBCT-guided patient setup, and real-time tracking of target motion are essential for accurate stereotactic body radiotherapy (SBRT) of small mobile tumors. However, there is lack of correlation between 4DCT-4DCBCT data in phases of regular respiration cycles and the real-time monitored irregular respiration motion data. We are now proposing a real-time 4D video technique to synchronize respiration patterns in 4DCT, 4DCBCT, and real-time target motion during the dose delivery. Results of feasibility studies with sequential surface images on several patients and volunteers demonstrated the capability of detecting the breathing patterns by the movements of the frontal surfaces of the thorax and abdomen. The deep breathing concurs with larger thorax surface shifts of > 5-mm or tilt angles of > 2-degrees and longer respiratory cycles with periods of >6- seconds. Normal breathing usually has small thorax surface shifts of < 2-mm and angles of < 2-degrees but wide ranges of abdomen surface shifts from 2 to 30-mm and angles from 1 to 5 degrees. At free breathing conditions, we also find that patient respiration cycles and abdomen surface movements are frequently changed with time. More importantly, the personal respiration patterns are predictable with the dynamic volumetric curves determined by the abdomen and thorax surface movements. The surface movements and changes of surface covered volume can be correlated with dynamic volumetric changes in 4DCT and 4DCBCT scans. Thus, the 4D video technique is potentially useful for real-time tracking of small mobile targets in SBRT through synchronization with 4DCT or 4DCBCT.Keywords4DCT4DCBCTSBRT4D videoand gated radiotherapy

Reliable active acoustic detection and tracking of small targets while minimizing the number of false alerts is challenging in a shallow, multipath-inducing, high-clutter harbor environment. These targets often exhibit low target strength and the acoustic clutter fields can be dense and highly dynamic. One approach to detect and track targets in this environment involves a two-stage tracker due to the processing gain required to continually track a weak target in such a significant clutter field. The first stage uses more than a single frame of observations to not only initiate tracks but also to contribute to track maintenance. The second tracking stage is initiated by the tentative target tracks extracted from the first stage. Track segment association algorithms are employed to combat periods or locations track intermittency that inhibit detection and cause tracks to fail and restart. This paper describes the results of this two-stage approach to track-before-detect processing applied to a networked harbor surveillance active acoustic detection and tracking system that consists of a large number of relatively simple nodes, employs a windowed Hough-Transform tracker at the beam level, and a Kalman-based, multi-object tracker at the single- and multi-node levels.

A model has been developed to compute the signal-to-noise ratio (SNR) for quasi-point sources imaged by infrared focal-plane-array sensors. In the far field such targets can be treated as point sources, while in the near field, where the target is much larger than the instantaneous field of view (IFOV), an extended target must be assumed. This paper describes the so-called Flat-Top Model which accounts for the effects on SNR of changes in the apparent size of the target relative to the sensor IFOV as a function of range; it also takes account of the pixel size and geometry. The model was developed to support work on the tracking of small missile targets in a naval environment.

Aiming at the needs of target tracking and non-textured target tracking in images with more residual non-uniformity, this paper proposes a visual Mean-Shift algorithm and corresponding improvement measures to solve the problems of window adaptive adjustment and fast target tracking. The article also optimizes the process of ship target tracking, so it's better to meet the need of non-textured targets tracking.

According to the character for the point target and the weak and small target of the IR image, the method discerning and detecting the IR weak and small point target is discussed in this paper. The method of the background adaptive forecast is taken to catch the point target and the weak and small target. IT provides the accurate tracking of the IR image target with a good foundation. Meantime the theory of the adaptive control is utilized for analyzing the tracking and control system of IR image emphatically. According to the character and demand of the control system an adaptive fuzzy PID controller for the parameter is researched and designed to realize the accurate track of the point target and the weak and small target of the IR image. Through a large number of the imitation for the practical system the results prove that the adaptive controller is provided with the high controlling precision, high speed response and the satisfactory robustness.

The traditional mean shift algorithm used fixed kernels or symmetric kernel function, which will cause the target tracking lost or failure. The target tracking algorithm based on mean shift with adaptive bandwidth was proposed. Firstly, the signed distance constraint function was introduced to produce the anisotropic kernel function based on signed distance kernel function. This anisotropic kernel function satisfies that the value of the region function outside the target is zero, which provides accurate tracking window for the target tracking. Secondly, calculate the mean shift window center of anisotropic kernel function template, the theory basis is the sum of vector weights from the sample point in the tracking window to the center point is zero. Thirdly, anisotropic kernel function templates adaptive update implementation by similarity threshold to limit the change of the template between two sequential pictures, so as to realize real-time precise tracking. Finally, the contrast experimental results show that our algorithm has good accuracy and high real time.

Real-time object tracking for unmanned aerial vehicles (UAVs) is an essential and challenging research topic for computer vision. However, the scenarios that UAVs deal with are complicated, and the UAV tracking targets are small. Therefore, general trackers often fail to take full advantage of their performance in UAV scenarios. In this paper, we propose a tracking method for UAV scenes, which utilizes background cues and aberrances response suppression mechanism to track in 4 degrees-of-freedom. Firstly, we consider the tracking task as a similarity measurement problem. In this study, we decompose this problem into two subproblems for optimization. Secondly, to alleviate the problem of small targets in UAV scenes, we utilize background cues fully. Also, to reduce interference by background information, we employ an aberrance response suppression mechanism. Then, to obtain accurate target state information, we introduce a logarithmic polar coordinate system. We perform phase correlation calculations in logarithmic polar coordinates to obtain the rotation and scale changes of the target. Finally, target states are obtained through response fusion, which includes displacement, scale, and rotation angle. Our approach is carried out in a large number of experiments on various UAV datasets, such as UAV123, DBT70, and UAVDT2019. Compared with the current advanced trackers, our method is superior on UAV small target tracking.