Target In Complex Environment Research Articles

Development of a YOLO-KCF Coupling Algorithm for Miniature Fixed-Wing UAVs in Target Detection and Tracking

Target detection and tracking represent key challenges facing miniature fixed-wing unmanned aerial vehicles (UAVs), particularly at high cruising speeds. Therefore, this paper proposes a vision-based target detection and tracking algorithm that systematically couples two mainstream methods, namely, you only look once (YOLO) and kernel correlation filter (KCF) algorithms. This combination enables small fixed-wing UAVs to achieve reliable target detection and rapid target tracking. A customized vision-guidance module is constructed to implement this algorithm, and a dual-thread execution mechanism is developed to ensure that the computational resources are used effectively. A miniature fixed-wing UAV experimental platform is also constructed and evaluated. Flight experiments are performed, and the results demonstrate that the developed algorithm can achieve satisfactory detection and tracking accuracy for stationary and moving ground targets in complex environments.

Deep learning-based circular disk type radar target detection in complex environment

Target identification is one of the most popular radar uses in real life. Target identification is a classifier that analyzes whether a signal contains an echo from a target (target-present) or is merely noise (target-absent). Deep learning techniques are a popular topic in classification, and they have evinced to be effective in a range of applications. In this paper, a 64 layers Circular Disk type RADAR Target Detection (CDRTD) model is proposed based on Transfer Learning using the SqueezeNet architecture of Convolutional Neural Network (CNN) that functions directly with processed radar target return eco signal and minimize the requirement of conventional laborious radar signal processing. Further, the proposed 64 layers SqueezeNet-based CNN CDRTD model was then implemented to identify circular disk type targets in complex environment. Finally, the target return eco data was tested to identify the circular disk type radar target in complex environments. We further analyzed target detection probability, false alarm rate, precision, recall, F1 in a complex environment and compared it with the ideal case. We found that our proposed CDRTD model can classify 83.3% of the test samples correctly with an overall accuracy of 94.59% in a noisy and cluttered environment whereas 100% of the test samples are classified correctly with an overall accuracy of 100% in an ideal environment.

Vision Transformer With Enhanced Self-Attention for Few-Shot Ship Target Recognition in Complex Environments

Ship target recognition is essential for maritime transportation, commercial trade, maritime security, and monitoring illegal activity. The majority of previous ship target recognition models are based on fully-supervised learning, which necessitates vast amounts of labeled training data. However, optical lenses capturing ship images in natural scenarios have numerous complex environments, making feature extraction difficult due to hardware, weather, light, waves, and other factors. Moreover, image annotation is also both expensive and time-consuming. How to effectively learn from unbalanced, limited, and sparsely annotated sample data is a significant challenge. In this paper, we propose a new vision transformer with enhanced self-attention(SAVT) that can locate ship targets in complex environments with just a few shots. SAVT consists of a novel enhanced self-attention(ESA) module and a novel measurement self-adjusting computation(MAC) module to differentiate unique ship classes in complex environments with few labeled samples. The ESA module focuses on the features of the target-region at each layer of the backbone network in order to ensure that the contour detailed features are extracted effectively from ship images with complex environments. The model is then enhanced in terms of speed and stability by utilizing the MAC module. CIB-ships and public MAR-ships datasets are used to evaluate the proposed method. In this paper, the results demonstrate that SAVT achieves good performance on few-shot labeled data under both 1-shot and 5-shot settings, while also providing valuable guidance for maritime ship target recognition with limited labeled samples.

PD-SegNet: Semantic Segmentation of Small Agricultural Targets in Complex Environments

PD-SegNet: Semantic Segmentation of Small Agricultural Targets in Complex Environments

Tracking of moving targets in complex environments

The tracking of a moving target algorithm based on the traditional visual servo can not introduce image and physical constraints, and does not consider the problems such as the features beyond the camera field of view, the robotic arm’s out-of-motion space, and the robotic arm reaching the joint limit. Moreover, the tracking accuracy and stability of the moving target continue to be poor in complex environments (such as the chaotic background, the illumination changes, and the target is partially occluded), and the recognition of the target image is extremely strict, In this paper, a new method of tracking and grasping moving targets is proposed by combining the pose estimation of targets with the tracking and grasping of industrial robots. Kalman filter is used to compensate for the time delay. This method avoids the influence of traditional methods on target depth estimation and image and physical constraints and has strong robustness.

Foxtail Millet Ear Detection Method Based on Attention Mechanism and Improved YOLOv5.

In the foxtail millet field, due to the dense distribution of the foxtail millet ears, morphological differences among foxtail millet ears, severe shading of stems and leaves, and complex background, it is difficult to identify the foxtail millet ears. To solve these practical problems, this study proposes a lightweight foxtail millet ear detection method based on improved YOLOv5. The improved model proposes to use the GhostNet module to optimize the model structure of the original YOLOv5, which can reduce the model parameters and the amount of calculation. This study adopts an approach that incorporates the Coordinate Attention (CA) mechanism into the model structure and adjusts the loss function to the Efficient Intersection over Union (EIOU) loss function. Experimental results show that these methods can effectively improve the detection effect of occlusion and small-sized foxtail millet ears. The recall, precision, F1 score, and mean Average Precision (mAP) of the improved model were 97.70%, 93.80%, 95.81%, and 96.60%, respectively, the average detection time per image was 0.0181 s, and the model size was 8.12 MB. Comparing the improved model in this study with three lightweight object detection algorithms: YOLOv3_tiny, YOLOv5-Mobilenetv3small, and YOLOv5-Shufflenetv2, the improved model in this study shows better detection performance. It provides technical support to achieve rapid and accurate identification of multiple foxtail millet ear targets in complex environments in the field, which is important for improving foxtail millet ear yield and thus achieving intelligent detection of foxtail millet.

A Robust and Efficient UAV Path Planning Approach for Tracking Agile Targets in Complex Environments

The research into the tracking methods of unmanned aerial vehicles (UAVs) for agile targets is multi-disciplinary, with important application scenarios. Using a quadrotor as an example, in this paper, we mainly researched the tracking-related modeling and application verification of agile targets. We propose a robust and efficient UAV path planning approach for tracking agile targets aggressively and safely. This approach comprehensively takes into account the historical observations of the tracking target and the surrounding environment of the location. It reliably predicts a short time horizon position of the moving target with respect to the dynamic constraints. Firstly, via leveraging the Bernstein basis polynomial and combining obstacle distribution information around the target, the prediction module evaluated the future movement of the target, presuming that it endeavored to stay away from the obstacles. Then, a target-informed dynamic searching method was embraced as the front end, which heuristically searched for a safe tracking trajectory. Secondly, the back-end optimizer ameliorated it into a spatial–temporal optimal and collision-free trajectory. Finally, the tracking trajectory planner generated smooth, dynamically feasible, and collision-free polynomial trajectories in milliseconds, which is consequently reasonable for online target tracking with a restricted detecting range. Statistical analysis, simulation, and benchmark comparisons show that the proposed method has at least 40% superior accuracy compared to the leading methods in the field and advanced capabilities for tracking agile targets.

Revolutionary entrapment model of uniformly distributed swarm robots in morphogenetic formation

This study proposes a method for uniformly revolving swarm robots to entrap multiple targets, which is based on a gene regulatory network, an adaptive decision mechanism, and an improved Vicsek-model. Using the gene regulatory network method, the robots can generate entrapping patterns according to the environmental input, including the positions of the targets and obstacles. Next, an adaptive decision mechanism is proposed, allowing each robot to choose the most well-adapted capture point on the pattern, based on its environment. The robots employ an improved Vicsek-model to maneuver to the planned capture point smoothly, without colliding with other robots or obstacles. The proposed decision mechanism, combined with the improved Vicsek-model, can form a uniform entrapment shape and create a revolving effect around targets while entrapping them. This study also enables swarm robots, with an adaptive pattern formation, to entrap multiple targets in complex environments. Swarm robots can be deployed in the military field of unmanned aerial vehicles’ (UAVs) entrapping multiple targets. Simulation experiments demonstrate the feasibility and superiority of the proposed gene regulatory network method.

MRUNet: A two-stage segmentation model for small insect targets in complex environments

Online automated identification of farmland pests is an important auxiliary means of pest control. In practical applications, the online insect identification system is often unable to locate and identify the target pest accurately due to factors such as small target size, high similarity between species and complex backgrounds. To facilitate the identification of insect larvae, a two-stage segmentation method, MRUNet was proposed in this study. Structurally, MRUNet borrows the practice of object detection before semantic segmentation from Mask R-CNN and then uses an improved lightweight UNet to perform the semantic segmentation. To reliably evaluate the segmentation results of the models, statistical methods were introduced to measure the stability of the performance of the models among samples in addition to the evaluation indicators commonly used for semantic segmentation. The experimental results showed that this two-stage image segmentation strategy is effective in dealing with small targets in complex backgrounds. Compared with existing state-of-the-art semantic segmentation methods, MRUNet shows better stability and detail processing ability under the same conditions. This study provides a reliable reference for the automated identification of insect larvae.

UAV Standoff Tracking for Narrow-Area Target in Complex Environment

This article studies the path planning for an unmanned aerial vehicle (UAV) standoff tracking a narrow-area target in complex environment. Since the target state estimation considerably influences the target tracking performance, the constrained interacting multiple model, which uses the geographic information of narrow-areas to enhance the estimation accuracy, is proposed. Then, based on the obtained estimation results, the dynamic Lyapunov guidance vector field (DLGVF) is proposed, which can guide UAVs to converge to not only the expected standoff distance in the horizontal plane but also the desired height in the vertical plane. Moreover, the DLGVF renders the UAV trajectories flexible and shortens the convergence time by skillfully introducing adjustment parameters. Finally, to simultaneously complete the missions of target tracking and obstacle avoidance, an integrated method based on the DLGVF and the interfered fluid dynamical system is presented. Simulations are implemented to demonstrate that the proposed framework is effective.

Research on camouflage target detection method based on improved YOLOv5

Objective: In the task of camouflage target detection, there is a problem that the target is highly integrated with the complex environment background, which is difficult to identify and leads to false detection and missed detection. A target detection algorithm CM-YOLOv5s is proposed for camouflage characteristics. Method: The algorithm uses YOLOv5s as the basic framework. First, a coordinated attention mechanism is embedded in the backbone feature extraction network, which enhances the network’s ability to extract camouflaged target features, weakens the attention to the surrounding background, and effectively improves the algorithm’s anti-background. Interference ability; secondly, the Mixup data enhancement strategy is used to simulate overlapping occlusion scenarios, which further strengthens the network model’s learning ability for complex samples. Results: The training and verification were carried out on the self-made Military Camouflage Target Dataset (MCTD), and the precision, recall, and average mAP of the improved CM-YOLOv5s algorithm reached 95.9%, 87.1%, and 94.1, respectively. %, compared with the original YOLOv5s model, the average accuracy rate is improved by 3.8 percentage points. Conclusion: The improved algorithm has better detection effect, and realizes accurate identification and rapid positioning of military camouflage targets in complex environments.

Design of cryogenic long-wave infrared detection system

To address the demand for detection of point / dim targets in complex environments, a cryogenic long-wave infrared detection system was designed. In order to improve the target detection capability, the system adopts high-order aspheric surfaces to reduce the number of optical lenses and improve the system transmittance. At the same time, it corrects on-axis / off-axis aberrations and advanced aberrations to improve the imaging quality of the system. In order to effectively reduce the background radiation and improve the system signal-to-noise ratio, the system adopts cryogenic optical technology. Through the scheme design and calculation analysis of the active refrigeration unit, the requirements of the overall and optical technical indicators are met. The outline of the aircraft image obtained by the field experiment is clear and distinguishable, which meets the requirements of target detection. The system has a good application prospect in the field of infrared imaging in early warning systems.

A Study on Small-Scale Ship Detection Based on Attention Mechanism

In ship detection based on optical images, the system typically needs to handle small-scale targets in complex environments owing to special application scenarios, and small-scale targets are easily ignored after a multi-layer convolution is applied in deep learning. A small-ship detection method based on an attention mechanism is therefore proposed in this study. The local attention module acts on the bottom feature prediction layer to highlight the key features and improve the detection ability of small target objects. Meanwhile, a high-level feature prediction layer is combined to classify, detect, and improve the recognition accuracy of the model. In this study, training was conducted on the SeaShips dataset. Because the SeaShips dataset is of a single type and consists of ships of roughly the same size, we changed the size of the default box, which not only improves the detection speed, it also significantly improves the detection accuracy compared with a conventional SSD algorithm.

An Intelligent Signal Processing Method for Motional Vital Signs Detection System Based on Deep Learning

Detection of vital signs for motional human targets in complex environment has always been a major challenge in the field of remote detection, remote healthcare and emergency rescue, because polytropic and multimodal interferences make intelligent signal processing more difficult. In this paper, a systematic intelligent signal processing scheme which contains signal preprocessing, vital signs identification, motion trajectory estimation and respiratory signal and heartbeat signal extraction is established. Based on CNN (Convolutional Neural Networks) model, accurate identification of motional vital signs getting rid of the interference of harmonics and distortion can be realized. Then, the misidentified outliers are eliminated with K-means clustering algorithm. Next, the motion trajectory of human targets can be estimated with Kalman filtering algorithm. Finally, the SVD-EEMD algorithm is proposed for respiratory signal and heartbeat signal extraction of dynamic human targets. The introduction of deep learning algorithms makes the proposed method have good performance of high accuracy, good robustness, strong adaptability and high efficiency, which can be observed in actual detection tasks contrast experiments.

YOLO-G: A Lightweight Network Model for Improving the Performance of Military Targets Detection

Military target detection technology is the foundation and key to perceive and analyze the battlefield situation, and it is also the premise of target tracking technology. Aiming at the task of military target detection, the detection performance of traditional detection algorithms is poor in complex environment. We realize automatic detection of military targets in complex environment through deep learning. In this research, we improve the components of YOLOv3 and propose a novel military target detection algorithm (YOLO-G). We have built a military target dataset composed of armed men with different weapons, which provides a test environment for various object detection algorithms. In the YOLOv3 network structure, by introducing the lightweight convolutional neural network GhostNet as the feature extraction network, the accuracy and speed of military target detection are improved. Then, the attention mechanism based on the coordinate attention block is introduced to enhance the representation ability of target features, suppress interference and improve the detection accuracy. Finally, the loss function of the target detector is redesigned by using DIOU loss function and Focal loss function, which further improves the detection accuracy of our detection model for military targets. We tested YOLO-G on the military target dataset. Experimental results show that our method improves the mAP by 2.9% and the detection speed by 25.9 frames/s compared with the original YOLOv3 algorithm, and the size of the proposed model is reduced to 1/6 of that of YOLOv3. In addition, we also compare our method with state-of-the-art object detection algorithms. The results show that YOLO-G also has superior detection performance, and the mAP index obtained by our method is 1.2% higher than that of the latest YOLOv5 on the premise of meeting the application requirements, which plays an important auxiliary role in the generation and analysis of battlefield situation.

Autonomous Drone Swarm Navigation and Multitarget Tracking With Island Policy-Based Optimization Framework

Swarm intelligence has been applied to replicate numerous natural processes and relatively simple species to achieve excellent performance in a variety of disciplines. An autonomous approach employing deep reinforcement learning is presented in this study for swarm navigation. In this approach, complex 3D environments with static and dynamic obstacles and resistive forces such as linear drag, angular drag, and gravity are modeled to track multiple dynamic targets. In this regard, a novel island policy optimization model is introduced to tackle multiple dynamic targets simultaneously and thus make the swarm more dynamic. Moreover, new reward functions for robust swarm formation and target tracking are devised to learn complex swarm behaviors. Since the number of agents is not fixed and has only the partial observance of the environment, swarm formation and navigation become challenging. In this regard, the proposed strategy consists of four main components to tackle the aforementioned challenges: 1) Island policy-based optimization framework with multiple targets tracking 2) Novel reward functions for multiple dynamic target tracking 3) Improved policy and critic-based framework for the dynamic swarm management 4) Memory. The dynamic swarm management phase translates basic sensory input to high-level commands and thus enhances swarm navigation and decentralized setup while maintaining the swarm’s size fluctuations. While in the island model, the swarm can split into individual sub-swarms according to the number of targets, thus allowing it to track multiple targets that are far apart. Also, when multiple targets come close to each other, these sub-swarms have the ability to rejoin and thus form a single swarm surrounding all the targets. Customized state-of-the-art policy-based deep reinforcement learning neuro-architectures are employed to achieve policy optimization. The results show that the proposed strategy enhances swarm navigation and can track multiple static and dynamic targets in complex environments.

Face mask detection algorithm for multi task recognition in complex environment

The right wearing masks can effectively prevent the spread of viruses. There are usually complex distractions in densely populated environments, which will affect detection tasks of face masks. However, the current detecting algorithm based on Faster R-CNN can not meet mask wearing detection of small targets in complex environments, so this paper puts forward a mask wearing detection algorithm based on the improved Faster R-CNN. This algorithm changes the traditional single RPN network model into one multi-task enhanced RPN model, which can improve the detection and recognition accuracy, the improved Soft-NMS algorithm is used to delete the redundant candidate boxes of regional candidate network output. At the same time, CIoU loss function with better performance, which fully considers the center point distance between the target and the detection frame and improves the accuracy of detection, replaced the original IoU loss function. 3000 sample images are used to do training and experimental verification of the model according to 1:3ratio of positive and negative samples. Experimental results show that compared with the Faster R-CNN algorithm, the algorithm proposed in this paper improves the face detection accuracy and face mask wearing detection by 7.15% and 15.99%respectively. Besides, the average detection accuracy improved by 11.57% and the FPS by 4.6.

Research on the Algorithm of Detection for Small and Weak Target Based on the Mechanism of High-Resolution Amplification

Aiming at the problem that the existing target detection framework based on big data and deep learning has poor recognition effect for small and weak targets with low resolution in complex scenes, in this paper, we improve the small targets detection accuracy and speed, based on the FCOS algorithm for target detection and the mechanism of high resolution amplification. The basic principle is to increase amplification precision gain regression network (R-NET) and amplification region selection algorithm, on the basis of enhanced learning. The former learns the correlation between coarse and fine detection, and the latter calculates the information gain of the amplified region. The results show that this method can detect small and weak targets in complex environment.

Design and analysis of laser photoelectric detection sensor

AbstractIn order to solve the problem of unstable detection and low detection ability of traditional photoelectric detection target in complex environment, a design method of laser photoelectric detection sensor is proposed. Laser photoelectric detection sensor with active and passive laser detection screen is formed by adding line laser to the traditional photoelectric detection target. According to the characteristics of laser echo energy when the projectile passing through the laser detection screen, the calculation model of the laser echo power received by the photoelectric detector under the random intersection of projectile and target is established, and the signal‐to‐noise ratio calculation function of the system is derived. Through the comparative test, the results show that the detection ability of the laser photoelectric detection sensor is obviously better than that of the traditional photoelectric detection target, especially in the low illumination environment; moreover, the signal‐to‐noise ratio of the laser photoelectric detection sensor still follows the law of decreasing with the increase of detection distance, and it keeps the detection characteristics of photoelectric detection system. By increasing the laser emission power, the signal‐to‐noise ratio of the laser photoelectric detection sensor is improved to a certain extent, and the detection ability of the system is improved. The results verify that the design method and theoretical model of photoelectric detection sensor proposed in this paper are scientific and feasible.

A Multi-AUV Path Planning System Based on the Omni-Directional Sensing Ability

Following the development of autonomous underwater vehicles (AUVs), multiple trajectory-based submarine target information collection constitutes one of the key technologies that significantly influence underwater information collection ability and deployment efficiency. In this paper, we propose an underwater information collection AUV, O-AUV, that can perceive the omnidirectional area and could detect a larger area than the traditional AUV. A 3D sensing model for the O-AUV is proposed to describe the complex underwater information collection spaces. Thereafter, a cube-based environment model involving candidate observation point calculation methods are suggested to adapt the O-AUV model. A voyage cost map is also built according to the multi-AUV path planning for a common submarine mission that must traverse numerous mission targets in complex environments through the R-Dijkstra algorithm. Specifically, the voyage planning problem is solved through a critical algorithm called ANSGA (accelerated NSGA-II algorithm), which in turn, is developed by modifying the non-dominated sorting genetic algorithm (NSGA-II) to accelerate the optimization rate for the Pareto solution. Experiments are carried out in MATLAB, and the results verify the validity of the proposed O-AUV+ANSGA algorithm framework.