Performance Measurement of Photoelectric Detection and Target Tracking Algorithm

The changed environment factors will affect the capture rate of target and the detection performance in photoelectric detection screen testing system, to improve the detection performance of system, it is very necessary to establish the target optical characteristic model and correlation detection probability calculation model. Based on the detection principle of unit photoelectric detection screen and the spatial geometric relation of four photoelectric detection screens testing system, this article establishes a new target radiation characteristics calculation model by using target's radiation luminance and radiation energy, gives the output signal expression function, derived the detection probability function by signal to noise ratio (SNR) and false alarm probability. Through calculation analysis, the results show that the detection probability of four photoelectric detection screens testing system is related to the target optical characteristic, the output photoelectric current and SNR of photoelectric detection receiving sensor can describe target detection performance. According to the experiments testing, the proposed calculation model can effectively evaluate the performance of photoelectric detection screen testing system.

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.

In this paper we propose a robust object tracking algorithm using a improved Mean-Shift model. As the traditional Mean-Shift algorithm for object tracking uses a single histogram. Because the traditional Mean-Shift lacks spatial distribution information, so it is difficult to track non-rigid object especially. With a focus on this problem, an improved Mean-Shift algorithm based on the shape feature and color of the target is presented. The results show that the algorithm can track the moving vehicles in real time, and it has a preferable adaptability and robustness to the irregular motion and deformation of the target.

In the photoelectric detection system, the photoelectric detector can convert the optical signal to be measured into a current signal, and the current amplifier transforms the current signal output by the detector into a voltage signal for amplification. In this study, the photo-multiplier tube (PMT) is selected as the photoelectric detector. Compared with other photoelectric detectors, it can obtain higher internal gain, higher sensitivity, and better response performance. The current amplifier is prepared by pre-amplifier and voltage amplifier. In order to capture photoelectric signals well, a large-format scanning system is set up to design each component module, control module, and host computer module of the system. Besides, a machine learning-based algorithm is proposed, namely semi-supervised manifold image recognition algorithm, which is used for identify photoelectric detection images. In the test process, the printed circuit board (PCB) and sapphire material are firstly used as the substrate of the current amplifier, and their influences in the circuit are compared. The peak value of the output noise of each substrate circuit is around 2.8 mV when the input of the current amplifier is short-circuited. Then, the signal gain and signal bandwidth of the photoelectric detection system remain stable when there is no optical signal input. During the process of changing the system signal gain ratio, the noise output of the system is the lowest when the voltage of PMT is 0.50 V and the current amplifier gain is set to 2.2 × 105 V/A. The proposed recognition algorithm can identify different types of targets well. After the image is projected into a two-dimensional space by the algorithm, the distance between classes increases, and the targets in the class promote aggregation, thereby enhancing the identify-ability between samples.

Real time and accrual object tracking is ultimate aim of a visual tracker. Recently mean shift object tracking algorithm is studied in an all-round way and utilized to visual tracking in both civil and military fields. Compared to the traditional mean shift algorithm and its other versions distance weight mean shift algorithm can effectively improve the precision and robustness. It analyzes the dissimilarity of target feature color histogram with distance weight and candidate area feature color histogram with distance weight to calculate mean shift vector, and searches for target area via each iteration in candidate area. Though improved on basis of traditional mean shift algorithm, there are a large amount of calculations and the processing speed has already been a bottleneck in real time object tracking. Graphics processor unit (GPU) has special hardware parallel computing resources and has been already employed in various embedded systems. It provides us with an alternative implementation on GPU which can solve such bottleneck problem. The paper proposes a way of implementation of distance weight mean shift algorithm on GPU. The experiment results show that the execution performance of the implementation on GPU is over 56 times speedup of that completely on CPU at most, and can meet the requirement of real time and accuracy.

The photoelectric detection system stands as a crucial instrument for target identification and task execution within diverse environments. The system is frequently confronted with rapid task alterations in the context of communication remote sensing observations. Conventional detection systems encounter challenges in swiftly adapting, underscoring the pressing necessity for an intelligent photoelectric detection system capable of multifaceted tasks and rapid alignment with communication remote sensing settings. This study undertakes a technical exploration of the intelligent photoelectric detection system, delineating the coexistence of semi-intelligent and fully intelligent modes. While the semi-intelligent mode is selected for specific task scenarios, the fully intelligent mode seamlessly takes precedence in the absence of specific tasks. Upon task assignment, the detection mode is designated, automatically calibrating system parameters (operating bands, aperture, integration time, gain, and focal length) in alignment with task requisites. The architecture comprises a detection module capable of seamlessly transitioning between imaging and spectral dimensions, complemented by an autonomous data processing module crafted through DSP+FPGA+ARM technologies. Grounded in this technological foundation, the study designs and employs an intelligent photoelectric detection system to procure communication remote sensing image data, focusing on underwater acoustic signal analysis. The system’s configuration facilitates the creation of a communication remote sensing photoelectric detection mechanism specifically tailored for underwater acoustic signals. Rigorous experimentation involving laser communication in air and sound waves in water culminates in the successful acquisition of communication remote sensing image data. Experimental findings affirm the system’s efficiency in effectively detecting underwater acoustic signals.

Wireless Sensor Network (WSN) is a new technology integrated with communications, embedded technology, and network functions; having capability of real-time collecting, communicating, and sensing, for which dynamic target locating and tracking is its critical task, as well as a basic element in its commercial and military application such as battlefield information accessing and traffic monitoring. Sensor target tracking is the technology of target location estimate based on measurements from corresponding sensors. An inaccurate estimated location may very easily lead to target tracking failure which reduces the reliability and stability of the target tracking [1]. Experts and scholars have done a lot of researches to solve problems exited in wireless sensor target tracking, and many new tracking algorithms have been proposed, among which tracking algorithms such as target contrail-fitting, linear prediction, Kalman filter, unscented Kalman filter(UKF) and particle filter[2] are most common applied. Sikdar, with his partners, has proposed target location tracking algorithm based on linear sensor which is proved better than conventional contrail fitting algorithm in its effects. Zhang Xiaoping , with his partners, has proposed WSN target tracking algorithm through modeling for quadratic polynomial motions which has improved target tracking accuracy[3]. However, there is a problem in common: all the algorithms above assume the tracking target contrail-fittings being in linear motion, while the actual contrail fitting is of uncertainty and variability, and the estimated accuracy can hardly be improved after being to a certain level. In this condition, the tracking error of the above algorithms can be greater [4]. Kalman filter algorithm can be applied for weakly nonlinear models, but for strongly nonlinear models, Unscented Kalman Filter algorithm can be better. Kalman filter work well in cases based on model-linear and Gaussian noise, thus its estimated accuracy is not that ideal [5, 6]. Particle filter algorithm is based on optimal regression Bayesian filtering algorithm in Monte Carlo simulation, which can accurately estimate the any distribution state with only a small amount of mobile anchor nodes. PF algorithm has distinguished advantages in processing non-linear, non-Gaussian cases [7]. However, in PF application process after several iterations, diversified degradation of the particles will occur, which is likely to lead a target tracking loss, thus further affect WSN target tracking accuracy [8]. In order to solve the diversified degradation of the particles in Particle Filter algorithm, this paper Research on the Target Tracking Algorithm for Wireless Sensor Network Based on Improved Particle Filter Liang Peng,Xinhan Huang, Li He

Research on object tracking has been an active field because of its fundamental roles in surveillance and monitoring. In this paper, a new adaptive algorithm for fast target tracking based on hierarchical block matching is proposed. The improvement of the algorithm lies in three aspects. First, the hierarchical pyramid method is applied to enhance the search efficiency of the local features. In addition, at different pyramid level, an adaptive searching strategy is adopted according to the number of candidate features. Second, since image blocks make full use of local characters of features, the structure similarity method, associated with the relation coefficient in statistics, can be exploited to design a new matching criteria, which provides more precise matching results, especially in the complex scenes such as the change of illumination and partial occlusion. Lastly, traditional algorithms often track the object through adjacent frames, whereas our algorithm will search two frames with a variable interval on the basis of matching results. The intervals are obtained by using the bisection method and thus the searching time can be greatly saved. Simulation results show that the proposed block matching method has better performances in the searching time and accuracy in contrast to the classic Mean-Shift target tracking algorithm and Particle Filter target tracking algorithm under the complex circumstances such as illumination variation and partial occlusion.

High tracking frame rates have been achieved based on traditional tracking methods which however would fail due to drifts of the object template or model, especially when the object disappears from the camera’s field of view. To deal with it, tracking-and-detection-combination has become more and more popular for long-term unknown object tracking, whose detector almost does not drift and can regain the disappeared object when it comes back. However, for online machine learning and multiscale object detection, expensive computing resources and time are required. So it is not a good idea to combine tracking and detection sequentially like Tracking-Learning-Detection algorithm. Inspired from parallel tracking and mapping, this article proposes a framework of parallel tracking and detection for unknown object tracking. The object tracking algorithm is split into two separate tasks—tracking and detection which can be processed in two different threads, respectively. One thread is used to deal with the tracking between consecutive frames with a high processing speed. The other thread runs online learning algorithms to construct a discriminative model for object detection. Using our proposed framework, high tracking frame rates and the ability of correcting and recovering the failed tracker can be combined effectively. Furthermore, our framework provides open interfaces to integrate state-of-the-art object tracking and detection algorithms. We carry out an evaluation of several popular tracking and detection algorithms using the proposed framework. The experimental results show that different tracking and detection algorithms can be integrated and compared effectively by our proposed framework, and robust and fast long-term object tracking can be realized.

Vehicle detection and tracking from a UAV perspective often encounters omission and misdetection due to the small targets, complex scenes and target occlusion, which finally influences hugely on detection accuracy and target tracking stability. Additionally, the number of parameters of current model is large that makes it is hard to be deployed on mobile devices. Therefore, this paper proposes a YOLO-LMP and NGCTrack-based target detection and tracking algorithm to address these issues. Firstly, the performance of detecting small targets in occluded scenes is enhanced by adding a MODConv to the small-target detection head and increasing its size; In addition, excessive deletion of prediction boxes is prevented by utilizing LSKAttention mechanism to adaptively adjust the target sensing field at the downsampling stage and combining it with the Soft-NMS strategy. Furthermore, the C2f module is replaced by the FPW to reduce the pointless computation and memory utilization of the model. At the target tracking stage, the so-called NGCTrack in our algorithm replaces IOU with GIOU and employs a modified NSA Kalman filter to adjust the state-space aspect ratio for width prediction. Finally, the camera adjustment mechanism was introduced to improve the precision and consistency of tracking. The experimental results show that, compared to YOLOv8, the YOLO-LMP model improves map50 and map50:95 metrics by 10.3 and 12.2%, respectively and the number of parameters is decreased by 47.7%. After combined it with the improved NGCTrack, the number of IDSW reduced by 73.6% compared to the ByteTrack method, while the MOTA and IDF1 increase by 5.2 and 9.8%, respectively.

As an important part of intelligent vehicle, environmental perception system mainly refers to the detection of the surrounding environment of the vehicle by the sensors attached on the vehicle. In order to ensure the accuracy and stability of the intelligent vehicle environmental perception system, it is necessary to use intelligent vehicle sensors to detect and track objects in the passable area. In this paper, an object detection and tracking algorithm based on the LiDAR and camera information fusion is proposed. The algorithm uses the point cloud data clustering method of LiDAR to detect the objects in the passable area and project them onto the image to determine the tracking objects. After the objects are determined, the algorithm uses color information to track objects in the image sequence. Since the object tracking algorithm based on image is easily affected by light, shadow and background interference, the algorithm uses LiDAR point cloud to modify the tracking results. This paper uses KITTI data set to verify and test this algorithm and experiments show that the target area detection overlap of the proposed target detection and tracking algorithm is 83.10% on average and the tracking success rate is 80.57%. Compared with particle filtering algorithm, the average region overlap increased by 29.47% and the tracking success rate increased by 19.96%.

Feature points and object edges are two kinds of primitives which are frequently used in target tracking algorithms. Feature points can be easily localized in an image. Their correspondences between images can be detected accurately. They can adapt to wide baseline transformations. However, feature points are not so stable that they are fragile to changes in illumination and viewpoint. On the contrary, object edges are stable under a very wide range of illumination and viewpoint changes. Unfortunately, edge-based algorithms often fail in the presence of highly textured targets and clutter which produce too many irrelevant edges. We found that both edge-based and point-based tracking have failure modes which are complementary. Based on this analysis, we propose a novel tracking algorithm which fuses point and edge features. Our tracking algorithm uses feature points matching to track object first, and then uses the transformation parameters archived in the first step to initialize the edge tracking. By this means, our algorithm alleviates the disturbance of irrelevant edges. Then, we use the texture boundary detection algorithm to find the precise object boundary. Texture boundary detection is different from the conventional gradient-based edge detection which can directly compute the most probable location of a texture boundary on the search line. Therefore, it is very fast and can be incorporated into a real-time tracking algorithm. Experimental results show that our tracking algorithm has outstanding tracking accuracy and robustness.

A kind of photoelectric detection method based on black-white bar code and modern photoelectric detection technology is put forward for measuring the displacement deviation of printing press cylinder surface in high-speed motion state. A high-precision noncontact photoelectric detection system is designed and implemented. The accurate testing bar code cooperates with the high-speed A/D mixed signal processing system, the position deviation of every point on the circumference of the printing press system in high-speed measurement state can be obtained, low measurement error which is in the range of ±10μm. The given experiment results indicate that: the system has stable working condition, high measurement speed, and the system provide a new kind of monitoring technology to effectively deal with the overprint deviation.

The Kalman filter has long been regarded as the optimal solution to many applications in computer vision for example the tracking objects, prediction and correction tasks. Its use in the analysis of visual motion has been documented frequently, we can use in computer vision and open cv in different applications in reality for example robotics, military image and video, medical applications, security in public and privacy society, etc. In this paper, we investigate the implementation of a Matlab code for a Kalman Filter using three algorithm for tracking and detection objects in video sequences (block-matching (Motion Estimation) and Camshift Meanshift (localization, detection and tracking object)). The Kalman filter is presented in three steps: prediction, estimation (correction) and update. The first step is a prediction for the parameters of the tracking and detection objects. The second step is a correction and estimation of the prediction parameters. The important application in Kalman filter is the localization and tracking mono-objects and multi-objects are given in results. This works presents the extension of an integrated modeling and simulation tool for the tracking and detection objects in computer vision described at different models of algorithms in implementation systems.

Aiming at the characteristics of small targets, few samples, many occlusions, and strong camouflage in the battlefield environment, a target detection and tracking system based on multi-source sensor data is designed. The system is mainly composed of three parts: the unmanned aerial vehicle (UAV) platform, the ground display control platform (GDCP), and the offline algorithm training platform. The offline-trained target detection and tracking algorithm is deployed in the UAV-borne AI processing chip, which can conduct the real-time detection and tracking of typical targets in the battlefield and send the results and attitude information of UAVs to the GDCP. The system can realize real-time detection of typical battlefield targets and tracking control through the GDCP.