Target Detection System Research Articles

Prediction and Control of Small Deviation in the Time-Delay of the Image Tracker in an Intelligent Electro-Optical Detection System

A small deviation in the time-delay of the image tracker is essential for improving the tracking precision of an electro-optical system, and for future advances in actuator technology. The core goal of this manuscript is to address issues such as tracking the controller time-delay compensation and the precision of an electro-optical detection system using an advanced filter design, a fire control modeling, and an anti-occlusion target detection system. To address this problem, a small deviation in the time-delay prediction and control method of the image tracker is proposed based on the principle of linear motion transformation. The time-delay error formation is analyzed in detail to reveal the scientific mechanism between the tracking controller feedback and the line-of-sight position correction. An advanced N-step Kalman filtering controller model is established by combining a line-of-sight firing control judgment and a single-sample training anti-occlusion DSST target tracking strategy. Finally, an actuator platform with three degrees of freedom is used to test the optical mechatronics system. The results show that the distribution probability of the line-of-sight measuring error in a circle with a radius of 0.15 mrad is 72%. Compared with the traditional control method, the tracking precision of the optimal method is improved by 58.3%.

Improved Convolutional Neural Network YOLOv5 for Underwater Target Detection Based on Autonomous Underwater Helicopter

To detect a desired underwater target quickly and precisely, a real-time sonar-based target detection system mounted on an autonomous underwater helicopter (AUH) using an improved convolutional neural network (CNN) is proposed in this paper. YOLOv5 is introduced as the basic CNN network because of its strength, lightweight and fast speed. Due to the turbidity and weak illumination of an undesirable underwater environment, some attention mechanisms are added, and the structure of YOLOv5 is optimized to improve the performance of the detector for sonar images with a 1–3% increment of mAP which can be up to 80.2% with an average speed of 0.025 s (40 FPS) in the embedded device. It has been verified both in the school tank and outdoor open water that the whole detection system mounted on AUH performs well and meets the requirements of real time and light weight using limited hardware.

A Space-ground Joint Target Detection System Based on Artificial Intelligence

Due to the low efficiency and poor adaptability of template matching in target detection, this paper represents a space-ground joint detection system based on artificial intelligence, which takes advantage of the high computation power of the ground system to train neural networks and utilize the measurement and control channel to update and synchronize the on-orbit system. Based on YOLOv5, an oriented bounding box is used for labeling and training, the angle is considered as a class and the loss for the angle is added to the code. After training the network with the ground system, the weight will be sent to the satellite. This process would repeat once there are new training data that worse the update. Based on the new routine for target detection, the accuracy and robustness are significantly higher than before.

Polarized laser target detection system for smoky environment based on full-waveform decomposition and multiscale convolutional neural networks with attention

To overcome the problem that the smoky environment affects the laser detection performance and generates false alarm, this paper proposes a polarization pulse laser target detection method based on the difference of the polarization information between the target and the smoke, combining full waveform decomposition and Multiple Scale-Attention convolutional neural network with Focal loss function (MSAFCNN). Optimal parameters of the algorithm are obtained by studying the recognition accuracy of the algorithm with different sampling rates and the number of convolution kernels. The polarization pulse laser detection platform is built and the target detection experiments under five different scenarios using infrared lasers are conducted. The polarization echo signals of the smoke and the targets are collected and the recognition accuracy of the proposed algorithm is calculated. The ablation experiments are carried out and MSAFCNN is compared with several advanced algorithms. The experimental results show that the proposed algorithm has the highest recognition accuracy (99.085% ± 0.249%) compared with other algorithms. According to the ablation experiment, the recognition accuracy can be improved by 1.381% using MSAFCNN. The recognition experiments with different sampling rates and numbers of convolutional kernels are performed, and the accuracy of the proposed algorithm can reach 99.348% ± 0.178% at 1 GHz sampling rate and 98.910% ± 0.297% at 500 MHz sampling rate. The optimal number of convolutional kernels is 16, and the number of the algorithm parameters is only 125.273 KB, which provides the feasibility for the subsequent implementation of the algorithm in hardware.

Inference-Optimized High-Performance Photoelectric Target Detection Based on GPU Framework

Deep learning has better detection efficiency than typical methods in photoelectric target detection. However, classical CNNs on GPU frameworks consume too much computing power and memory resources. We propose a multi-stream inference-optimized TensorRT (MSIOT) method to solve this problem effectively. MSIOT uses knowledge distillation to effectively reduce the number of model parameters by layer guidance between CNNs and lightweight networks. Moreover, we use the TensorRT and multi-stream mode to reduce the number of model computations. MSIOT again increases inference speed by 9.3% based on the 4.3–7.2× acceleration of TensorRT. The experimental results show that the model’s mean average accuracy, precision, recall, and F1 score after distillation can reach up to 94.20%, 93.16%, 95.4%, and 94.27%, respectively. It is of great significance for designing a real-time photoelectric target detection system.

Investigation of Autonomous Multi-UAV Systems for Target Detection in Distributed Environment: Current Developments and Open Challenges

Uncrewed aerial vehicles (UAVs), also known as drones, are ubiquitous and their use cases extend today from governmental applications to civil applications such as the agricultural, medical, and transport sectors, etc. In accordance with the requirements in terms of demand, it is possible to carry out various missions involving several types of UAVs as well as various onboard sensors. According to the complexity of the mission, some configurations are required both in terms of hardware and software. This task becomes even more complex when the system is composed of autonomous UAVs that collaborate with each other without the assistance of an operator. Several factors must be considered, such as the complexity of the mission, the types of UAVs, the communication architecture, the routing protocol, the coordination of tasks, and many other factors related to the environment. Unfortunately, although there are many research works that address the use cases of multi-UAV systems, there is a gap in the literature regarding the difficulties involved with the implementation of these systems from scratch. This review article seeks to examine and understand the communication issues related to the implementation from scratch of autonomous multi-UAV systems for collaborative decisions. The manuscript will also provide a formal definition of the ecosystem of a multi-UAV system, as well as a comparative study of UAV types and related works that highlight the use cases of multi-UAV systems. In addition to the mathematical modeling of the collaborative target detection problem in distributed environments, this article establishes a comparative study of communication architectures and routing protocols in a UAV network. After reading this review paper, readers will benefit from the multicriteria decision-making roadmaps to choose the right architectures and routing protocols adapted for specific missions. The open challenges and future directions described in this manuscript can be used to understand the current limitations and how to overcome them to effectively exploit autonomous swarms in future trends.

Performance Analysis of VCA-Based Target Detection System for Maritime Surveillance

In the latest years great importance and research efforts have been put into safety and security aspects concerning the vehicular framework. In this connection, maritime surveillance is playing an important role, since situation awareness proves fundamental to ensure safety conditions at sea. In this work, we propose a novel maritime surveillance system based on Video Content Analysis, where vessel detection is performed automatically by a remote Machine Learning based target identification algorithm. As performance study, we carry out experimental tests analyzing the impact of packet loss, compression rate and transport protocol type on ship-to-ground communication over a satellite link, and their joint effects on video quality, transmission time and vessel detection accuracy.

A real-time omnidirectional target detection system based on FPGA

A real-time omnidirectional target detection system based on FPGA

Real-Time Target Detection System for Animals Based on Self-Attention Improvement and Feature Extraction Optimization

In this paper, we propose a wildlife detection algorithm based on improved YOLOv5s by combining six real wildlife images of different sizes and forms as datasets. Firstly, we use the RepVGG model to simplify the network structure that integrates the ideas of VGG and ResNet. This RepVGG introduces a structural reparameterization approach to ensure model flexibility while reducing the computational effort. This not only enhances the ability of model feature extraction but also speeds up the model computation, further improving the model’s real-time performance. Secondly, we use the sliding window method of the Swin Transformer module to divide the feature map to speed up the convergence of the model and improve the real-time performance of the model. Then, it introduces the C3TR module to segment the feature map, expand the perceptual field of the feature map, solve the problem of backpropagation gradient disappearance and gradient explosion, and enhance the feature extraction and feature fusion ability of the model. Finally, the model is improved by using SimOTA, a positive and negative sample matching strategy, by introducing the cost matrix to obtain the highest accuracy with the minimum cost. The experimental results show that the improved YOLOv5s algorithm proposed in this paper improves mAP by 3.2% and FPS by 11.9 compared with the original YOLOv5s algorithm. In addition, the detection accuracy and detection speed of the improved YOLOv5s model in this paper have obvious advantages in terms of the detection effects of other common target detection algorithms on the animal dataset in this paper, which proves that the improved effectiveness and superiority of the improved YOLOv5s target detection algorithm in animal target detection.

An Ultrasonic Target Detection System Based on Piezoelectric Micromachined Ultrasonic Transducers

In this paper, an ultrasonic target detection system based on Piezoelectric Micromachined Ultrasonic Transducers (PMUTs) is proposed, which consists of the PMUTs based ultrasonic sensor and the sensor system. Two pieces of 3 × 3 PMUTs arrays with the resonant frequency of 115 kHz are used as transmitter and receiver of the PMUTs-based ultrasonic sensor. Then, the sensor system can calculate the target's position through the signal received by the above receiver. The static and dynamic performance of the proposed prototype system are characterized on black, white, and transparent targets. The experiment results demonstrated that the proposed system can detect targets of different colors, transparencies, and motion states. In the static experiments, the static location errors of the proposed system in the range of 200 mm to 320 mm are 0.51 mm, 0.50 mm and 0.53 mm, whereas the errors of a commercial laser sensor are 2.89 mm, 0.62 mm, and N\A. In the dynamic experiments, the experimental materials are the targets with thicknesses of 1 mm, 1.5 mm, 2 mm and 2.5 mm, respectively. The proposed system can detect the above targets with a maximum detection error of 4.00%. Meanwhile, the minimum resolution of the proposed system is about 0.5 mm. Finally, in the comprehensive experiments, the proposed system successfully guides a robotic manipulator to realize the detecting, grasping, and moving of a transparent target with 1 mm. This ultrasonic target detection system has demonstrated a cost-effective method to detect targets, especially transparent targets, which can be widely used in the detection and transfer of glass substrates in automated production lines.

Research on Spaceborne Target Detection Based on Yolov5 and Image Compression

Satellite image compression technology plays an important role in the development of space science. As optical sensors on satellites become more sophisticated, high-resolution and high-fidelity satellite images will occupy more storage. This raises the required transmission bandwidth and transmission rate in the satellite–ground data transmission system. In order to reduce the pressure from image transmission on the data transmission system, a spaceborne target detection system based on Yolov5 and a satellite image compression transmission system is proposed in this paper. It can reduce the pressure on the data transmission system by detecting the object of interest and deciding whether to transmit. An improved Yolov5 network is proposed to detect the small target on the high-resolution satellite image. Simulation results show that the improved Yolov5 network proposed in this paper can detect specific targets in real satellite images, including aircraft, ships, etc. At the same time, image compression has little effect on target detection, so detection complexity can be effectively reduced and detection speed can be improved by detecting the compressed images.

Using deep learning in an embedded system for real-time target detection based on images from an unmanned aerial vehicle: vehicle detection as a case study

ABSTRACT For a majority of remote sensing applications of unmanned aerial vehicles (UAVs), the data need to be downloaded to ground devices for processing, but this procedure cannot satisfy the demands of real-time target detection. Our objective in this study is to develop a real-time system based on an embedded technology for image acquisition, target detection, the transmission and display of the results, and user interaction while providing support for the interactions between multiple UAVs and users. This work is divided into three parts: (1) We design the technical procedure and the framework for the implementation of a real-time target detection system according to application requirements. (2) We develop an efficient and reliable data transmission module to realize real-time cross-platform communication between airborne embedded devices and ground-side servers. (3) We optimize the YOLOv4 algorithm by using the K-Means algorithm and TensorRT inference to improve the accuracy and speed of the NVIDIA Jetson TX2. In experiments involving static detection, it had an overall confidence of 89.6% and a rate of missed detection of 3.8%; in experiments involving dynamic detection, it had an overall confidence and a rate of missed detection of 88.2% and 4.6%, respectively.

Construction Site Multi-Category Target Detection System Based on UAV Low-Altitude Remote Sensing

On-site management of construction sites has always been a significant problem faced by the construction industry. With the development of UAVs, their use to monitor construction safety and progress will make construction more intelligent. This paper proposes a multi-category target detection system based on UAV low-altitude remote sensing, aiming to solve the problems of relying on fixed-position cameras and a single category of established detection targets when mainstream target detection algorithms are applied to construction supervision. The experimental results show that the proposed method can accurately and efficiently detect 15 types of construction site targets. In terms of performance, the proposed method achieves the highest accuracy in each category compared to other networks, with a mean average precision (mAP) of 82.48%. Additionally, by applying it to the actual construction site, the proposed system is confirmed to have comprehensive detection capability and robustness.

Modified Two-Point Correction Method for Wide-Spectrum LWIR Detection System.

Non-uniformity commonly exists in the infrared focal plane, which behaves as the fixed-pattern noise (FPN) and seriously affects the image quality of long-wave infrared (LWIR) detection systems. The two-point correction (TPC) method is commonly used to reduce image FPN in engineering. However, when a wide-spectrum LWIR detection system calibrated with a black body is used to detect weak and small targets in the sky, FPN still appears in the image, affecting its uniformity. The effects of atmospheric transmittance characteristics of long-range paths on the non-uniformity of wide-spectrum long-wave infrared systems have not been studied. This paper proposes a modified TPC model based on spectral subdivision that introduces atmospheric transmittance. Additionally, the effects of atmospheric transmittance characteristics on the long-wave infrared non-uniform correction coefficient are analyzed. The experimental results for a black body scene and sky scene using a weak and small target detection system with a long-wave Sofradir FPA demonstrate that the wide-spectrum LWIR detection system fully considers atmospheric transmittance when performing calibration based on the TPC method, which can reduce the non-uniformity of the image.

Real-Time Target Detection System for Intelligent Vehicles Based on Multi-Source Data Fusion.

To improve the identification accuracy of target detection for intelligent vehicles, a real-time target detection system based on the multi-source fusion method is proposed. Based on the ROS melodic software development environment and the NVIDIA Xavier hardware development platform, this system integrates sensing devices such as millimeter-wave radar and camera, and it can realize functions such as real-time target detection and tracking. At first, the image data can be processed by the You Only Look Once v5 network, which can increase the speed and accuracy of identification; secondly, the millimeter-wave radar data are processed to provide a more accurate distance and velocity of the targets. Meanwhile, in order to improve the accuracy of the system, the sensor fusion method is used. The radar point cloud is projected onto the image, then through space-time synchronization, region of interest (ROI) identification, and data association, the target-tracking information is presented. At last, field tests of the system are conducted, the results of which indicate that the system has a more accurate recognition effect and scene adaptation ability in complex scenes.

Cross-modal guiding and reweighting network for multi-modal RSVP-based target detection

Rapid Serial Visual Presentation (RSVP) based Brain–Computer Interface (BCI) facilities the high-throughput detection of rare target images by detecting evoked event-related potentials (ERPs). At present, the decoding accuracy of the RSVP-based BCI system limits its practical applications. This study introduces eye movements (gaze and pupil information), referred to as EYE modality, as another useful source of information to combine with EEG-based BCI and forms a novel target detection system to detect target images in RSVP tasks. We performed an RSVP experiment, recorded the EEG signals and eye movements simultaneously during a target detection task, and constructed a multi-modal dataset including 20 subjects. Also, we proposed a cross-modal guiding and fusion network to fully utilize EEG and EYE modalities and fuse them for better RSVP decoding performance. In this network, a two-branch backbone was built to extract features from these two modalities. A Cross-Modal Feature Guiding (CMFG) module was proposed to guide EYE modality features to complement the EEG modality for better feature extraction. A Multi-scale Multi-modal Reweighting (MMR) module was proposed to enhance the multi-modal features by exploring intra- and inter-modal interactions. And, a Dual Activation Fusion (DAF) was proposed to modulate the enhanced multi-modal features for effective fusion. Our proposed network achieved a balanced accuracy of 88.00% (±2.29) on the collected dataset. The ablation studies and visualizations revealed the effectiveness of the proposed modules. This work implies the effectiveness of introducing the EYE modality in RSVP tasks. And, our proposed network is a promising method for RSVP decoding and further improves the performance of RSVP-based target detection systems.

Conversion from multi-spectral data into SAR data with Deep Convolution Neural Architecture using Generative Adversarial Network

Synthetic Aperture Radar (SAR) is a high-resolution radar extensively used for aerial and terrestrial images in numerous applications. The SAR images are all weather and day/night capable. It is extensively used in defense/military systems for surveillance, target detection and target tracking. In current times, the need for deep learning algorithms has increased due to its capability of generating SAR images, as it is very intensive and expensive task for the acquisition and formation of SAR images through sensors. Thus, alternative methods are required to produce SAR image data. In this paper, generative adversarial networks (GAN) are used to generate SAR images from a limited pre-existing dataset. This paper presents a novel way of translating optical images to SAR images, for the generation of paired, unpaired data set. Due to the unavailability of an open-source paired, unpaired image dataset, a synthetic paired image dataset is created for proving the concepts of CycleGAN and Pix-to-Pix algorithm by fine tuning the algorithms using generated datasets. The paper tried tackling this problem in two ways, both paired and unpaired image-to-image translation.

Waveform Design of DFRC System for Target Detection in Clutter Environment

Waveform Design of DFRC System for Target Detection in Clutter Environment

Retracted: Deep Learning Target Detection System for Sewage Treatment.

[This retracts the article DOI: 10.1155/2022/2743781.].

Yolo v3-SPP real-time target detection system based on ZYNQ

Yolo v3-SPP real-time target detection system based on ZYNQ